Research map / Detection and segmentation / Weakly supervised detection and segmentation
CA-SSL: Class-Agnostic Semi-Supervised Learning for Detection and Segmentation
Lu Qi, Jason Kuen, Zhe Lin, Jiuxiang Gu, Fengyun Rao, Dian Li, Weidong Guo, Zhen Wen, Ming-Hsuan Yang, Jiaya Jia
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use class-agnostic rather than class-specific pseudo labels in warmup (ablation) | CA-SSL warmup (objects) · COCO val2017 (tiny) | AP det: 47.1 -> 48.1 | Improved |
| use pseudo labels rather than class-agnostic ground-truth labels in warmup (ablation) | CA-SSL warmup (objects) · COCO val2017 (tiny) | AP det: 46.9 -> 48.1 | Improved |
| add warmup on class-agnostic pseudo labels over ImageNet pretraining (ablation) | Swin-T CondInst · COCO val2017 (tiny) | AP det: 46.8 -> 48.1 | Improved |
| switch from box objects to mask entities in warmup labels (ablation) | CA-SSL warmup · COCO val2017 panoptic (tiny) | PQ: 42.5 -> 43.7 | Improved |
| switch from box objects to mask entities in warmup labels (ablation) | CA-SSL warmup · COCO val2017 detection (tiny) | AP det: 48.1 -> 48.2 | No clear effect |
| increase warmup epochs from 12 to 48 (ablation) | CA-SSL warmup · COCO val2017 entity AP | AP^e: 38.4 -> 40.2 | Improved |
| increase warmup and finetuning from 12 epochs to 60 and 36 (ablation) | CA-SSL · COCO val2017 AP det | AP det: 45.3 -> 48.2 | Improved |
| use a stronger pseudo labeler (entity AP 38.0 to 42.1) (ablation) | CA-SSL warmup · COCO val2017 warmed-up entity AP | AP^e: 36.1 -> 40.2 | Improved |
| add strong augmentation in both warmup and finetuning (ablation) | CA-SSL · COCO val2017 AP det | AP det: 48.2 -> 49.1 | Improved |
| scale unlabeled data from 123K to 3.66M images (ablation) | CA-SSL · COCO val2017 AP det | AP det: 48.2 -> 50.6 | Improved |
| initialize finetuning with warmup backbone (ablation) | Swin-T-FCOS · COCO val2017 AP det | AP det: 46.8 -> 50.6 | Improved |
| also initialize neck, head and classifier from warmup model (ablation) | backbone-initialized model · COCO val2017 AP det | AP det: 50.6 -> 51.5 | Improved |
Closest papers by meaning
- Toward Efficient Semi-Supervised Object Detection With Detection Transformer (TPAMI 2025 · similarity 0.90)
- Unbiased Teacher for Semi-Supervised Object Detection (ICLR 2021 · similarity 0.89)
- Towards Realistic Semi-Supervised Learning (ECCV 2022 · similarity 0.89)
- UniT: Unified Knowledge Transfer for Any-Shot Object Detection and Segmentation (CVPR 2021 · similarity 0.89)
- Instant-Teaching: An End-to-End Semi-Supervised Object Detection Framework (CVPR 2021 · similarity 0.89)
- Semi-DETR: Semi-Supervised Object Detection With Detection Transformers (CVPR 2023 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
