Research map / Detection and segmentation / Open-set and few-shot detection
Meta-DETR: Image-Level Few-Shot Detection with Inter-Class Correlation Exploitation
Gongjie Zhang, Zhipeng Luo, Kaiwen Cui, Shijian Lu, Eric P. Xing
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 CAM with C=1 to Meta-DETR (ablation) | Meta-DETR · Pascal VOC split 1 (1-shot) | mAP@0.5: 27.2 -> 30.3 | Improved |
| add CAM with C=1 to Meta-DETR (ablation) | Meta-DETR · Pascal VOC split 1 (10-shot) | mAP@0.5: 59.3 -> 62.0 | Improved |
| increase support classes aggregated from C=1 to C=5 (ablation) | Meta-DETR · Pascal VOC split 1 (1-shot) | mAP@0.5: 30.3 -> 35.1 | Improved |
| increase support classes aggregated from C=1 to C=5 (ablation) | Meta-DETR · Pascal VOC split 1 (2-shot) | mAP@0.5: 44.0 -> 49.0 | Improved |
| increase support classes aggregated from C=1 to C=5 (ablation) | Meta-DETR · Pascal VOC split 1 (10-shot) | mAP@0.5: 62.0 -> 62.0 | No clear effect |
| add CAM with C=5 to FsDetView (ablation) | FsDetView · Pascal VOC split 1 (1-shot) | mAP@0.5: 24.2 -> 30.1 | Improved |
| add CAM with C=5 to FsDetView (ablation) | FsDetView · Pascal VOC split 1 (10-shot) | mAP@0.5: 57.4 -> 57.5 | No clear effect |
| image-level detection (Meta-DETR w/o CAM) instead of region-level FsDetView + Deform. Trans. (ablation) | Meta-DETR · Pascal VOC split 1 (2-shot) | mAP@0.5: 36.3 -> 42.1 | Improved |
| image-level detection instead of region-level at 1-shot (ablation) | Meta-DETR · Pascal VOC split 1 (1-shot) | mAP@0.5: 28.0 -> 27.2 | Hurt |
| add background prototype modelling (ablation) | CAM · Pascal VOC split 1 (1-shot) | mAP@0.5: 32.6 -> 35.1 | Improved |
| add sigmoid and query multiplication (ablation) | CAM · Pascal VOC split 1 (1-shot) | mAP@0.5: 31.2 -> 35.1 | Improved |
| place CAM at first encoder layer instead of third (ablation) | Meta-DETR · Pascal VOC split 1 (1-shot) | mAP@0.5: 27.1 -> 35.1 | Improved |
Later papers that compared with this method
5 later accepted papers report Meta-DETR as a baseline in their results tables; 5 of them report a better number on most of the results they share with it.
- DAPE: Harmonizing Content-Position Encoding for Versatile Dense Visual Prediction (AAAI 2026 · better on 1 of 1 shared result)
- Reference Twice: A Simple and Unified Baseline for Few-Shot Instance Segmentation (TPAMI 2024 · better on 2 of 2 shared results)
- Few-Shot Object Detection with Foundation Models (CVPR 2024 · better on 1 of 1 shared result)
- Integrally Migrating Pre-trained Transformer Encoder-decoders for Visual Object Detection (ICCV 2023 · better on 1 of 1 shared result)
- A Survey of Self-Supervised and Few-Shot Object Detection (TPAMI 2022 · better on 2 of 2 shared results)
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 6 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
- Frustratingly Simple Few-Shot Object Detection (ICML 2020 · similarity 0.93)
- Meta-Learning to Detect Rare Objects (ICCV 2019 · similarity 0.93)
- Meta-ZSDETR: Zero-shot DETR with Meta-learning (ICCV 2023 · similarity 0.91)
- Incremental-DETR: Incremental Few-Shot Object Detection via Self-Supervised Learning (AAAI 2023 · similarity 0.91)
- Fine-Grained Prototypes Distillation for Few-Shot Object Detection (AAAI 2024 · similarity 0.91)
- Weakly Supervised Few-Shot Object Detection with DETR (AAAI 2024 · 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.
