Research map / Detection and segmentation / Open-set and few-shot detection
Object Detection With Self-Supervised Scene Adaptation
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 pseudo-labeling, location-aware mixup, and object-mask mid-fusion instead of no adaptation | M2 (ResNet-101) · Scenes100 | APGm_co: +3.76 | Helped |
| Use the proposed adaptation framework instead of ST | M2 (ResNet-101) · Scenes100 | APGm_co: +3.76 vs +0.80 | Helped |
| Apply STAC adaptation | M2 (ResNet-101) · Scenes100 | APGm_co: -1.26 | Hurt |
| Apply Adaptive Teacher adaptation | M2 (ResNet-101) · Scenes100 | APGm_co: -0.75 | Hurt |
| Apply H2FA R-CNN adaptation | M2 (ResNet-101) · Scenes100 | APGm_co: -3.10 | Hurt |
| Apply TIA adaptation | M2 (ResNet-101) · Scenes100 | APGm_co: -0.32 | Hurt |
| Apply LODS adaptation | M2 (ResNet-101) · Scenes100 | APGm_co: +0.45 | Helped |
| Add location-aware mixup rather than using pseudo-labeling alone (ablation) | Scene adaptation · Scenes100 | APGm_co: +0.95 -> +1.72 | Helped |
| Use location-aware rather than random mixup without fusion (ablation) | Scene adaptation · Scenes100 | APGm_co: +1.22 -> +1.72 | Helped |
| Add object-mask mid-fusion instead of using pseudo-labeling alone (ablation) | Scene adaptation · Scenes100 | APGm_co: +0.95 -> +3.40 | Helped |
| Use mid rather than early fusion with location-aware mixup (ablation) | Scene adaptation · Scenes100 | APGm_co: +2.25 -> +3.76 | Helped |
| Use mid rather than late fusion with location-aware mixup (ablation) | Scene adaptation · Scenes100 | APGm_co: +3.66 -> +3.76 | Helped |
Closest papers by meaning
- Automatic Adaptation of Object Detectors to New Domains Using Self-Training (CVPR 2019 · similarity 0.88)
- As Pseudo-Label Free as Possible: Leveraging Adaptive Feature Generation for Sparsely Annotated Object Detection (AAAI 2025 · similarity 0.86)
- Adapting Object Detectors via Selective Cross-Domain Alignment (CVPR 2019 · similarity 0.86)
- Multi-View Domain Adaptive Object Detection on Camera Networks (AAAI 2023 · similarity 0.86)
- Instance Relation Graph Guided Source-Free Domain Adaptive Object Detection (CVPR 2023 · similarity 0.86)
- Test-Time Adaptive Object Detection with Foundation Model (NeurIPS 2025 · similarity 0.85)
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.