AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Relative Contrastive Loss for Unsupervised Representation Learning

Shixiang Tang, Feng Zhu, Lei Bai, Rui Zhao, Wanli Ouyang

ECCV 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Contrastive representation theory · 2 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
increase hierarchy levels from 1 to 2 (ablation)RCL · ImageNet-1K linear eval (200 epochs, predictor/level ablation)top-1 accuracy: 70.2 -> 71.3Improved
increase hierarchy levels from 2 to 3 (ablation)RCL · ImageNet-1K linear eval (200 epochs, predictor/level ablation)top-1 accuracy: 71.3 -> 71.8Improved
increase hierarchy levels from 3 to 4 (ablation)RCL · ImageNet-1K linear eval (200 epochs, predictor/level ablation)top-1 accuracy: 71.8 -> 71.4Hurt
use multiple criterion-specific predictors instead of one (3 levels) (ablation)RCL · ImageNet-1K linear eval (200 epochs, predictor/level ablation)top-1 accuracy: 71.8 -> 72.6Improved
replace NNCLR nearest-neighbor positives with offline K-means relative labels (ablation)RCL · ImageNet-1K linear eval (200 epochs, clustering ablation)top-1 accuracy: 70.7 -> 71.8Improved
use hierarchical DBSCAN labels instead of K-means (ablation)RCL · ImageNet-1K linear eval (200 epochs, clustering ablation)top-1 accuracy: 71.8 -> 72.3Improved
use online hierarchical clustering instead of offline DBSCAN (ablation)RCL · ImageNet-1K linear eval (200 epochs, clustering ablation)top-1 accuracy: 72.3 -> 72.6Improved
online hierarchical clustering vs offline DBSCAN epoch time (ablation)RCL · ImageNet-1K linear eval (200 epochs, clustering ablation)training time per epoch: 986s -> 776sImproved
increase support queue size from 65536 to 98304 (ablation)RCL · ImageNet-1K linear eval (200 epochs)top-1 accuracy: +0.36%Improved
increase support queue beyond 98304 (ablation)RCL · ImageNet-1K linear eval (200 epochs)top-1 accuracyNo clear effect
RCL vs MoCo v3 (800 epochs)RCL · ImageNet-1K linear eval (800+ epochs)top-1 accuracy: 73.8 -> 75.8Improved
RCL vs NNCLR (200 epochs)RCL · ImageNet-1K linear eval (200 epochs)top-1 accuracy: 70.7 -> 72.6Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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