AI Paper Atlas

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

Efficient Unsupervised Visual Representation Learning with Explicit Cluster Balancing

Ioannis Maniadis Metaxas, Georgios Tzimiropoulos, Ioannis Patras

ECCV 2024 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Empirical contrastive visual learning · 1 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 predictor head (ablation)ExCB · ImageNet linear (ResNet50, 100 ep, multi-crop)linear accuracy: 73.8 -> 74.0Improved
stop gradient to centroid layer for local crops (ablation)ExCB · ImageNet linear (ResNet50, 100 ep, multi-crop)linear accuracy: 74.0 -> 74.3Improved
cosine weight decay schedule 0.001 to 0.0001 for centroid layer (ablation)ExCB · ImageNet linear (ResNet50, 100 ep, multi-crop)linear accuracy: 74.3 -> 74.5Improved
reduce batch size from 1024 to 256 (ablation)ExCB · ImageNet linear (ResNet50, 100 ep, no multi-crop)linear accuracy: 70.7 -> 70.5No clear effect
vary number of clusters K away from 65536 (ablation)ExCB · ImageNet linear (ResNet50, 100 ep, no multi-crop)linear accuracy: 70.7 -> 70.3 (K=32768); 70.7 -> 70.6 (K=98304)Hurt
use linear rather than quadratic balancing function for small clusters (ablation)ExCB · ImageNet linear (ResNet50, 100 ep, multi-crop)linear accuracy: 74.3 -> 74.5Improved
ExCB balancing vs DINO centering: fraction of empty clustersExCB · ImageNet train clusters (K=65,536)empty clusters: 74.7% -> 1.6%Improved
ExCB vs SMoG on semi-supervised 1% labelsExCB · ImageNet semi-supervised 1% labelstop-1 accuracy: 58.0 -> 57.8No clear effect
ExCB vs MoCo-v2 on COCO detectionExCB · COCO val2017 Mask R-CNNAP^b: 39.3 -> 39.2No clear effect
ExCB vs prior methods with fewer epochs and smaller batchExCB · ImageNet linear (ResNet50)linear top-1 accuracy: 76.4 -> 76.5Improved

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