AI Paper Atlas

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

TPAMI 2022 · Detection and segmentation › Open-set and few-shot detection · approach: Few-shot object detection · 246 citations (OpenAlex)

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 changedWhereMeasuredEffect
add CAM with C=1 to Meta-DETR (ablation)Meta-DETR · Pascal VOC split 1 (1-shot)mAP@0.5: 27.2 -> 30.3Improved
add CAM with C=1 to Meta-DETR (ablation)Meta-DETR · Pascal VOC split 1 (10-shot)mAP@0.5: 59.3 -> 62.0Improved
increase support classes aggregated from C=1 to C=5 (ablation)Meta-DETR · Pascal VOC split 1 (1-shot)mAP@0.5: 30.3 -> 35.1Improved
increase support classes aggregated from C=1 to C=5 (ablation)Meta-DETR · Pascal VOC split 1 (2-shot)mAP@0.5: 44.0 -> 49.0Improved
increase support classes aggregated from C=1 to C=5 (ablation)Meta-DETR · Pascal VOC split 1 (10-shot)mAP@0.5: 62.0 -> 62.0No clear effect
add CAM with C=5 to FsDetView (ablation)FsDetView · Pascal VOC split 1 (1-shot)mAP@0.5: 24.2 -> 30.1Improved
add CAM with C=5 to FsDetView (ablation)FsDetView · Pascal VOC split 1 (10-shot)mAP@0.5: 57.4 -> 57.5No 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 -> 42.1Improved
image-level detection instead of region-level at 1-shot (ablation)Meta-DETR · Pascal VOC split 1 (1-shot)mAP@0.5: 28.0 -> 27.2Hurt
add background prototype modelling (ablation)CAM · Pascal VOC split 1 (1-shot)mAP@0.5: 32.6 -> 35.1Improved
add sigmoid and query multiplication (ablation)CAM · Pascal VOC split 1 (1-shot)mAP@0.5: 31.2 -> 35.1Improved
place CAM at first encoder layer instead of third (ablation)Meta-DETR · Pascal VOC split 1 (1-shot)mAP@0.5: 27.1 -> 35.1Improved

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.

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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy