Estimation of Fractal Dimension and Semantic Segmentation of Motion-Blurred Images by Knowledge Distillation in Autonomous Vehicle
Abstract
1. Introduction
- The knowledge distillation (KD) technique is adopted to improve semantic segmentation performance at a low computational cost, without the additional restoration step for motion-blurred images captured from a vehicle’s front-viewing camera. For this purpose, a KD-based semantic segmentation network (KDS-Net) is proposed.
- A new type of edge-enhanced segmentation loss (EESL) is proposed to utilize edge features that disappear because of motion blur. To achieve this, an edge-mask generator (EMG) is designed to generate an edge mask from ground truth segmentation data, ensuring the KDS-Net’s robustness in edge regions.
- To enhance segmentation performance on objects of various sizes in a motion-blurred environment, multiscale inputs are used for the backbone encoder and decoder architecture, and the shallow convolution module (SCM) is applied to reduce the resultant increase in computational load. Additionally, a feature attention fusion module (FAFM) is proposed to utilize multiscale features.
- Our light KDS-Net minimizes the number of parameters to 21.44 million, demonstrating its ability to operate on embedded systems such as edge computing at real-time speed for real-world vehicle applications. From them, we confirm that KDS-Net can be applied to the edge intelligence-empowered internet of vehicles by removing data privacy concerns and communication overheads caused by transmitting the huge amount of images from a vehicle’s frontal-viewing camera to and receiving the segmentation result from the high computing cloud by 5G technology.
- To analyze the shape level consistency of the segmentation results under motion blur, we incorporate fractal dimension estimation to evaluate the complexity and irregularity of class-specific regions, thereby providing a structural measure of segmentation correctness within the proposed KD framework. In addition, the proposed model and code, along with experimental databases, are disclosed via GitHub (https://github.com/JSI5668/KDS-Net.git (accessed on 13 July 2025)) to facilitate fair evaluation by other researchers.
2. Related Work
2.1. Not Considering Motion Blur
2.1.1. Semantic Segmentation for Real-Time Processing
2.1.2. Semantic Segmentation with High Accuracy
2.2. Considering Motion Blur
2.2.1. Semantic Segmentation with Motion Blur Restoration
2.2.2. Semantic Segmentation Without Motion Blur Restoration
Data Augmentation-Based Method
KD-Based Method
Enhanced Segmentation Model-Based Method
Fusion of KD-Based and Enhanced Segmentation Model-Based Method
3. Proposed Method
3.1. Overview of Proposed Method
3.2. KDS-Net for the Retoration of Motion-Blurred Image
3.2.1. Detail Description of KDS-Net
3.2.2. EMG
3.3. Loss Functions of KDS-Net
3.3.1. Distillation Loss with Vector Quantization
3.3.2. EESL with EMG
3.4. Fractal Dimension Estimation (FDE)
Algorithm 1 Pseudocode for FDE |
Input: BM: Binary masks of a specific semantic class extracted from the ground truth and KDS-Net predictions Output: FD: Fractal dimension 1: Determine the maximum dimension of the box and round it to the nearest power of 2 Max_dimension = max(size(BM)) = 2^[log2(Max_dimension)] 2: If the image size is smaller than , pad the image to match the dimension of if size(BM) < size() Pad_width = ((0, − BM.shape [0]), (0, − BM.shape [1])) Pad_BM = pad(BM, Pad_width, mode = ‘constant’, constant_values = 0) else Pad_BM = BM 3: Initialize an array storing the number of boxes for each dimension size n = zeros(1, + 1) 4: Compute the number of boxes, N( containing at least one pixel of the positive region n[ + 1] = sum(BM [:]) 5: While > 1: a. Reduce the size of by a factor of 2 b. Update the number of boxes N( 6: Compute log(N() and log() for each 7: Fit a line to the points [(log(), log(N()] using the least squares method 8: FD is determined by the slope of the fitted line Return FD |
4. Experimental Results and Analysis
4.1. Experimental Databases and Setup
4.2. Training of KDS-Net
4.3. Testing of Proposed Method
4.3.1. Evaluation Metrics
4.3.2. Testing on CamVid Database
Ablation Studies
Comparative Experiments Between the Proposed and State-of-the-Art (SOTA) Methods
Analysis of Feature Maps by Gradient-Weighted Class Activation Mapping (Grad-CAM)
4.3.3. Testing on KITTI Database
Comparative Experiments Between the Proposed and SOTA Methods
Analysis of Feature Maps by Grad-CAM
Comparisons of Inference Time and Computational Cost
5. Discussions
5.1. Statistical Analysis
5.2. Analysis of Error Cases by Proposed Method
5.3. FD Analysis for Class-Wise Segmentation Quality
5.4. Comparisons of Proposed Method with SOTA Motion Deblurring Researches
6. Conclusions
Author Contributions
Funding
Data Availability Statement
Conflicts of Interest
References
- Gong, L.; Zhang, Y.; Zhang, Y.; Yang, Y.; Xu, W. Erroneous pixel prediction for semantic image segmentation. Comput. Vis. Media 2022, 8, 165–175. [Google Scholar] [CrossRef]
- Wang, Y.; Li, Y.; Elder, J.H.; Wu, R.; Lu, H. Class-conditional domain adaptation for semantic segmentation. Comput. Vis. Media 2024, 10, 1013–1030. [Google Scholar] [CrossRef]
- Jeong, S.I.; Jeong, M.S.; Kang, S.J.; Ryu, K.B.; Park, K.R. SDAN-MD: Supervised dual attention network for multi-stage motion deblurring in frontal-viewing vehicle-camera images. J. King Saud Univ.-Comput. Inf. Sci. 2023, 35, 101556. [Google Scholar] [CrossRef]
- Franchi, G.; Belkhir, N.; Ha, M.L.; Hu, Y.; Bursuc, A.; Blanz, V.; Yao, A. Robust semantic segmentation with superpixel-mix. arXiv 2021, arXiv:2108.00968. [Google Scholar]
- Kamann, C.; Rother, C. Increasing the robustness of semantic segmentation models with painting-by-numbers. In Proceedings of the European Conference on Computer Vision, Glasgow, UK, 23–28 August 2020; Springer: Cham, Switzerland, 2020; pp. 369–387. [Google Scholar]
- Guo, D.; Pei, Y.; Zheng, K.; Yu, H.; Lu, Y.; Wang, S. Degraded image semantic segmentation with dense-gram networks. IEEE Trans. Image Process. 2019, 29, 782–795. [Google Scholar] [CrossRef] [PubMed]
- Vertens, J.; Valada, A.; Burgard, W. SMSnet: Semantic motion segmentation using deep convolutional neural networks. In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Vancouver, BC, Canada, 24–28 September 2017; pp. 582–589. [Google Scholar]
