AI Paper Atlas

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

Fixing Localization Errors to Improve Image Classification

Guolei Sun, Salman Khan, Wen Li, Hisham Cholakkal, Fahad Shahbaz Khan, Luc Van Gool

ECCV 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Loss design and classifier theory · 13 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 HNCmse lossResNet-56 CE · CIFAR-100top-1 accuracy: 72.40 -> 73.35Improved
add HNCmse lossResNet-110 CE · CIFAR-100top-1 accuracy: 73.79 -> 75.00Improved
add HNCmse lossResNet-101 CE · ImageNettop-1 error: 23.2 -> 22.3Improved
add HNCkd lossResNet-152 CE · ImageNettop-1 error: 22.9 -> 21.8Improved
add HNCmse lossResNet-50 CE · CUB-200-2011accuracy: 86.0 -> 87.1Improved
add HNCmse lossResNet-101 · MS-COCOmAP: 74.9 -> 77.8Improved
add HNCmse lossAttention Consistency (AC) · MS-COCOmAP: 77.5 -> 78.5Improved
add HNCkd lossResNet-110 CE · CIFAR-100 FGSM eps 0.05accuracy: 14.55 -> 29.80Improved
add HNCmse lossResNet-110 CE · CIFAR-100 symmetric noise r 0.6accuracy: 22.48 -> 32.86Improved
add HNCmse lossResNet-110 CE · CIFAR-100 asymmetric noise r 0.4accuracy: 40.89 -> 46.51Improved
add HNC loss (ablation)ResNeXt-29 c=8 CE · CIFAR-100accuracy: 81.77 -> 82.32Improved
add HNC loss (ablation)DenseNet-BC CE · CIFAR-100accuracy: 77.32 -> 78.78Improved

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