AI Paper Atlas

Research map / Label-efficient and robust learning / Noisy labels

MoPro: Webly Supervised Learning with Momentum Prototypes

Junnan Li, Caiming Xiong, Steven Hoi

ICLR 2021 · Label-efficient and robust learning › Noisy labels · approach: Noisy cross-modal hashing and multi-label · 47 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 MoPro instead of Cross-Entropy pretrainingResNet-50 pretrained on WebVision-V1.0 · WebVision-V1.0 clean validationtop-1 accuracy: 72.4 -> 73.9Improved
Use MoPro instead of Cross-Entropy pretrainingResNet-50 pretrained on WebVision-V1.0 · ILSVRC 2012 validationtop-1 accuracy: 65.7 -> 67.8Improved
Use MoPro instead of Cross-Entropy pretrainingResNet-50 pretrained on WebVision-V1.0 · VOC07, 1-shotmAP: 54.5 -> 59.5Improved
Use MoPro instead of Cross-Entropy pretrainingResNet-50 pretrained on WebVision-V1.0 · ImageNet, 1% finetuningtop-1 accuracy: 67.6 -> 71.2Improved
Use MoPro instead of Cross-Entropy pretrainingResNet-50 pretrained on WebVision-V1.0 · COCO val2017, 1× schedulebounding-box AP: 39.2 -> 39.7Improved
Use MoPro instead of Cross-Entropy pretrainingResNet-50 pretrained on WebVision-V1.0 · ImageNet-Raccuracy: 49.56 -> 54.87Improved
Add prototypical contrastive loss (ablation)MoPro pretrained on WebVision-V0.5 · ImageNet, 1% finetuningtop-1 accuracy: 68.0 -> 69.3Improved
Add instance contrastive loss (ablation)MoPro pretrained on WebVision-V0.5 · ImageNet, 1% finetuningtop-1 accuracy: 68.2 -> 69.3Improved
Add both prototypical and instance contrastive losses (ablation)MoPro pretrained on WebVision-V0.5 · ImageNet, 1% finetuningtop-1 accuracy: 66.9 -> 69.3Improved
Use prototype similarity in pseudo-labeling (ablation)MoPro pretrained on WebVision-V0.5 · ImageNet, 1% finetuningtop-1 accuracy: 68.4 -> 69.3Improved

Later papers that compared with this method

4 later accepted papers report MoPro† as a baseline in their results tables; 4 of them report a better number on most of the results they share with it.

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