- Yu, Z.; Huang, R.; Byeon, W.; Liu, S.; Liu, G.; Breuel, T.; Anandkumar, A.; Kautz, J. Coupled segmentation and edge learning via dynamic graph propagation. In Proceedings of the Advances in Neural Information Processing Systems, Virtual, 6-14 December 2021; Volume 34, pp. 4919–4932. [Google Scholar]
- Zhang, J.; Yang, K.; Stiefelhagen, R. ISSAFE: Improving semantic segmentation in accidents by fusing event-based data. In Proceedings of the 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Prague, Czech Republic, 27 September–1 October 2021; IEEE: Piscataway, NJ, USA, 2021; pp. 1132–1139. [Google Scholar]
- Rahman, Q.M.; Sunderhauf, N.; Corke, P.; Dayoub, F. FSNet: A failure detection framework for semantic segmentation. IEEE Robot. Autom. Lett. 2022, 7, 3030–3037. [Google Scholar] [CrossRef]
- Zhao, H.; Qi, X.; Shen, X.; Shi, J.; Jia, J. ICNet for real-time semantic segmentation on high-resolution images. In Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany, 8–14 September 2018; pp. 405–420. [Google Scholar]
- Li, G.; Yun, I.; Kim, J.; Kim, J. DABNet: Depth-wise asymmetric bottleneck for real-time semantic segmentation. arXiv 2019, arXiv:1907.11357. [Google Scholar]
- Wu, T.; Tang, S.; Zhang, R.; Cao, J.; Zhang, Y. CGNet: Alight-weight context guided network for semantic segmentation. IEEE Trans. Image Process. 2020, 30, 1169–1179. [Google Scholar] [CrossRef] [PubMed]
- Chen, L.C.; Zhu, Y.; Papandreou, G.; Schroff, F.; Adam, H. Encoder decoder with atrous separable convolution for semantic image segmentation. In Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany, 8–14 September 2018; pp. 801–818. [Google Scholar]
- Fu, J.; Liu, J.; Tian, H.; Li, Y.; Bao, Y.; Fang, Z.; Lu, H. Dual attention network for scene segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA, 15–20 June 2019; pp. 3146–3154. [Google Scholar]
- Wang, J.; Sun, K.; Cheng, T.; Jiang, B.; Deng, C.; Zhao, Y.; Liu, D.; Mu, Y.; Tan, M.; Wang, X. Deep high-resolution representation learning for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 2020, 43, 3349–3364. [Google Scholar] [CrossRef] [PubMed]
- Fan, J.; Li, C.; Liu, X.; Song, M.; Yao, A. Augmentation-Free Dense Contrastive Knowledge Distillation for Efficient Semantic Segmentation. In Proceedings of the 37th Conference on Neural Information Processing Systems (NeurIPS), New Orleans, LA, USA, 10–16 December 2023; pp. 1–13. [Google Scholar]
- Mansourian, A.M.; Jalali, A.; Ahmadi, R.; Kasaei, S. Attention-guided Feature Distillation for Semantic Segmentation. arXiv 2025, arXiv:2403.05451v3. [Google Scholar]
- Liu, L.; Wang, Z.; Phan, M.H.; Zhang, B.; Ge, J.; Liu, Y. BPKD: Boundary Privileged Knowledge Distillation for Semantic Segmentation. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Waikoloa, HI, USA, 3–8 January 2024; pp. 1062–1072. [Google Scholar]
- Hinton, G. Distilling the Knowledge in a Neural Network. arXiv 2015, arXiv:1503.02531. [Google Scholar]
- Yang, C.; Yu, X.; An, Z.; Xu, Y. Categories of response-based, feature-based, and relation-based knowledge distillation. In Advancements in Knowledge Distillation: Towards New Horizons of Intelligent Systems; Springer: Berlin/Heidelberg, Germany, 2023; pp. 1–32. [Google Scholar]
- Zhou, Z.; Rahman Siddiquee, M.M.; Tajbakhsh, N.; Liang, J. Unet++: A nested u-net architecture for medical image segmentation. In Proceedings of the International Workshop on Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support, Granada, Spain, 20 September 2018; pp. 3–11. [Google Scholar]
- Johnson, J.; Alahi, A.; Li, F.-F. Perceptual losses for real time style transfer and super-resolution. In Proceedings of the European Conference on Computer Vision (ECCV), Amsterdam, The Netherlands, 11–14 October 2016; pp. 694–711. [Google Scholar]
- Simonyan, K. Very deep convolutional networks for large-scale image recognition. arXiv 2014, arXiv:1409.1556. [Google Scholar]
- Goodfellow, I.; Pouget-Abadie, J.; Mirza, M.; Xu, B.; Warde-Farley, D.; Ozair, S.; Courville, A.; Bengio, Y. Generative adversarial nets. In Proceedings of the Advances in Neural Information Processing Systems (NeurIPS), Montreal, QC, Canada, 8–13 December; 2014; Volume 27. [Google Scholar]
- Brouty, X.; Garcin, M. Fractal properties; information theory, and market efficiency. Chaos Solitons Fractals 2024, 180, 114543. [Google Scholar] [CrossRef]
- Yin, J. Dynamical fractal: Theory and case study. Chaos Solitons Fractals 2023, 176, 114190. [Google Scholar] [CrossRef]
- Brostow, G.J.; Shotton, J.; Fauqueur, J.; Cipolla, R. Segmentation and recognition using structure from motion point clouds. In Proceedings of the European Conference on Computer Vision, Marseille, France, 12–18 October 2008; pp. 44–57. [Google Scholar]
- Geiger, A.; Lenz, P.; Stiller, C.; Urtasun, R. Vision meets robotics: The KITTI dataset. Int. J. Robot. Res. 2013, 32, 1231–1237. [Google Scholar] [CrossRef]
- Kohavi, R. A study of cross-validation and bootstrap for ac curacy estimation and model selection. In Proceedings of the 14th International Joint Conference on Artificial Intelligence, Montreal, QC, Canada, 20–25 August 1995. [Google Scholar]
- Nah, S.; Kim, T.H.; Lee, K.M. Deep multi-scale convolutional neural network for dynamic scene deblurring. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA, 21–26 July 2017; pp. 3883–3891. [Google Scholar]
- Shen, Z.; Wang, W.; Lu, X.; Shen, J.; Ling, H.; Xu, T.; Shao, L. Human aware motion deblurring. In Proceedings of the IEEE/CVF International Conference on Computer Vision, Seoul, Republic of Korea, 27 October–2 November 2019; pp. 5572–5581. [Google Scholar]
- Rim, J.; Lee, H.; Won, J.; Cho, S. Real-world blur dataset for learning and benchmarking deblurring algorithms. In Proceedings of the European Conference on Computer Vision, Glasgow, UK, 23–28 August 2020; pp. 184–201. [Google Scholar]
- Kupyn, O.; Budzan, V.; Mykhailych, M.; Mishkin, D.; Matas, J. DeblurGAN: Blind motion deblurring using conditional adversarial networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 18–23 June 2018; pp. 8183–8192. [Google Scholar]
- Plompen, A.J.; Cabellos, O.; De Saint Jean, C.; Fleming, M.; Algora, A.; Angelone, M.; Archier, P.; Bauge, E.; Bersillon, O.; Blokhin, A. The joint evaluated fission and fusion nuclear data library, JEFF-3.3. Eur. Phys. J. A 2020, 56, 181. [Google Scholar] [CrossRef]
- NVIDIA. NVIDIA GeForce RTX 30 Series Graphics Cards. 2024. Available online: https://www.nvidia.com/en-us/geforce/graphics-cards/30-series/ (accessed on 13 July 2025).
