AI Paper Atlas

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

Contrastive Multiview Coding

Yonglong Tian, Dilip Krishnan, Phillip Isola

ECCV 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Uncertainty-aware multi-view learning · 2,060 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
use Y,DbDr colorspace instead of L,abCMC ResNet-50x2 · ImageNet-1ktop-1 accuracy: 68.3 / 88.2 -> 69.0 / 88.9Improved
add RandAugment (ablation)CMC {Y,DbDr} ResNet-50x2 · ImageNet-1ktop-1 accuracy: 69.0 -> 70.6Improved
add dorsal (optical flow) stream to ventral stream (ablation)CMC CaffeNet · UCF-101accuracy: 55.3 -> 59.1Improved
add dorsal (optical flow) stream to ventral streamCMC CaffeNet · HMDB-51accuracy: 26.7 vs 27.2 for Cross and LearnNo clear effect
add more views (depth, normals) beyond L and ab (ablation)CMC patch-based · NYU-Depth-V2 segmentationmIoUImproved
full-graph instead of core-view paradigm (ablation)CMC · NYU-Depth-V2 segmentation from LmIoU: 34.1 -> 34.4No clear effect
use contrastive instead of predictive learning (ablation)L,Depth encoder · STL-10accuracy: 55.5 -> 58.3Improved
use contrastive instead of predictive learning (ablation)L,Normal encoder · STL-10accuracy: 58.4 -> 60.1Improved
use contrastive instead of predictive learning (ablation)L,Seg. Map encoder · STL-10accuracy: 57.7 -> 59.2Improved
increase number of negatives from 64 to 4096 (ablation)CMC AlexNet · ImageNet 100 classesaccuracy: saturates at around 60.3% with m=4096Improved
add MoCo momentum encoder (ablation)CMC · ImageNet-100top-1 accuracy: 75.6 -> 77.2 (+1.6)Improved
add PIRL JigSaw branch (ablation)CMC · ImageNet-100top-1 accuracy: 75.6 -> 78.0 (+2.4)Improved

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