AI Paper Atlas

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

Reweighting Augmented Samples by Minimizing the Maximal Expected Loss

Mingyang Yi, Lu Hou, Lifeng Shang, Xin Jiang, Qun Liu, Zhi-Ming Ma

ICLR 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Loss design and classifier theory · 8 citations (OpenAlex)

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
Use loss-based MMEL weights instead of uniform weightsResNet56 · CIFAR-10accuracy: 94.62($\pm$0.18) -> 94.85($\pm$0.15)Improved
Use loss-based MMEL weights instead of uniform weightsResNet56 · CIFAR-100accuracy: 73.44($\pm$0.13) -> 74.20($\pm$0.24)Improved
Apply MMEL-H with standard image augmentationResNet · ImageNetaccuracy: +0.72; +1.08; +0.38Improved
Use soft consistency loss rather than the hard-label lossResNet · ImageNetaccuracy: -1.24; -0.97; -1.33Hurt
Add MMEL reweighting with augmented text samplesBERT_BASE · GLUE dev AvgAvg: 83.5($\pm$0.27) -> 84.5($\pm$0.11)Improved
Add MMEL reweighting with augmented text samplesBERT_BASE · GLUE test AvgAvg: 79.6($\pm$0.09) -> 80.5($\pm$0.17)Improved
Use teacher-predicted labels for augmented samples instead of original labels (ablation)MMEL-H · GLUE devAvg: 78.1 -> 84.5Improved
Use teacher-predicted labels for augmented samples instead of original labels (ablation)MMEL-S · GLUE devAvg: 80.0 -> 84.7Improved
Increase augmented samples from 2 to 5 (ablation)MMEL-H · CIFAR-10, ResNet56accuracy: 94.29($\pm$0.08) -> 94.78($\pm$0.09)Improved
Increase augmented samples from 10 to 20 (ablation)MMEL-H · CIFAR-100, ResNet56accuracy: 74.20($\pm$0.24) -> 74.10($\pm$0.05)No clear effect
Use beam search rather than greedy search to generate augmented text (ablation)MMEL · GLUE devAvgNo clear effect
Generate the two sentences separately rather than together (ablation)MMEL · GLUE devAvgMixed

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