- Paszke, A.; Gross, S.; Massa, F.; Lerer, A.; Bradbury, J.; Chanan, G.; Killeen, T.; Lin, Z.; Gimelshein, N.; Antiga, L. Pytorch: An imperative style, high-performance deep learning library. In Proceedings of the Advances in Neural Information Processing Systems, Vancouver, BC, Canada, 8–14 December 2019; Volume 32. [Google Scholar]
- Kingma, D.P.; Ba, J. Adam: A method for stochastic optimization. arXiv 2014, arXiv:1412.6980. [Google Scholar]
- Everingham, M.; Eslami, S.A.; Van Gool, L.; Williams, C.K.; Winn, J.; Zisserman, A. The pascal visual object classes challenge: A retrospective. Int. J. Comput. Vis. 2015, 111, 98–136. [Google Scholar] [CrossRef]
- Mongkhonthanaphon, S.; Limpiyakorn, Y. Classification of titanium microstructure with fully convolutional neural networks. J. Phys. Conf. Ser. 2019, 1195, 012022. [Google Scholar] [CrossRef]
- Zamir, S.W.; Arora, A.; Khan, S.; Hayat, M.; Khan, F.S.; Yang, M.H.; Shao, L. Multi-stage progressive image restoration. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA, 20–25 June 2021; pp. 14821–14831. [Google Scholar]
- Chen, L.; Lu, X.; Zhang, J.; Chu, X.; Chen, C. Hinet: Half instance normalization network for image restoration. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA, 20–25 June 2021; pp. 182–192. [Google Scholar]
- Cho, S.J.; Ji, S.W.; Hong, J.P.; Jung, S.W.; Ko, S.J. Rethinking coarse to-fine approach in single image deblurring. In Proceedings of the IEEE/CVF International Conference on Computer Vision, Montreal, BC, Canada, 11–17 October 2021; pp. 4641–4650. [Google Scholar]
- Mao, X.; Liu, Y.; Liu, F.; Li, Q.; Shen, W.; Wang, Y. Intriguing findings of frequency selection for image deblurring. In Proceedings of the AAAI Conference on Artificial Intelligence, Washington, DC, USA, 7–14 February 2023; Volume 37, pp. 1905–1913. [Google Scholar]
- Xu, Y.; Zhu, Y.; Quan, Y.; Ji, H. Attentive deep network for blind motion deblurring on dynamic scenes. Comput. Vis. Image Underst. 2021, 205, 103169. [Google Scholar] [CrossRef]
- Gao, H.; Zhang, Y.; Yang, J.; Dang, D. Mixed hierarchy network for image restoration. Pattern Recognit. 2024, 161, 111313. [Google Scholar] [CrossRef]
- Zhao, H.; Shi, J.; Qi, X.; Wang, X.; Jia, J. Pyramid scene parsing network. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA, 21–26 July 2017; pp. 2881–2890. [Google Scholar]
- Xiao, T.; Liu, Y.; Zhou, B.; Jiang, Y.; Sun, J. Unified perceptual parsing for scene understanding. In Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany, 8–14 September 2018; pp. 418–434. [Google Scholar]
- Hou, Q.; Zhang, L.; Cheng, M.M.; Feng, J. Strip pooling: Rethinking spatial pooling for scene parsing. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA, 13–19 June 2020; pp. 4003–4012. [Google Scholar]
- Xie, E.; Wang, W.; Yu, Z.; Anandkumar, A.; Alvarez, J.M.; Luo, P. SegFormer: Simple and efficient design for semantic seg mentation with transformers. Adv. Neural Inf. Process. Syst. 2021, 34, 12077–12090. [Google Scholar]
- Hong, Y.; Pan, H.; Sun, W.; Jia, Y. Deep dual-resolution networks for real-time and accurate semantic segmentation of road scenes. arXiv 2021, arXiv:2101.06085. [Google Scholar]
- Romero, A.; Ballas, N.; Kahou, S.E.; Chassang, A.; Gatta, C.; Bengio, Y. FitNets: Hints for thin deep nets. arXiv 2014, arXiv:1412.6550. [Google Scholar]
- Zagoruyko, S.; Komodakis, N. Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer. In Proceedings of the International Conference on Learning and Representations (ICLR), Toulon, France, 24–26 April 2017; pp. 1–13. [Google Scholar]
- Tung, F.; Mori, G. Similarity-preserving knowledge distillation. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Republic of Korea, 27 October–2 November 2019; pp. 1365–1374. [Google Scholar]
- Chen, P.; Liu, S.; Zhao, H.; Jia, J. Distilling knowledge via knowledge review. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA, 20–25 June 2021; pp. 5008–5017. [Google Scholar]
