Completely Weakly Supervised Class-Incremental Learning for Semantic Segmentation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kim, David Minkwan, Lee, Soeun, Kang, Byeongkeun
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913841536827392
author Kim, David Minkwan
Lee, Soeun
Kang, Byeongkeun
author_facet Kim, David Minkwan
Lee, Soeun
Kang, Byeongkeun
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_10781
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Completely Weakly Supervised Class-Incremental Learning for Semantic Segmentation
Kim, David Minkwan
Lee, Soeun
Kang, Byeongkeun
Computer Vision and Pattern Recognition
Artificial Intelligence
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.
title Completely Weakly Supervised Class-Incremental Learning for Semantic Segmentation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2505.10781