A Self-Distillation Embedded Supervised Affinity Attention Model for Few-Shot Segmentation

Abstract

Few-shot segmentation focuses on the generalization of models to segment unseen object with limited annotated samples. However, existing approaches still face two main challenges. First, huge feature distinction between support and query images causes knowledge transferring barrier, which harms the segmentation performance. Second, limited support prototypes cannot adequately represent features of support objects, hard to guide high-quality query segmentation. To deal with the above two issues, we propose self-distillation embedded supervised affinity attention model to improve the performance of fewshot segmentation task. Specifically, the self-distillation guided prototype module uses self-distillation to align the features of support and query. The supervised affinity attention module generates high-quality query attention map to provide sufficient object information. Extensive experiments prove that our model significantly improves the performance compared to existing methods. Comprehensive ablation experiments and visualization studies also show the significant effect of our method on fewshot segmentation task. On COCO-20 i dataset, we achieve new state-of-the-art results. Training code and pretrained models are available at https://github.com/cv516Buaa/SD-AANet.

CLIP-Driven Prototype Network for Few-Shot Semantic Segmentation

“…Much of the subsequent work has focused on designing different modules to aggregate features of the two types of images using the support set features and query image features extracted through the backbone network. For example, SD-AANet [ 54 ] designs two modules to aggregate fusion features SDPM and SAAM. HSNet [ 55 ] aggregates multi-scale features using 4D convolutional kernels.…”