AI Paper Atlas

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

SelecMix: Debiased Learning by Contradicting-pair Sampling

Inwoo Hwang, Sangjun Lee, Yunhyeok Kwak, Seong Joon Oh, Damien Teney, Jin-Hwa Kim, Byoung-Tak Zhang

NeurIPS 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Data augmentation and generalization bias · 4 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
Apply SelecMix to LfFCorrupted CIFAR-10 · Corrupted CIFAR-10, α=0.5%unbiased accuracy: 30.04 -> 39.44Improved
Apply SelecMix to LfFCorrupted CIFAR-10 · Corrupted CIFAR-10, α=1.0%unbiased accuracy: 33.80 -> 43.68Improved
Apply SelecMix to vanilla ResNet18BFFHQ · BFFHQ, α=0.5%accuracy on bias-conflicting test examples: 65.60 -> 71.60Improved
Use both contradicting positives and negatives instead of standard mixup (ablation)Vanilla model · Corrupted CIFAR-10, α=0.5%unbiased accuracy: 23.53 -> 38.14Improved
Use both contradicting pair types rather than positives only (ablation)Vanilla model · BFFHQ, α=0.5%unbiased accuracy: 66.20 -> 71.60Improved
Replace selective pair selection with standard mixup (ablation)Vanilla model · Colored MNIST, α=1.0%unbiased accuracy: 50.51 -> 46.19Hurt
Use the GSC biased embedding rather than the LfF cosine embedding to select contradicting negatives (ablation)SelecMix · Corrupted CIFAR-10, α=0.5%unbiased accuracy: 33.69 -> 41.82Improved
Use the GSC biased embedding rather than the LfF cosine embedding to select contradicting positives (ablation)SelecMix · Corrupted CIFAR-10, α=0.5%unbiased accuracy: 40.31 -> 42.94Improved
Use the GSC biased embedding rather than the LfF cosine embedding to select both pair types (ablation)SelecMix · Corrupted CIFAR-10, α=0.5%unbiased accuracy: 38.05 -> 43.68Improved

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