Few-Shot Semantic Segmentation Network for Distinguishing Positive and Negative Examples
Open Access
- 26 March 2025
- journal article
- research article
- Published by MDPI AG in Applied Sciences
- Vol. 15 (7) , 3627
Abstract
Few-shot segmentation (FSS) aims to segment a query image with a few support images. However, there can be large differences between images from the same category, and similarities between different categories, making it a challenging task. In addition, most FSS methods use powerful encoders to extract features from the training class, which makes the model pay more attention to the features of the ‘seen’ class, and perform poorly on the segmentation task of ‘unseen’ classes. In this work, we propose a novel end-to-end model, called GFormer. GFormer has four components: encoder, prototype extractor, adversarial prototype generator, and decoder. Our encoder makes simple modifications to VIT to reduce the focus on image content, using a prototype extractor to extract prototype features from a range of support images. We further introduce different classes that are similar to the support image categories as negative examples, taking the support image categories as positive examples. We use the adversarial prototype generator to extract the adversarial prototypes from the positive and negative examples. The decoder segments the query images under the guidance of the prototypes. We conduct extensive experiments on a variety of unknown classes. The results verify the feasibility of the proposed model and prove that the proposed model has strong generalization performance for new classes.Keywords
This publication has 14 references indexed in Scilit:
- Adaptive Agent Transformer for Few-Shot Segmentation2022
- Masked-attention Mask Transformer for Universal Image Segmentation2022
- Segmenter: Transformer for Semantic Segmentation2021
- Rethinking and Improving Relative Position Encoding for Vision Transformer2021
- Generative adversarial networksCommunications of the ACM, 2020
- SG-One: Similarity Guidance Network for One-Shot Semantic SegmentationIEEE Transactions on Cybernetics, 2020
- FSS-1000: A 1000-Class Dataset for Few-Shot Segmentation2020
- CANet: Class-Agnostic Segmentation Networks With Iterative Refinement and Attentive Few-Shot Learning2019
- Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation2018
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009