AI Paper Atlas

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

Where and What? Examining Interpretable Disentangled Representations

Xinqi Zhu, Chang Xu, Dacheng Tao

CVPR 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Contrastive representation theory · 33 citations (OpenAlex)

Check 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 PS loss and SC module to InfoGAN (ablation)InfoGAN · CelebATPL: 10.9 -> 8.1Improved
Add PS loss to InfoGAN (ablation)InfoGAN · CelebAPPL: 43.6 -> 34.3Improved
Add SC module to InfoGAN (ablation)InfoGAN · CelebAFID: 6.0 -> 5.9Improved
Add PS loss and SC module to InfoGAN (ablation)InfoGAN · FFHQPPL: 142.7 -> 120.1Improved
Replace SC mask with softmax mask (ablation)InfoGAN + Both · CelebATPL: 8.1 -> 14.8Hurt
Set PS-loss weight to 0.1 (ablation)InfoGAN + Both · FFHQFID: 13.5 -> 16.0Hurt
Set PS-loss weight to 0.001 (ablation)InfoGAN + Both · FFHQFID: 13.5 -> 23.7Hurt
Use only 1 rectangle in SC masks (ablation)InfoGAN + Both · CelebAFID: 6.0 -> 9.0Hurt
Use 4 rectangles in SC masks (ablation)InfoGAN + Both · CelebAFID: 6.0 -> 5.9Improved
Add SC module on DSprites (ablation)Ours · DSpritesFactorVAE metric: 83.54 (6.91) -> 81.47 (5.39)Hurt
Select top training seeds using TPLOurs · 3DShapesFactorVAE metric: 92.04 (6.49) -> 93.41 (3.34)Improved
Use the full method rather than InfoGANInfoGAN · Shoes+EdgesPPL: 2952.2 -> 246.2Improved

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