- Chen, D.; Mei, J.P.; Zhang, H.; Wang, C.; Feng, Y.; Chen, C. Knowledge Distillation with the Reused Teacher Classifier. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA, 18–24 June 2022; pp. 11933–11942. [Google Scholar]
- Selvaraju, R.R.; Cogswell, M.; Das, A.; Vedantam, R.; Parikh, D.; Batra, D. Grad-cam: Visual explanations from deep networks via gradient-based localization. In Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy, 22–29 October 2017; pp. 618–626. [Google Scholar]
- Cohen, J. A power primer. In Methodological Issues and Strategies in Clinical Research, 4th ed.; Kazdin, A.E., Ed.; American Psychological Association: Washington, DC, USA, 2016; pp. 279–284. [Google Scholar]
Stage | Layer | Filter (Number of Filters, Size) | Stride | Padding | Output |
---|---|---|---|---|---|
1 | Input | - | - | - | 224 224 3 |
DB (X0,0) | 64, 7 7 3 | 2 | 3 3 | 112 112 64 | |
DB (X1,0) | 64, 1 1 64 64, 3 3 64 256, 1 1 64 | 2 | 1 1 | 56 56 256 | |
2 | SCM | 32, 3 3 3 64, 1 1 32 64, 3 3 64 125, 1 1 64 128, 1 1 128 256, 3 3 128 256, 3 3 256 | 1 | 1 1 | 56 56 256 |
FAFM | 256, 1 1 512 16, 1 1 16 256, 1 1 256 | 1 | 1 1 | 56 56 256 | |
DB (X2,0) | 128, 1 1 512 128, 3 3 128 512, 1 1 128 128, 1 1 512 128, 3 3 128 | 1 | 1 1 | 28 28 512 | |
3 | SCM * | - | - | 1 1 | 28 28 512 |
FAFM * | - | - | - | 28 28 512 | |
DB (X3,0) | - | - | 1 1 | 14 14 1024 | |
4 | SCM * | - | - | 1 1 | 14 14 1024 |
FAFM * | - | - | - | 14 14 1024 | |
DB (X4,0) | - | - | 1 1 | 7 7 2048 |
Layer | Filter (Number of Filters, Size) | Output |
---|---|---|
Upsample (X1,0) | - | 112 112 256 |
Concatenate (X0,0, X1,0) | - | 112 112 320 |
DB (X0,1) | 64, 3 3 320 64, 3 3 64 | 112 112 64 |
Upsample (X2,0) | - | 56 56 512 |
Concatenate (X1,0, X2,0) | - | 56 56 768 |
DB (X1,1) | 256, 3 3 768 256, 3 3 256 | 56 56 256 |
Upsample (X3,0) | - | 28 28 1024 |
Concatenate (X2,0, X3,0) | - | 28 28 1536 |
DB (X2,1) | 512, 3 3 1536 512, 3 3 512 | 28 28 512 |
Upsample (X4,0) | - | 14 14 2048 |
Concatenate (X3,0, X4,0) | - | 14 14 3072 |
DB (X3,1) | 256, 3 3 3072 256, 3 3 256 | 14 14 256 |
Upsample (X1,1) | - | 112 112 256 |
Concatenate (X0,0, X0,1, X1,1) | - | 112 112 384 |
DB (X0,2) | 64, 3 3 384 64, 3 3 64 | 112 112 64 |
Upsample (X2,1) | - | 56 56 512 |
Concatenate (X1,0, X1,1, X2,1) | - | 56 56 1024 |
DB (X1,2) | 256, 3 3 1024 256, 3 3 256 | 56 56 256 |
Upsample (X3,1) | - | 28 28 256 |
Concatenate (X2,0, X2,1, X3,1) | - | 28 28 1280 |
DB (X2,2) | 128, 3 3 1280 128, 3 3 128 | 28 28 128 |
Upsample (X1,2) | - | 112 112 256 |
Concatenate (X0,0, X0,1, X0,2, X1,2) | - | 112 112 448 |
DB (X0,3) | 64, 3 3 448 64, 3 3 64 | 112 112 64 |
Upsample (X2,2) | - | 56 56 128 |
Concatenate (X1,0, X1,1, X1,2, X2,2) | - | 56 56 896 |
DB (X1,3) | 64, 3 3 896 64, 3 3 64 | 56 56 64 |
Upsample (X1,3) | - | 112 112 64 |
Concatenate (X0,0, X0,1, X0,2, X0,3, X1,3) | - | 56 56 896 |
DB (X0,4) | 32, 3 3 320 32, 3 3 32 | 112 112 32 |
DB (X0,5) | 16, 3 3 32 16, 3 3 16 12, 3 3 16 | 224 224 12 |
Layer | Filter (Number of Filter, Size, Stride) | Padding | Input Size | Output Size |
---|---|---|---|---|
Input layer | - | - | 224 × 224 × 1 | 224 × 224 × 1 |
1st Conv layer | 16, 3 × 3 × 1, 1 | 1 × 1 | 224 × 224 × 1 | 224 × 224 × 16 |
2nd Conv layer | 32, 3 × 3 × 16, 1 | 1 × 1 | 224 × 224 × 16 | 224 × 224 × 32 |
3rd Conv layer | 64, 3 × 3 × 32, 1 | 1 × 1 | 224 × 224 × 32 | 224 × 224 × 64 |
4th Conv layer | 2, 1 × 1 × 64, 1 | 1 × 1 | 224 × 224 × 64 | 224 × 224 × 2 |
Database | # Images | Size | Class Names (Ratio %) | |
---|---|---|---|---|
CamVid | Subset A | 351 | 320 240 | Sky (15.81), Building (24.10), Pole (0.99), Road (29.33), Sidewalk (6.69), Tree (11.19), Sign symbol (1.08), Fence (1.43), Car (4.64), Pedestrian (0.64), Bicyclist (0.53), Unlabeled (3.57) |
Subset B | 350 | |||
KITTI | Subset A | 223 | 512 176 | Sky (5.89), Building (20.91), Road (17.01), Sidewalk (7.22), Fence (3.14), Tree (34.58), Pole (0.51), Car (7.34), Sign symbol (0.36), Pedestrian (0.07), Bicyclist (0.12), Unlabeled (2.85) |
Subset B | 222 |
Database | Model | Training Time per Epoch |
