Self Correspondence Distillation for End-to-End Weakly-Supervised Semantic Segmentation
This work addresses the challenge of training accurate segmentation models with weak supervision, which is important for reducing annotation costs in computer vision, though it appears incremental as it builds on existing end-to-end WSSS methods.
The paper tackles the problem of insufficient semantic information extraction in end-to-end weakly supervised semantic segmentation (WSSS) with image-level labels, proposing a Self Correspondence Distillation method and Variation-aware Refine Module, which significantly outperform state-of-the-art methods on PASCAL VOC 2012 and MS COCO 2014 datasets.
Efficiently training accurate deep models for weakly supervised semantic segmentation (WSSS) with image-level labels is challenging and important. Recently, end-to-end WSSS methods have become the focus of research due to their high training efficiency. However, current methods suffer from insufficient extraction of comprehensive semantic information, resulting in low-quality pseudo-labels and sub-optimal solutions for end-to-end WSSS. To this end, we propose a simple and novel Self Correspondence Distillation (SCD) method to refine pseudo-labels without introducing external supervision. Our SCD enables the network to utilize feature correspondence derived from itself as a distillation target, which can enhance the network's feature learning process by complementing semantic information. In addition, to further improve the segmentation accuracy, we design a Variation-aware Refine Module to enhance the local consistency of pseudo-labels by computing pixel-level variation. Finally, we present an efficient end-to-end Transformer-based framework (TSCD) via SCD and Variation-aware Refine Module for the accurate WSSS task. Extensive experiments on the PASCAL VOC 2012 and MS COCO 2014 datasets demonstrate that our method significantly outperforms other state-of-the-art methods. Our code is available at {https://github.com/Rongtao-Xu/RepresentationLearning/tree/main/SCD-AAAI2023}.