# Self Correspondence Distillation for End-to-End Weakly-Supervised Semantic Segmentation Source: [Self Correspondence Distillation for End-to-End Weakly-Supervised Semantic Segmentation]() Collection index: [llms.txt]() Data updated: 2025-10-26T01:03:50.423Z Authors: Rongtao Xu, Changwei Wang, Jiaxi Sun, Shibiao Xu, Weiliang Meng, Xiaopeng Zhang Published: 2023-02-27T13:46:40.000Z ## Abstract 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}. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Semantic Segmentation on COCO 2017 (val)](): Semantic segmentation; COCO 2017 (val); mIoU: 40.1. - [Semantic Segmentation on COCO (val)](): Semantic segmentation; COCO (val); mIoU: 40.1. - [Semantic Segmentation on Pascal VOC 2012 (val) (Resolution-Dependent mIoU)](): Semantic segmentation; PASCAL VOC 2012 (val); mIoU: 67.3. - [Semantic Segmentation on COCO 2014 (val)](): Semantic segmentation; COCO 2014 (val); mIoU: 40.1. - [Semantic Segmentation on PASCAL VOC 2012 (test)](): Semantic segmentation; PASCAL VOC 2012 (test); mIoU: 67.5. - [Semantic Segmentation on PASCAL VOC 2012 (val)](): Semantic segmentation; PASCAL VOC 2012 (val); Mean IoU: 67.3. ## Original sources and implementation [Original paper]() [PDF]()