Research map / Detection and segmentation / Open-set and few-shot detection
Generalized and Discriminative Few-Shot Object Detection via SVD-Dictionary Enhancement
Aming WU, Suqi Zhao, Cheng Deng, Wei Liu
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 SVD-Dictionary enhancement to MPSR | MPSR · COCO 30-shot | AP: 13.8 -> 16.2 | Improved |
| add SVD-Dictionary enhancement to FSCE | FSCE · COCO 30-shot | AP: 15.4 -> 16.0 | Improved |
| add SVD-Dictionary enhancement to MPSR | MPSR · PASCAL VOC Split 1 2-shot | nAP50: 41.2 -> 47.4 | Improved |
| add SVD-Dictionary enhancement to FSCE | FSCE · PASCAL VOC Split 2 10-shot | nAP50: 48.7 -> 48.2 | No clear effect |
| add SVD-Dictionary enhancement to FSCE | FSCE · PASCAL VOC Split 1 3-shot | nAP75: 20.1 -> 25.1 | Improved |
| add dictionary learning on top of SVD generalization (ablation) | MPSR + Ours · PASCAL VOC Split 1 2-shot | nAP50: 44.3 -> 47.4 | Improved |
| add SVD-based generalization only (no dictionary learning) to MPSR (ablation) | MPSR · PASCAL VOC Split 1 2-shot | nAP50: 41.2 -> 44.3 | Improved |
| vary k from 50% to 10% of singular values (ablation) | MPSR + Ours · PASCAL VOC Split 1 1-shot | nAP50: 41.5 -> 40.6 | Hurt |
| vary k from 50% to 90% of singular values (ablation) | MPSR + Ours · PASCAL VOC Split 1 2-shot | nAP50: 47.4 -> 41.8 | Hurt |
| reduce codewords from 24 to 16 (ablation) | MPSR + Ours · PASCAL VOC Split 1 1-shot | nAP50: 41.5 -> 39.2 | Hurt |
| increase codewords from 24 to 32 (ablation) | MPSR + Ours · PASCAL VOC Split 1 10-shot | nAP50: 61.2 -> 60.3 | Mixed |
| add SVD-Dictionary enhancement to MPSR | MPSR · PASCAL VOC Split 1 5-shot | Base AP50: 69.4 -> 69.8 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- FSCE — FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding (CVPR 2021) · better on 6 of 7 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Generalized Semantic Contrastive Learning via Embedding Side Information for Few-Shot Object Detection (TPAMI 2025 · similarity 0.89)
- Label, Verify, Correct: A Simple Few Shot Object Detection Method (CVPR 2022 · similarity 0.88)
- Fine-Grained Prototypes Distillation for Few-Shot Object Detection (AAAI 2024 · similarity 0.87)
- Weakly Supervised Few-Shot Object Detection with DETR (AAAI 2024 · similarity 0.87)
- Few-Shot Object Detection with Foundation Models (CVPR 2024 · similarity 0.87)
- 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.
