Research map / Detection and segmentation / Open-set and few-shot detection
Few-Shot Object Detection and Viewpoint Estimation for Objects in the Wild
Yang Xiao, Renaud Marlet
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 |
|---|---|---|---|
| add explicit difference fqry - fcls to product aggregation (ablation) | Ours · PASCAL VOC novel set 1, 10-shot | AP50 (%): 51.5 -> 55.5 | Improved |
| add fqry to product plus difference aggregation (ablation) | Ours · PASCAL VOC novel set 1, 10-shot | AP50 (%): 55.5 -> 57.4 | Improved |
| add fqry to product-only aggregation (ablation) | Ours · PASCAL VOC novel set 1, 10-shot | AP50 (%): 51.5 -> 49.6 | Hurt |
| add fqry and fcls to product aggregation (ablation) | Ours · PASCAL VOC novel set 1, 10-shot | AP50 (%): 51.5 -> 54.2 | Improved |
| full aggregation instead of product only (ablation) | Ours · PASCAL VOC novel set 1, 3-shot | AP50 (%): 35.0 -> 42.2 | Improved |
| full aggregation instead of product only (ablation) | Ours · PASCAL VOC novel set 2, 10-shot | AP50 (%): 45.4 -> 45.7 | Improved |
| use full aggregation to reduce variance across random support sets (ablation) | Ours · PASCAL VOC novel set 1, 10-shot | AP50 (%): ± 5.8 -> ± 2.7 | Improved |
| use Ours instead of Meta R-CNN on COCO 10-shot | Ours · MS-COCO novel, 10-shot | AP 0.5:0.95: 8.7 -> 12.5 | Improved |
| use Ours instead of TFA w/cos on VOC set 2 10-shot | Ours · PASCAL VOC novel set 2, 10-shot | AP50 (%): 39.5 -> 45.7 | Improved |
| use Ours instead of TFA w/cos on VOC set 1 1-shot | Ours · PASCAL VOC novel set 1, 1-shot | AP50 (%): 25.3 -> 24.2 | Hurt |
| use Ours instead of MetaView on ObjectNet3D | Ours · ObjectNet3D 10-shot | Acc30: 0.48 -> 0.64 | Improved |
| use Ours instead of MetaView on Pascal3D+ | Ours · Pascal3D+ 10-shot | Acc30: 0.33 -> 0.52 | Improved |
Closest papers by meaning
- Meta-Learning to Detect Rare Objects (ICCV 2019 · similarity 0.89)
- Meta-DETR: Image-Level Few-Shot Detection with Inter-Class Correlation Exploitation (TPAMI 2022 · similarity 0.88)
- Towards Generalizable Multi-Camera 3D Object Detection via Perspective Rendering (AAAI 2025 · similarity 0.88)
- Frustratingly Simple Few-Shot Object Detection (ICML 2020 · similarity 0.88)
- Fine-Grained Prototypes Distillation for Few-Shot Object Detection (AAAI 2024 · similarity 0.86)
- Revisiting Few-Shot Object Detection with Vision-Language Models (NeurIPS 2024 · similarity 0.86)
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.
