AI Paper Atlas

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

CS-Isolate: Extracting Hard Confident Examples by Content and Style Isolation

Yexiong Lin, Yu Yao, Xiaolong Shi, Mingming Gong, Xu Shen, Dong Xu, Tongliang Liu

NeurIPS 2023 · Label-efficient and robust learning › Noisy labels · approach: Instance-dependent noise modeling · 0 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 content/style isolation (CS-Isolate)DivideMix · CIFAR-10N Worsttest accuracy: 92.48 -> 94.28Improved
add content/style isolation (CS-Isolate)DivideMix · CIFAR-10 IDN-0.4test accuracy: 94.16 -> 95.54Improved
add content/style isolation (CS-Isolate)DivideMix · CIFAR-100 IDN-0.4test accuracy: 70.50 -> 73.11Improved
add content/style isolation (CS-Isolate)DivideMix · Fashion-MNIST IDN-0.4test accuracy: 92.28 -> 94.40Improved
add content/style isolation (CS-Isolate)DivideMix · Clothing1Mtest accuracy: 74.76 -> 74.92Improved
add content/style isolation (CS-Isolate)DivideMix · CIFAR-10 Pair-45%test accuracy: 70.86 -> 87.54Improved
add content/style isolation (CS-Isolate)DivideMix · CIFAR-10 Sym-80%test accuracy: 92.43 -> 92.57No clear effect
add content/style isolation (CS-Isolate)DivideMix · CIFAR-10N Worstrecall of confident examples: 0.966 -> 0.980Improved
add content/style isolation (CS-Isolate)DivideMix · CIFAR-10N Worstprecision of confident examples: 0.951 -> 0.956No clear effect
add content/style isolation (CS-Isolate)Co-Teaching · CIFAR-10N Worsttest accuracy: 82.04 -> 83.93No clear effect
add content/style isolation (CS-Isolate)Me-Momentum · CIFAR-10N Worsttest accuracy: 84.21 -> 86.95Improved
add content/style isolation (CS-Isolate)Me-Momentum · CIFAR-10N Worstrecall ratio of confident examples: 92.02 -> 95.76Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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