|国家预印本平台
首页|Completely Weakly Supervised Class-Incremental Learning for Semantic Segmentation

Completely Weakly Supervised Class-Incremental Learning for Semantic Segmentation

Completely Weakly Supervised Class-Incremental Learning for Semantic Segmentation

来源:Arxiv_logoArxiv
英文摘要

This work addresses the task of completely weakly supervised class-incremental learning for semantic segmentation to learn segmentation for both base and additional novel classes using only image-level labels. While class-incremental semantic segmentation (CISS) is crucial for handling diverse and newly emerging objects in the real world, traditional CISS methods require expensive pixel-level annotations for training. To overcome this limitation, partially weakly-supervised approaches have recently been proposed. However, to the best of our knowledge, this is the first work to introduce a completely weakly-supervised method for CISS. To achieve this, we propose to generate robust pseudo-labels by combining pseudo-labels from a localizer and a sequence of foundation models based on their uncertainty. Moreover, to mitigate catastrophic forgetting, we introduce an exemplar-guided data augmentation method that generates diverse images containing both previous and novel classes with guidance. Finally, we conduct experiments in three common experimental settings: 15-5 VOC, 10-10 VOC, and COCO-to-VOC, and in two scenarios: disjoint and overlap. The experimental results demonstrate that our completely weakly supervised method outperforms even partially weakly supervised methods in the 15-5 VOC and 10-10 VOC settings while achieving competitive accuracy in the COCO-to-VOC setting.

David Minkwan Kim、Soeun Lee、Byeongkeun Kang

计算技术、计算机技术

David Minkwan Kim,Soeun Lee,Byeongkeun Kang.Completely Weakly Supervised Class-Incremental Learning for Semantic Segmentation[EB/OL].(2025-05-15)[2025-07-16].https://arxiv.org/abs/2505.10781.点此复制

评论