AI Paper Atlas

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

MetaMask: Revisiting Dimensional Confounder for Self-Supervised Learning

Jiangmeng Li, Wenwen Qiang, Yanan Zhang, Wenyi Mo, Changwen Zheng, Bing Su, Hui Xiong

NeurIPS 2022 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Inductive bias and minimal representations · 12 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 MetaMask to CMCCMC · CIFAR-10, convtop-1 accuracy: 81.31 -> 85.24Improved
Add MetaMask to Barlow TwinsBarlow Twins · CIFAR-10, CIFAR-100, STL-10, and IN-200; conv and fctop-1 accuracy: 76.63 -> 85.24; 78.49 -> 86.90; 52.80 -> 58.02; 52.95 -> 56.78; 80.97 -> 84.96; 81.43 -> 86.13; 39.81 -> 42.91; 40.34 ->Improved
Add MetaMask to SwAVSwAV · CIFAR-10, CIFAR-100, STL-10, and IN-200; conv and fctop-1 accuracy: 72.19 -> 80.37; 72.36 -> 77.22; 46.58 -> 52.07; 46.75 -> 52.98; 74.65 -> 81.34; 75.30 -> 82.19; 39.67 -> 40.28; 39.02 ->Improved
Add MetaMask to SimCLRSimCLR · CIFAR-10, CIFAR-100, STL-10, and IN-200; conv and fctop-1 accuracy: 80.58 -> 82.85; 80.07 -> 81.64; 50.03 -> 53.70; 49.82 -> 54.24; 75.57 -> 81.37; 77.15 -> 82.90; 36.24 -> 40.56; 39.83 ->Improved
Add MetaMask to BYOLBYOL · ResNet-18 CIFAR-10top-1 accuracy: 88.05 -> 87.53Hurt
Add MetaMask to BYOLBYOL · CIFAR-10, CIFAR-100, STL-10, and IN-200; conv and fctop-1 accuracy: 77.18 -> 79.26; 80.01 -> 82.73; 53.64 -> 55.68; 53.78 -> 54.72; 41.59 -> 42.72; 41.90 -> 43.29; 81.73 -> 83.01; 81.57 ->Improved
Add MetaMask to SimSiamSimSiam · CIFAR-10, CIFAR-100, STL-10, and IN-200; conv and fctop-1 accuracy: 78.14 -> 80.03; 81.13 -> 81.39; 52.55 -> 54.70; 53.52 -> 55.02; 41.03 -> 41.82; 41.27 -> 42.67; 80.91 -> 82.35; 81.88 ->Improved
Add MetaMask to DCLDCL · CIFAR-10, CIFAR-100, STL-10, and IN-200; conv and fctop-1 accuracy: 80.89 -> 81.33; 80.93 -> 81.34; 51.38 -> 53.05; 51.09 -> 53.74; 38.79 -> 40.28; 40.26 -> 41.69; 77.09 -> 80.94; 78.39 ->Improved
Add MetaMask to HCLHCL · CIFAR-10, CIFAR-100, STL-10, and IN-200; conv and fctop-1 accuracy: 82.13 -> 83.65; 82.76 -> 83.95; 52.69 -> 54.03; 53.13 -> 54.26; 40.05 -> 40.43; 41.23 -> 41.01; 79.86 -> 81.52; 80.20 ->Mixed
Add MetaMask to Barlow TwinsBarlow Twins · CIFAR-10, CIFAR-100, STL-10, and IN-200; ResNet-18top-1 accuracy: 85.72 -> 87.53; 60.31 -> 61.42; 73.62 -> 73.97; 45.10 -> 46.81Improved
Add MetaMask to SimCLRSimCLR · CIFAR-10, CIFAR-100, STL-10, and IN-200; ResNet-18top-1 accuracy: 81.73 -> 86.01; 58.27 -> 61.03; 70.09 -> 74.90; 44.46 -> 45.87Improved
Add MetaMask to NNCLRNNCLR · CIFAR-10, CIFAR-100, STL-10, and IN-200; ResNet-18top-1 accuracy: 81.44 -> 85.78; 61.64 -> 61.89; 71.89 -> 74.02; 47.10 -> 46.90Mixed

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