AI Paper Atlas

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

A Contrastive Objective for Learning Disentangled Representations

Jonathan Kahana, Yedid Hoshen

ECCV 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Contrastive representation theory · 8 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 domain-wise negatives (negatives only from same domain) (ablation)DCoDR · SmallNorbinvariance (lower better): 0.863 -> 0.143Improved
add domain-wise negatives (ablation)DCoDR-norec · SmallNorbinvariance (lower better): 0.879 -> 0.071Improved
add MoCo-V2 pre-trained initialization (ablation)DCoDR · SmallNorbinformativeness: 0.701 -> 0.785Improved
add MoCo-V2 pre-trained initialization (ablation)DCoDR · SmallNorbinvariance (lower better): 0.253 -> 0.143Improved
add positive augmentations (ablation)DCoDR · SmallNorbinformativeness: 0.555 -> 0.785Improved
add positive augmentations (ablation)DCoDR · SmallNorbinvariance (lower better): 0.057 -> 0.143Hurt
add positive augmentations (ablation)DCoDR-norec · SmallNorbinformativeness: 0.166 -> 0.730Improved
use selected augmentations instead of SimSiam augmentations (ablation)DCoDR · SmallNorbinformativeness: 0.643 -> 0.785Improved
use Gaussian blur instead of horizontal flip augmentationDCoDR-norec · Cars3Dinformativeness: 0.725 -> 0.960Improved
add reconstruction constraintDCoDR · SmallNorbinformativeness: 0.730 -> 0.785Improved
add reconstruction constraintDCoDR · Edges2Shoesretrieval accuracy: 0.53 -> 0.90Improved
add reconstruction constraintDCoDR · CelebAlandmark L1 error (lower better): 1.127 -> 0.858Improved

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