AI Paper Atlas

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

Noise Is Also Useful: Negative Correlation-Steered Latent Contrastive Learning

Jiexi Yan, Lei Luo, Chenghao Xu, Cheng Deng, Heng Huang

CVPR 2022 · Label-efficient and robust learning › Noisy labels · approach: Sample selection and co-training · 21 citations (OpenAlex)

This paper tried a common change: Add a contrastive loss

Add latent contrastive loss · CIFAR-100, symmetric noise 40% · test accuracy (%): 59.12 -> 68.59 Improved

What 1,317 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.

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 LaCoL instead of JNPLCIFAR-10 with symmetric label noise · CIFAR-10, symmetric noise 20%–60%test accuracy (%): 93.53 -> 94.12; 91.89 -> 92.33; 88.45 -> 88.72Improved
Use LaCoL instead of JNPLCIFAR-10 with asymmetric label noise · CIFAR-10, asymmetric noise 20%–40%test accuracy (%): 93.45 -> 93.76; 90.72 -> 91.07Improved
Use LaCoL instead of the strongest listed baselineCIFAR-100 with symmetric label noise · CIFAR-100, symmetric noise 20%–60%test accuracy (%): 71.75 -> 71.24; 68.11 -> 68.59; 61.26 -> 61.93Mixed
Use LaCoL instead of the strongest listed baselineCIFAR-100 with asymmetric label noise · CIFAR-100, asymmetric noise 20%–40%test accuracy (%): 70.13 -> 70.84; 59.51 -> 59.73Improved
Use LaCoL instead of the strongest listed baselineCIFAR-10 with instance-dependent noise · CIFAR-10, instance-dependent noise 20%–40%test accuracy (%): 90.41 -> 92.47; 84.78 -> 86.76Improved
Use LaCoL instead of CDRCIFAR-100 with instance-dependent noise · CIFAR-100, instance-dependent noise 20%–40%test accuracy (%): 67.33 -> 70.16; 55.94 -> 63.87Improved
Use LaCoL instead of JNPLClothing-1M · Clothing-1Mtest accuracy (%): 74.15 -> 74.68Improved
Add diversity-preserving weak-selection/strong-training augmentation (ablation)LaCoL on CIFAR-100 · CIFAR-100, symmetric noise 40%test accuracy (%): 67.24 -> 68.59Improved
Add diversity-preserving weak-selection/strong-training augmentation (ablation)LaCoL on CIFAR-100 · CIFAR-100, asymmetric noise 40%test accuracy (%): 58.22 -> 59.73Improved
Add latent contrastive loss (ablation)LaCoL on CIFAR-100 · CIFAR-100, symmetric noise 40%test accuracy (%): 59.12 -> 68.59Improved
Add latent contrastive loss (ablation)LaCoL on CIFAR-100 · CIFAR-100, asymmetric noise 40%test accuracy (%): 47.71 -> 59.73Improved
Add cross-space similarity consistency loss (ablation)LaCoL on CIFAR-100 · CIFAR-100, symmetric noise 40%test accuracy (%): 66.91 -> 68.59Improved

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