---|---|---|
CamVid | Teacher model | 82.98 |
Student model | 57.32 | |
KITTI | Teacher model | 49.68 |
Student model | 32.51 |
Method | SCM | FAFM | EMG | KD | VQ |
---|---|---|---|---|---|
Case 1 | |||||
Case 2 | ✓ | ||||
Case 3 | ✓ | ✓ | |||
Case 4 | ✓ | ✓ | ✓ | ||
Case 5 | ✓ | ✓ | ✓ | ✓ | |
Case 6 (proposed) | ✓ | ✓ | ✓ | ✓ | ✓ |
Method | PA | mPA | FW IoU | mIoU |
---|---|---|---|---|
Case 1 | 90.72 | 66.27 | 83.54 | 59.19 |
Case 2 | 91.10 | 69.93 | 84.24 | 61.25 |
Case 3 | 91.62 | 72.78 | 85.18 | 63.86 |
Case 4 | 92.37 | 75.41 | 86.40 | 66.62 |
Case 5 | 93.56 | 79.13 | 88.33 | 71.66 |
Case 6 (proposed) | 93.69 | 79.80 | 88.56 | 72.42 |
Method | 1st Layer | 2nd Layer | 3rd Layer |
---|---|---|---|
Case 1 | ✓ | ||
Case 2 | ✓ | ||
Case 3 | ✓ | ||
Case 4 | ✓ | ✓ | |
Case 5 | ✓ | ✓ | |
Case 6 (proposed) | ✓ | ✓ | ✓ |
Method | PA | mPA | FW IoU | mIoU |
---|---|---|---|---|
Case 1 | 92.88 | 77.78 | 87.24 | 69.65 |
Case 2 | 93.17 | 77.66 | 87.68 | 70.21 |
Case 3 | 93.18 | 77.18 | 87.66 | 70.03 |
Case 4 | 93.30 | 77.71 | 87.87 | 70.04 |
Case 5 | 93.41 | 79.26 | 88.11 | 71.58 |
Case 6 (proposed) | 93.69 | 79.80 | 88.56 | 72.42 |
Method | DB (X1,0) | DB (X2,0) | DB (X3,0) | DB (X4,0) |
---|---|---|---|---|
Case 1 | ✓ | |||
Case 2 | ✓ | |||
Case 3 | ✓ | |||
Case 4 | ✓ | |||
Case 5 (proposed) | ✓ | ✓ | ✓ | ✓ |
Method | PA | mPA | FW IoU | mIoU |
---|---|---|---|---|
Case 1 | 92.73 | 75.22 | 86.91 | 67.74 |
Case 2 | 92.91 | 75.68 | 87.22 | 68.58 |
Case 3 | 92.94 | 76.76 | 87.23 | 69.27 |
Case 4 | 93.05 | 76.45 | 87.43 | 69.41 |
Case 5 (proposed) | 93.56 | 79.13 | 88.33 | 71.66 |
Method | PA | mPA | FW IoU | mIoU | |
---|---|---|---|---|---|
W restoration | DeblurGAN-V2 [34] | 91.54 | 71.75 | 85.04 | 64.69 |
MPRNet [41] | 91.01 | 72.10 | 83.90 | 64.67 | |
HINet [42] | 91.54 | 72.85 | 84.83 | 65.47 | |
MIMO-UNet [43] | 90.41 | 69.44 | 82.93 | 61.97 | |
MIMO-UNet-Plus [43] | 90.66 | 70.17 | 83.34 | 62.76 | |
DeepRFT [44] | 92.08 | 74.03 | 85.73 | 66.64 | |
DeepRFT-Plus [44] | 92.00 | 75.85 | 86.98 | 68.62 | |
Attentive deep [45] | 90.91 | 70.47 | 83.77 | 63.28 | |
MHNet [46] | 90.58 | 70.01 | 83.26 | 62.67 | |
SDAN-MD [3] | 92.89 | 76.82 | 87.10 | 69.58 | |
W/O restoration | PSPNet [47] | 88.98 | 64.56 | 80.65 | 56.04 |
ICNet [11] | 88.29 | 62.39 | 79.60 | 54.27 | |
DeeplabV3-Plus [14] | 89.45 | 67.18 | 81.51 | 59.25 | |
UperNet [48] | 91.01 | 71.03 | 84.00 | 63.15 | |
Alpha blending [15] | 88.93 | 65.68 | 80.72 | 57.95 | |
SPNet [49] | 92.70 | 75.05 | 86.85 | 67.91 | |
HRNet [16] | 92.63 | 76.27 | 86.72 | 68.81 | |
SegFormer [50] | 92.78 | 75.38 | 86.96 | 67.95 | |
DDRNet [51] | 91.65 | 73.73 | 85.96 | 66.21 | |
W/O restoration and W KD | Teacher | 94.33 | 80.72 | 89.55 | 74.76 |
Student | 92.37 | 75.41 | 86.40 | 66.62 | |
Fitnet [52] | 92.30 | 72.31 | 86.14 | 65.85 | |
AT [53] | 91.23 | 69.29 | 84.37 | 63.11 | |
SP [54] | 92.20 | 74.03 | 86.10 | 66.80 | |
ReviewKD [55] | 92.40 | 74.34 | 86.34 | 67.57 | |
SimKD [56] | 92.37 | 74.36 | 86.28 | 67.44 | |
KDS-Net (ours) | 93.69 | 79.80 | 88.56 | 72.42 |
Method | Sky | Building | Pole | Road | Sidewalk | Tree | Sign | Fence | Car | Pedestrian | Bicyclist | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
W restoration | DeblurGAN-V2 [34] | 90.85 | 84.87 | 14.35 | 94.75 | 76.07 | 76.48 | 42.78 | 53.91 | 82.56 | 33.62 | 61.34 |
MPRNet [41] | 89.26 | 83.14 | 18.07 | 95.62 | 79.21 | 67.92 | 41.57 | 48.82 | 83.74 | 40.16 | 63.91 | |
HINet [42] | 89.61 | 84.64 | 17.17 | 95.47 | 78.86 | 72.37 | 42.40 | 51.99 | 83.97 | 38.60 | 65.05 | |
MIMO-UNet [43] | 89.03 | 82.32 | 15.06 | 94.90 | 76.46 | 68.10 | 38.11 | 41.14 | 81.81 | 34.56 | 60.17 | |
MIMO-UNet-Plus [43] | 89.36 | 82.65 | 15.70 | 95.13 | 77.44 | 68.52 | 38.96 | 42.81 | 82.38 | 35.83 | 61.54 | |
DeepRFT [44] | 90.40 | 85.75 | 17.35 | 95.57 | 79.34 | 75.03 | 43.44 | 55.34 | 84.85 | 40.47 | 65.60 | |
DeepRFT-Plus [44] | 91.16 | 87.08 | 18.51 | 95.98 | 80.97 | 78.03 | 45.85 | 60.60 | 85.94 | 43.13 | 67.55 | |
