AI Paper Atlas

Research map / Detection and segmentation / CNN features

DetCo: Unsupervised Contrastive Learning for Object Detection

Enze Xie, Jian Ding, Wenhai Wang, Xiaohang Zhan, Hang Xu, Peize Sun, Zhenguo Li, Ping Luo

ICCV 2021 · Detection and segmentation › CNN features · approach: Region-based and query-based detectors · 363 citations (OpenAlex)

This paper tried a common change: Add a contrastive loss

add global and local contrastive learning · ImageNet linear classification (100ep) · top-1 accuracy: 64.3 -> 67.1 Improved

What 1,317 accepted papers report for this change

See this change in detailMatched by the wording of each paper's own result, read by AI from the full text. Papers report gains more often than failures, so this shows what gets published, not the chance a change works.

Read the paper

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 multi-level supervision (ablation)MoCo v2 · VOC07+12 detection (100ep)mAP: 56.3 -> 57.0Improved
add multi-level supervision (ablation)MoCo v2 · ImageNet linear classification (100ep)top-1 accuracy: 64.3 -> 63.2Hurt
add multi-level supervision (ablation)MoCo v2 · VOC07 SVM Res2 featureaccuracy: 47.1 -> 50.9Improved
add multi-level supervision (ablation)MoCo v2 · VOC07 SVM Res5 featureaccuracy: 82.1 -> 81.8Hurt
add global and local contrastive learning (ablation)MoCo v2 · ImageNet linear classification (100ep)top-1 accuracy: 64.3 -> 67.1Improved
add global and local contrastive learning (ablation)MoCo v2 · VOC07+12 detection (100ep)mAP: 56.3 -> 56.8Improved
add global and local contrastive learning on top of multi-level supervision (ablation)MoCo v2 + MLS · VOC07+12 detection (100ep)mAP: 57.0 -> 57.4Improved
add global and local contrastive learning on top of multi-level supervision (ablation)MoCo v2 + MLS · ImageNet linear classification (100ep)top-1 accuracy: 63.2 -> 66.6Improved
DetCo pretraining instead of MoCo v2 under 12k-iteration fine-tuningMask R-CNN R50-C4 · COCO 12kAP50^bb: 45.3 -> 49.1Improved
pretrain DetCo 800 epochs instead of 200 (ablation)DetCo · VOC07+12 detectionAP: 57.8 -> 58.2Improved
DetCo with 100 epochs vs MoCo v2 with 800 epochsDetCo · VOC07+12 detectionAP: 57.4 -> 57.4No clear effect
use DetCo pretraining instead of supervised pretrainingSparse R-CNN · COCOAP: 45.0 -> 46.5Improved

Later papers that compared with this method

1 later accepted paper reports DetCo as a baseline in their results tables; 0 of them report a better number on most of the results they share with it.

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