Image Recognition and Segmentation Based on Neural Networks

Dear Colleagues,

Image recognition and semantic image segmentation have wide applications in many fields. For example, in autonomous vehicles, image segmentation is crucial because it provides the necessary context information for pixel-level scene understanding in order for actions to be taken. In addition, in the field of remote sensing, the fusion and interpretation of optical and SAR images can obtain comprehensive target element information. Image recognition and segmentation are widely used in target search and land resource surveys. Recent developments in deep learning have provided many ways to effectively solve this problem with improved accuracy.

In recent years, the development of image recognition and segmentation has been greatly promoted by the development of neural networks; in particular, CNN and Transformer have been proposed as solid networks for this type of endeavor.

A large number of excellent network architectures such as ResNet, Deeplab, U-Net, Bert, GPT, etc., have also been proposed. Recently, the visual foundation model based on the Vit and Swin framework has further improved the accuracy of image recognition and segmentation. Pre-training foundational models and their "pre-training-fine-tuning" methods have become the mainstream paradigm of image processing tasks. Visual prompt engineering and adaptor module have become emerging research directions. In addition, due to the limited feature expression ability of single modal data, learning the information of each modal from multi-modality to improve the recognition and segmentation accuracy has also become a frequently debated issue. The goal of this Special Issue is to provide a forum to bring together different ideas related to multi-modal data processing, the foundation model and self-supervised, semi-supervised learning for image recognition and segmentation.

In this Special Issue, original research articles and reviews are welcome. Research areas may include (but are not limited to) the following:

•  Foundation model architecture design；
•  Semi-supervised methods for recognition and segmentation；
•  Multi-modal processing；
•  Fine-grained object detection and recognition;
• Visual prompter for image recognition segmentation;
• Adaptor for image recognition and segmentation;
• Lightweight model for image recognition and segmentation;
• Multi-task for image recognition;
• Autonomous vehicle;
• Open-vocabulary image recognition and segmentation.

Dr. Wenkai Zhang
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Electronics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• image recognition
• image segmentation
• foundation model
• unsupervised learning
• multi-modal processing
• adaptor
• lightweight
• visual prompter
• multi-task
• open-vocabulary