Attentive deep [45] | 89.25 | 83.46 | 16.21 | 94.99 | 77.15 | 70.43 | 38.26 | 48.32 | 82.62 | 35.28 | 60.12 | |
MHNet [46] | 89.06 | 82.76 | 15.64 | 94.81 | 76.32 | 69.56 | 37.59 | 46.29 | 81.68 | 34.63 | 61.02 | |
SDAN-MD [3] | 90.88 | 87.09 | 20.99 | 96.34 | 82.45 | 76.64 | 48.86 | 60.84 | 86.77 | 45.37 | 69.21 | |
W/O restoration | PSPNet [47] | 88.25 | 80.40 | 2.62 | 92.75 | 68.87 | 71.46 | 23.38 | 42.53 | 71.56 | 24.26 | 50.32 |
ICNet [11] | 88.24 | 78.45 | 2.37 | 92.15 | 66.75 | 70.35 | 21.34 | 43.23 | 71.23 | 17.34 | 41.51 | |
DeeplabV3-Plus [14] | 86.52 | 81.51 | 11.58 | 93.59 | 72.74 | 69.75 | 32.98 | 40.69 | 77.94 | 30.20 | 54.20 | |
UperNet [48] | 89.13 | 83.72 | 9.31 | 94.83 | 76.56 | 74.08 | 34.50 | 56.00 | 78.74 | 34.86 | 58.89 | |
Alpha blending [15] | 87.95 | 80.04 | 12.03 | 92.72 | 69.88 | 69.79 | 28.49 | 41.09 | 75.26 | 29.75 | 50.48 | |
SPNet [49] | 90.39 | 86.92 | 15.46 | 96.18 | 82.14 | 78.06 | 42.93 | 65.42 | 84.19 | 39.99 | 65.32 | |
HRNet [16] | 90.91 | 86.56 | 23.28 | 95.95 | 81.44 | 77.78 | 45.14 | 62.45 | 83.05 | 43.62 | 66.74 | |
SegFormer [50] | 91.13 | 86.91 | 12.55 | 96.01 | 81.41 | 79.28 | 46.42 | 64.01 | 83.47 | 41.39 | 64.94 | |
DDRNet [51] | 90.35 | 85.78 | 15.33 | 95.85 | 80.60 | 76.87 | 41.01 | 59.22 | 82.02 | 38.99 | 63.12 | |
W/O Restoration and W KD | Teacher | 91.60 | 89.84 | 25.64 | 97.08 | 86.53 | 82.56 | 62.34 | 73.17 | 86.84 | 53.14 | 73.65 |
Student | 86.95 | 86.34 | 8.79 | 95.57 | 81.31 | 77.82 | 50.99 | 60.00 | 79.79 | 41.75 | 63.51 | |
Fitnet [52] | 90.90 | 85.66 | 18.46 | 95.99 | 80.82 | 77.95 | 47.75 | 58.67 | 80.10 | 30.29 | 57.81 | |
AT [53] | 90.15 | 83.02 | 16.01 | 95.50 | 79.29 | 76.58 | 46.76 | 50.60 | 71.55 | 31.47 | 53.29 | |
SP [54] | 90.78 | 86.02 | 21.48 | 96.14 | 81.70 | 76.03 | 50.23 | 50.78 | 79.56 | 41.38 | 60.70 | |
ReviewKD [55] | 90.75 | 86.58 | 24.56 | 95.86 | 81.03 | 77.18 | 51.20 | 53.66 | 79.76 | 42.37 | 60.28 | |
SimKD [56] | 91.03 | 86.47 | 25.04 | 95.73 | 80.73 | 77.37 | 50.57 | 54.76 | 78.85 | 41.93 | 59.34 | |
KDS-Net (ours) | 91.57 | 88.49 | 27.42 | 96.77 | 84.63 | 80.77 | 54.00 | 67.28 | 86.42 | 48.32 | 70.94 |
Method | PA | mPA | FW IoU | mIoU | |
---|---|---|---|---|---|
W restoration | DeblurGAN-V2 [34] | 84.48 | 56.53 | 74.06 | 48.73 |
MPRNet [41] | 84.56 | 55.50 | 73.66 | 48.33 | |
HINet [42] | 85.59 | 60.70 | 75.29 | 52.29 | |
MIMO-UNet [43] | 84.12 | 53.48 | 72.22 | 46.00 | |
MIMO-UNet-Plus [43] | 84.17 | 54.64 | 73.03 | 47.22 | |
DeepRFT [44] | 85.20 | 59.70 | 74.60 | 50.82 | |
DeepRFT-Plus [44] | 86.86 | 62.05 | 77.19 | 53.82 | |
Attentive deep [45] | 82.87 | 52.32 | 71.16 | 44.70 | |
MHNet [46] | 84.02 | 55.91 | 72.88 | 48.03 | |
SDAN-MD [3] | 87.27 | 63.56 | 77.84 | 55.59 | |
W/O restoration | PSPNet [47] | 82.75 | 52.15 | 71.51 | 43.58 |
ICNet [11] | 77.98 | 45.69 | 65.30 | 36.54 | |
DeeplabV3-Plus [14] | 83.39 | 53.57 | 71.99 | 45.77 | |
UperNet [48] | 87.66 | 61.16 | 78.45 | 53.69 | |
Alpha blending [15] | 78.97 | 52.11 | 65.57 | 43.02 | |
SPNet [49] | 88.07 | 59.53 | 79.02 | 52.69 | |
HRNet [16] | 88.07 | 62.37 | 79.33 | 54.31 | |
SegFormer [50] | 87.67 | 55.99 | 77.73 | 48.99 | |
DDRNet [51] | 87.18 | 59.64 | 77.71 | 52.14 | |
W/O restoration and W KD | Teacher | 93.44 | 66.91 | 87.84 | 62.10 |
Student | 89.29 | 62.67 | 80.98 | 55.60 | |
Fitnet [52] | 89.37 | 64.06 | 81.32 | 55.96 | |
AT [53] | 89.40 | 62.75 | 81.25 | 55.41 | |
SP [54] | 89.62 | 62.95 | 81.62 | 56.05 | |
ReviewKD [55] | 89.60 | 67.19 | 81.71 | 57.74 | |
SimKD [56] | 89.76 | 62.95 | 81.77 | 56.23 | |
KDS-Net (ours) | 90.10 | 66.61 | 82.36 | 59.29 |
Method | Sky | Building | Road | Sidewalk | Fence | Tree | Pole | Car | Sign | Pedestrian | Bicyclist | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
W restoration | DeblurGAN-V2 [34] | 87.15 | 73.24 | 79.03 | 51.62 | 35.96 | 80.54 | 7.50 | 70.92 | 23.58 | 16.09 | 10.38 |
MPRNet [41] | 85.80 | 71.02 | 80.76 | 53.04 | 28.89 | 79.96 | 15.27 | 72.92 | 24.64 | 14.30 | 5.05 | |
HINet [42] | 83.94 | 72.55 | 82.93 | 57.03 | 36.90 | 80.45 | 15.58 | 76.43 | 27.89 | 29.95 | 11.60 | |
