Next Article in Journal
Adaptive Multi-Objective Optimization for UAV-Assisted Wireless Powered IoT Networks
Previous Article in Journal
Revealing Short-Term Memory Communication Channels Embedded in Alphabetical Texts: Theory and Experiments
Previous Article in Special Issue
Optimized Deep Learning for Mammography: Augmentation and Tailored Architectures
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Article

SAM-Based Input Augmentations and Ensemble Strategies for Image Segmentation

Department of Information Engineering, University of Padova, 35122 Padua, Italy
*
Author to whom correspondence should be addressed.
These authors contributed equally to this work.
Information 2025, 16(10), 848; https://doi.org/10.3390/info16100848
Submission received: 6 August 2025 / Revised: 25 September 2025 / Accepted: 29 September 2025 / Published: 30 September 2025
(This article belongs to the Special Issue Applications of Deep Learning in Bioinformatics and Image Processing)

Abstract

Despite the remarkable progress of deep learning in image segmentation, models often struggle with generalization across diverse datasets. This study explores novel input augmentation techniques and ensemble strategies to improve image segmentation performance. We investigate how the Segment Anything Model (SAM) can produce relevant information for model training. We believe that SAM offers a promising source of prior information that can be exploited to improve robustness and accuracy. Building on this, we propose input augmentation techniques that integrate SAM information directly into the images, enhancing the learning process of segmentation models. Each proposed augmentation method comes with its unique advantages; therefore, to leverage the strengths of each approach, we introduce AuxMix, a model trained with a combination of SAM-based augmentation methods. We conduct experiments on different state-of-the-art segmentation models, evaluating the effects of each method independently and within an ensemble framework. The results show that our ensemble strategy, combining complementary information from each augmentation, leads to robust and improved segmentation performance in a large set of datasets. We use only publicly available datasets in our experiments, and all the code developed to reproduce our results is available online on GitHub.
Keywords: image segmentation; input augmentation; ensembles; deep neural networks image segmentation; input augmentation; ensembles; deep neural networks

Share and Cite

MDPI and ACS Style

Carisi, L.; Chiereghin, F.; Fantozzi, C.; Nanni, L. SAM-Based Input Augmentations and Ensemble Strategies for Image Segmentation. Information 2025, 16, 848. https://doi.org/10.3390/info16100848

AMA Style

Carisi L, Chiereghin F, Fantozzi C, Nanni L. SAM-Based Input Augmentations and Ensemble Strategies for Image Segmentation. Information. 2025; 16(10):848. https://doi.org/10.3390/info16100848

Chicago/Turabian Style

Carisi, Lorenzo, Francesco Chiereghin, Carlo Fantozzi, and Loris Nanni. 2025. "SAM-Based Input Augmentations and Ensemble Strategies for Image Segmentation" Information 16, no. 10: 848. https://doi.org/10.3390/info16100848

APA Style

Carisi, L., Chiereghin, F., Fantozzi, C., & Nanni, L. (2025). SAM-Based Input Augmentations and Ensemble Strategies for Image Segmentation. Information, 16(10), 848. https://doi.org/10.3390/info16100848

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop