AI Paper Atlas

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

Lower-Bounded Proper Losses for Weakly Supervised Classification

Shuhei M Yoshida, Takashi Takenouchi, Masashi Sugiyama

ICML 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Learning from unlabeled and positive-unlabeled data · 2 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 gLS to backward-corrected cross entropyLinear model · MNISTtest accuracy: 81.52 ± 1.44 % -> 83.77 ± 0.55 %Improved
Add gLS to backward-corrected cross entropyMLP · MNISTtest accuracy: 83.09 ± 0.67 % -> 88.63 ± 0.38 %Improved
Add gLS to backward-corrected cross entropyResNet-20 · CIFAR-10test accuracy: 28.86 ± 2.06 % -> 49.71 ± 3.04 %Improved
Add gLS to backward-corrected cross entropyWRN-28-2 · CIFAR-10test accuracy: 29.57 ± 1.58 % -> 49.98 ± 2.59 %Improved
Tune weight decay for BC (ablation)Linear model · MNISTtest accuracy: 81.52 ± 1.44 % -> 83.56 ± 0.87 %Improved
Tune weight decay for BC (ablation)MLP · MNISTtest accuracy: 83.09 ± 0.67 % -> 83.30 ± 1.01 %No clear effect
Tune weight decay for BC (ablation)ResNet-20 · CIFAR-10test accuracy: 28.86 ± 2.06 % -> 29.56 ± 1.49 %No clear effect
Tune weight decay for BC + GA (ablation)MLP · MNISTtest accuracy: 87.88 ± 1.11 % -> 89.15 ± 0.75 %Improved
Tune weight decay for BC + GA (ablation)ResNet-20 · CIFAR-10test accuracy: 34.39 ± 2.96 % -> 35.36 ± 1.80 %No clear effect
Use gLS with α > 1 rather than α < 1 (ablation)WRN-28-2 · CIFAR-10test accuracyImproved
Vary gLS exponent toward α=1 while remaining in the proper, bounded regime (ablation)WRN-28-2 · CIFAR-10test accuracyImproved
Vary the gLS coefficient k across two orders of magnitude (ablation)WRN-28-2 · CIFAR-10test accuracyImproved

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