MIMO-UNet [43] | 84.12 | 70.39 | 79.49 | 50.64 | 23.54 | 79.13 | 8.95 | 69.28 | 19.07 | 16.71 | 4.70 | |
MIMO-UNet-Plus [43] | 85.27 | 71.25 | 80.09 | 51.65 | 25.28 | 79.63 | 10.06 | 70.85 | 19.83 | 16.39 | 9.14 | |
DeepRFT [44] | 85.99 | 72.62 | 81.53 | 54.70 | 31.73 | 80.01 | 14.26 | 73.40 | 26.32 | 26.81 | 11.35 | |
DeepRFT-Plus [44] | 87.23 | 75.82 | 83.13 | 57.10 | 39.54 | 82.43 | 15.27 | 74.15 | 29.69 | 30.69 | 12.42 | |
Attentive deep [45] | 81.77 | 69.13 | 78.24 | 50.19 | 26.17 | 78.65 | 9.87 | 65.36 | 15.10 | 14.77 | 2.52 | |
MHNet [46] | 84.13 | 70.24 | 80.37 | 53.15 | 28.73 | 79.23 | 13.38 | 70.60 | 22.30 | 20.82 | 5.38 | |
SDAN-MD [3] | 87.86 | 75.66 | 84.10 | 59.13 | 39.53 | 82.53 | 18.11 | 82.08 | 31.10 | 35.42 | 15.95 | |
W/O restoration | PSPNet [47] | 79.65 | 71.95 | 74.73 | 48.67 | 30.55 | 79.43 | 7.69 | 67.80 | 15.08 | 2.18 | 1.68 |
ICNet [11] | 81.12 | 69.62 | 56.76 | 38.78 | 14.58 | 78.28 | 1.03 | 55.71 | 6.01 | 0.00 | 0.00 | |
DeeplabV3-Plus [14] | 80.43 | 69.99 | 79.46 | 52.03 | 29.13 | 79.58 | 10.50 | 64.33 | 19.63 | 13.17 | 5.18 | |
UperNet [48] | 87.61 | 78.19 | 86.16 | 58.53 | 42.60 | 84.74 | 14.71 | 73.44 | 28.57 | 24.40 | 14.17 | |
Alpha blending [15] | 78.84 | 65.70 | 74.57 | 43.52 | 28.18 | 69.12 | 11.77 | 62.32 | 19.69 | 11.46 | 8.09 | |
SPNet [49] | 87.45 | 78.23 | 85.45 | 60.02 | 43.44 | 84.53 | 12.20 | 76.23 | 25.76 | 12.62 | 13.66 | |
HRNet [16] | 88.43 | 78.22 | 85.42 | 61.89 | 42.13 | 84.29 | 21.31 | 79.03 | 27.11 | 17.28 | 12.16 | |
SegFormer [50] | 87.96 | 77.13 | 83.61 | 57.85 | 39.28 | 84.31 | 8.49 | 72.29 | 19.58 | 5.58 | 2.80 | |
DDRNet [51] | 86.68 | 76.65 | 84.35 | 59.69 | 37.47 | 83.20 | 16.87 | 75.82 | 25.00 | 16.55 | 11.27 | |
W/O Restoration and W KD | Teacher | 91.12 | 86.36 | 94.15 | 81.53 | 70.49 | 89.64 | 16.09 | 88.52 | 56.36 | 6.77 | 2.04 |
Student | 86.51 | 78.64 | 86.93 | 64.50 | 50.48 | 86.25 | 14.03 | 82.13 | 39.69 | 13.56 | 8.82 | |
Fitnet [52] | 87.51 | 79.22 | 87.47 | 65.88 | 48.26 | 86.45 | 13.48 | 81.65 | 40.60 | 12.99 | 12.10 | |
AT [53] | 88.10 | 79.44 | 86.97 | 65.41 | 47.86 | 86.35 | 12.08 | 82.04 | 38.16 | 10.39 | 12.73 | |
SP [54] | 88.13 | 79.78 | 87.97 | 66.88 | 48.22 | 86.22 | 18.37 | 82.18 | 39.12 | 11.66 | 8.03 | |
ReviewKD [55] | 88.51 | 79.45 | 87.76 | 66.50 | 49.99 | 86.42 | 22.50 | 82.60 | 42.75 | 16.53 | 12.08 | |
SimKD [56] | 87.92 | 79.67 | 88.37 | 67.52 | 48.42 | 86.28 | 19.08 | 92.77 | 37.15 | 12.85 | 8.54 | |
KDS-Net (ours) | 89.81 | 81.45 | 87.63 | 66.42 | 50.87 | 86.53 | 23.25 | 84.14 | 38.99 | 25.51 | 17.58 |
Method | Inference Time/Inference Speed | ||
---|---|---|---|
Desktop | Jetson Embedded System | ||
W restoration | DeblurGAN-V2 [34] | 40.94/24.43 | 198.98/5.03 |
MPRNet [41] | 47.52/21.04 | 551.79/1.81 | |
HINet [42] | 18.55/53.91 | 92.39/10.82 | |
MIMO-UNet [43] | 21.04/47.53 | 101.18/9.88 | |
MIMO-UNet-Plus [43] | 35.63/28.07 | 308.77/3.24 | |
DeepRFT [44] | 37.62/26.58 | 420.53/2.38 | |
DeepRFT-Plus [44] | 77.87/12.84 | 1400.37/0.71 | |
Attentive deep [45] | 66.65/15.00 | 704.97/1.42 | |
MHNet [46] | 56.01/17.85 | 387.12/2.58 | |
SDAN-MD [3] | 48.68/20.54 | 648.44/1.54 | |
W/O restoration | PSPNet [47] | 8.45/118.34 | 41.63/24.02 |
ICNet [11] | 13.48/74.18 | 57.39/17.42 | |
DeeplabV3-Plus [14] | 7.47/133.87 | 41.46/24.12 | |
UperNet [48] | 8.24/121.36 | 42.52/23.52 | |
Alpha blending [15] | 7.45/134.23 | 41.46/24.12 | |
SPNet [49] | 17.93/55.77 | 74.89/13.35 | |
HRNet [16] | 40.61/24.62 | 154.00/6.49 | |
SegFormer [50] | 6.29/158.98 | 31.64/31.61 | |
DDRNet [51] | 6.94/144.09 | 27.01/37.02 | |
Proposed (KDS-Net) | 6.29/158.98 | 32.18/31.08 |
Method | # Parameters (Unit: Mega) | GPU Memory Requirement (Unit: Mega Byte) | FLOPs (Unit: Giga) | |
---|---|---|---|---|
W restoration | DeblurGAN-V2 [34] | 44.85 | 678.81 | 102.4 |
MPRNet [41] | 59.89 | 1306.02 | 1982.4 | |
HINet [42] | 128.43 | 678.81 | 464.16 | |
MIMO-UNet [43] | 46.57 | 1149.11 | 205.52 | |
MIMO-UNet-Plus [43] | 55.87 | 2024.62 | 423.82 | |
DeepRFT [44] | 49.31 | 2009.62 | 48.82 | |
