AI Paper Atlas

Research map / Label-efficient and robust learning / Semi-supervised learning

Webly Supervised Image Classification with Self-Contained Confidence

Jingkang Yang, Litong Feng, Weirong Chen, Xiaopeng Yan, Huabin Zheng, Ping Luo, Wayne Zhang

ECCV 2020 · Label-efficient and robust learning › Semi-supervised learning · approach: Confidence-based pseudo-label selection · 15 citations (OpenAlex)

This paper tried a common change: Add dropout

add MC dropout to pretrained model · WebVision-500 (stage 2) · Top-1 accuracy (%): 76.46 -> 76.00 No clear effect

What 795 accepted papers report for this change

See this change in detailMatched by the wording of each paper's own result, read by AI from the full text. Papers report gains more often than failures, so this shows what gets published, not the chance a change works.

Read the paper

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 graph-based aggregation (GBA) to vanilla model (ablation)SCC framework · ImageNet val (stage 2)Top-1 accuracy (%): 69.78 -> 71.56Improved
add GBA to vanilla model (ablation)SCC framework · WebVision-500 (stage 2)Top-1 accuracy (%): 76.46 -> 77.12Improved
add GBA to mixup model (ablation)SCC framework · WebVision-500 (stage 2)Top-1 accuracy (%): 77.47 -> 77.76Improved
add mixup regularization to pretrained model (ablation)SCC framework · ImageNet val (stage 2)Top-1 accuracy (%): 69.78 -> 72.25Improved
add entropy regularizer to pretrained model (ablation)SCC framework · WebVision-500 (stage 2)Top-1 accuracy (%): 76.46 -> 73.78Hurt
add label smoothing to pretrained model (ablation)SCC framework · WebVision-500 (stage 2)Top-1 accuracy (%): 76.46 -> 77.02Improved
add MC dropout to pretrained model (ablation)SCC framework · WebVision-500 (stage 2)Top-1 accuracy (%): 76.46 -> 76.00No clear effect
replace vanilla with ensemble (E=5) confidence provider (ablation)SCC framework · WebVision-500 (stage 2)Top-1 accuracy (%): 76.46 -> 79.12Improved
replace sample-wise SCC with constant confidence (ablation)SCC framework · WebVision-500Top-1 accuracy (%): 77.17 (Vanilla+GBA) not exceeded by any constantHurt
use mixup as confidence provider instead of vanilla (ablation)SCC framework · WebVision-500 SCC qualityECE: 0.2371 -> 0.1828Improved
add GBA to vanilla confidence provider (ablation)SCC framework · WebVision-500 SCC qualityOCE: 0.1518 -> 0.0002Improved
add GBA to vanilla confidence provider (ablation)SCC framework · WebVision-500 SCC qualityECE: 0.2371 -> 0.2494Hurt

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