Continual Segmentation with Disentangled Objectness Learning and Class Recognition
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914735562162176 |
|---|---|
| author | Gong, Yizheng Yu, Siyue Wang, Xiaoyang Xiao, Jimin |
| author_facet | Gong, Yizheng Yu, Siyue Wang, Xiaoyang Xiao, Jimin |
| contents | Most continual segmentation methods tackle the problem as a per-pixel classification task. However, such a paradigm is very challenging, and we find query-based segmenters with built-in objectness have inherent advantages compared with per-pixel ones, as objectness has strong transfer ability and forgetting resistance. Based on these findings, we propose CoMasTRe by disentangling continual segmentation into two stages: forgetting-resistant continual objectness learning and well-researched continual classification. CoMasTRe uses a two-stage segmenter learning class-agnostic mask proposals at the first stage and leaving recognition to the second stage. During continual learning, a simple but effective distillation is adopted to strengthen objectness. To further mitigate the forgetting of old classes, we design a multi-label class distillation strategy suited for segmentation. We assess the effectiveness of CoMasTRe on PASCAL VOC and ADE20K. Extensive experiments show that our method outperforms per-pixel and query-based methods on both datasets. Code will be available at https://github.com/jordangong/CoMasTRe. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_03477 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Continual Segmentation with Disentangled Objectness Learning and Class Recognition Gong, Yizheng Yu, Siyue Wang, Xiaoyang Xiao, Jimin Computer Vision and Pattern Recognition Most continual segmentation methods tackle the problem as a per-pixel classification task. However, such a paradigm is very challenging, and we find query-based segmenters with built-in objectness have inherent advantages compared with per-pixel ones, as objectness has strong transfer ability and forgetting resistance. Based on these findings, we propose CoMasTRe by disentangling continual segmentation into two stages: forgetting-resistant continual objectness learning and well-researched continual classification. CoMasTRe uses a two-stage segmenter learning class-agnostic mask proposals at the first stage and leaving recognition to the second stage. During continual learning, a simple but effective distillation is adopted to strengthen objectness. To further mitigate the forgetting of old classes, we design a multi-label class distillation strategy suited for segmentation. We assess the effectiveness of CoMasTRe on PASCAL VOC and ADE20K. Extensive experiments show that our method outperforms per-pixel and query-based methods on both datasets. Code will be available at https://github.com/jordangong/CoMasTRe. |
| title | Continual Segmentation with Disentangled Objectness Learning and Class Recognition |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.03477 |