DeepRFT-Plus [44] | 62.73 | 4176.38 | 49.70 | |
Attentive deep network [45] | 46.67 | 7497.51 | 542.73 | |
MHNet [46] | 56.79 | 5276.01 | 157.34 | |
SDAN-MD [3] | 60.09 | 7719.86 | 2363.33 | |
W/O restoration | PSPNet [47] | 48.76 | 548.73 | 115.57 |
ICNet [11] | 28.30 | 186.28 | 28.30 | |
DeeplabV3-Plus [14] | 39.76 | 333.51 | 37.38 | |
UperNet [48] | 37.28 | 349.12 | 47.98 | |
Alpha blending [15] | 39.76 | 333.51 | 37.38 | |
SPNet [49] | 60.61 | 895.58 | 155.16 | |
HRNet [16] | 65.85 | 622.52 | 58.72 | |
SegFormer [50] | 3.72 | 105.16 | 4.26 | |
DDRNet [51] | 5.73 | 56.59 | 3.06 | |
Proposed (KDS-Net) | 21.44 | 607.74 | 112.42 |
Results | R2 | C | FD | |
---|---|---|---|---|
Figure 14a | Ground truth | 0.98226 | 0.99109 | 1.41403 |
Predict | 0.98211 | 0.99102 | 1.41657 | |
Figure 14b | Ground truth | 0.97282 | 0.98632 | 1.32727 |
Predict | 0.97406 | 0.98695 | 1.33675 | |
Figure 14c | Ground truth | 0.98244 | 0.99118 | 1.40099 |
Predict | 0.98273 | 0.99133 | 1.39811 | |
Figure 14d | Ground truth | 0.98880 | 0.99438 | 1.47055 |
Predict | 0.99115 | 0.99556 | 1.47309 |
Method | PA | mPA | FW IoU | mIoU |
---|---|---|---|---|
DeblurGAN-V2 [34] | 91.54 | 71.75 | 85.04 | 64.69 |
MPRNet [41] | 91.01 | 72.10 | 83.90 | 64.67 |
HINet [42] | 91.54 | 72.85 | 84.83 | 65.47 |
MIMO-UNet [43] | 90.41 | 69.44 | 82.93 | 61.97 |
MIMO-Unet-Plus [43] | 90.66 | 70.17 | 83.34 | 62.76 |
DeepRFT [44] | 92.08 | 74.03 | 85.73 | 66.64 |
DeepRFT-Plus [44] | 92.00 | 75.85 | 86.98 | 68.62 |
Attentive deep [45] | 90.91 | 70.47 | 83.77 | 63.28 |
MHNet [46] | 90.58 | 70.01 | 83.26 | 62.67 |
SDAN-MD [3] | 92.89 | 76.82 | 87.10 | 69.58 |
KDS-Net (ours) | 93.69 | 79.80 | 88.56 | 72.42 |
Method | PA | mPA | FW IoU | mIoU |
---|---|---|---|---|
DeblurGAN-V2 [34] | 84.48 | 56.53 | 74.06 | 48.73 |
MPRNet [41] | 84.56 | 55.50 | 73.66 | 48.33 |
HINet [42] | 85.59 | 60.70 | 75.29 | 52.29 |
MIMO-Unet [43] | 84.12 | 53.48 | 72.22 | 46.00 |
MIMO-Unet-Plus [43] | 84.17 | 54.64 | 73.03 | 47.22 |
DeepRFT [44] | 85.20 | 59.70 | 74.60 | 50.82 |
DeepRFT-Plus [44] | 86.86 | 62.05 | 77.19 | 53.82 |
Attentive deep [45] | 82.87 | 52.32 | 71.16 | 44.70 |
MHNet [46] | 84.02 | 55.91 | 72.88 | 48.03 |
SDAN-MD [3] | 87.27 | 63.56 | 77.84 | 55.59 |
KDS-Net (ours) | 90.10 | 66.61 | 82.36 | 59.29 |
Method | # Parameters (Unit: Mega) | GPU Memory Requirement (Unit: Mega Byte) | FLOPs (Unit: Giga) |
---|---|---|---|
DeblurGAN-V2 [34] | 44.85 | 678.81 | 102.4 |
MPRNet [41] | 59.89 | 1306.02 | 1982.4 |
HINet [42] | 128.43 | 678.81 | 464.16 |
MIMO-UNet [43] | 46.57 | 1149.11 | 205.52 |
MIMO-UNet-Plus [43] | 55.87 | 2024.62 | 423.82 |
DeepRFT [44] | 49.31 | 2009.62 | 48.82 |
DeepRFT-Plus [44] | 62.73 | 4176.38 | 49.70 |
Attentive deep network [45] | 46.67 | 7497.51 | 542.73 |
MHNet [46] | 56.79 | 5276.01 | 157.34 |
SDAN-MD [3] | 60.09 | 7719.86 | 2363.33 |
Proposed (KDS-Net) | 21.44 | 607.74 | 112.42 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Jeong, S.I.; Jeong, M.S.; Park, K.R. Estimation of Fractal Dimension and Semantic Segmentation of Motion-Blurred Images by Knowledge Distillation in Autonomous Vehicle. Fractal Fract. 2025, 9, 460. https://doi.org/10.3390/fractalfract9070460
Jeong SI, Jeong MS, Park KR. Estimation of Fractal Dimension and Semantic Segmentation of Motion-Blurred Images by Knowledge Distillation in Autonomous Vehicle. Fractal and Fractional. 2025; 9(7):460. https://doi.org/10.3390/fractalfract9070460
Chicago/Turabian StyleJeong, Seong In, Min Su Jeong, and Kang Ryoung Park. 2025. "Estimation of Fractal Dimension and Semantic Segmentation of Motion-Blurred Images by Knowledge Distillation in Autonomous Vehicle" Fractal and Fractional 9, no. 7: 460. https://doi.org/10.3390/fractalfract9070460
APA StyleJeong, S. I., Jeong, M. S., & Park, K. R. (2025). Estimation of Fractal Dimension and Semantic Segmentation of Motion-Blurred Images by Knowledge Distillation in Autonomous Vehicle. Fractal and Fractional, 9(7), 460. https://doi.org/10.3390/fractalfract9070460