AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

RegionCL: Exploring Contrastive Region Pairs for Self-Supervised Representation Learning

Yufei Xu, Qiming Zhang, Jing Zhang, Dacheng Tao

ECCV 2022 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Invariance-based self-supervised learning · 13 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 RegionCL region-level contrastive pairsMoCov2 · ImageNet linear classificationTop-1: 67.5 -> 69.4Improved
add RegionCL region-level contrastive pairsDenseCL · ImageNet linear classificationTop-1: 63.6 -> 68.5Improved
add RegionCL region-level contrastive pairsSimSiam · ImageNet linear classificationTop-1: 68.1 -> 71.3Improved
add RegionCL to MoByMoBy Swin-T · ImageNet linear (100 ep)Top-1: 70.9 -> 73.9Improved
add RegionCL to MoByMoBy Swin-T · ImageNet linear (300 ep)Top-1: 75.3 -> 77.0Improved
add RegionCL with 1% labelsDenseCL · ImageNet 1% labelsTop-1: 38.9 -> 47.8Improved
add RegionCLMoCov2 · COCO Mask-RCNN FPN 1xAPbb: 38.9 -> 40.1Improved
add RegionCLDenseCL · COCO RetinaNet 1xAPbb: 37.7 -> 38.8Improved
add RegionCLMoCov2 · Cityscapes instance segmentationAP: 33.9 -> 34.9Improved
use paste view positives (Eq. 2 term) (ablation)RegionCL-M · ImageNet 20-NN (100 ep)accuracy: 49.3 -> 50.0Improved
use canvas view positives (ablation)RegionCL-M · ImageNet 20-NN (100 ep)accuracy: 49.3 -> 51.8Improved
use both paste and canvas views (ablation)RegionCL-M · ImageNet 20-NN (100 ep)accuracy: 49.3 -> 54.6Improved

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