AI Paper Atlas

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

AutoMix: Mixup Networks for Sample Interpolation via Cooperative Barycenter Learning

Jianchao Zhu, Liangliang Shi, Junchi Yan, Hongyuan Zha

ECCV 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Loss design and classifier theory · 21 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
use random-ratio label weighting (d) rather than first image's label (a) (ablation)AutoMix · CIFAR-10 (full)top-1 error: 5.38 -> 3.72Improved
use random-ratio label weighting rather than half-half mix (b) (ablation)AutoMix · CIFAR-10 (full)top-1 error: 3.91 -> 3.72Improved
use random-ratio label weighting rather than multi-label sum (c) (ablation)AutoMix · CIFAR-10 (sub)top-1 error: 15.35 -> 15.17Improved
mix images from random classes rather than only same-label pairs (ablation)AutoMix · CIFAR-10 (full)top-1 error: 4.21 -> 3.72Improved
mix images from random classes rather than only different-label pairs (ablation)AutoMix · CIFAR-10 (full)top-1 error: 3.98 -> 3.72Improved
add AutoMix over baselineResNet-18 · CIFAR-10 (full)top-1 error: 4.59 -> 3.72Improved
add AutoMix over baselineResNet-18 · Tiny-ImageNet (full)top-1 error: 40.35 -> 37.15Improved
add AutoMix over baselineResNet-18 · MIMLmAP: 72.14 -> 74.80Improved
add AutoMix over Manifold MixupResNet-18 · GTSRB (full)top-1 error: 0.38 -> 0.41No clear effect
add OptTransMix to BC11-layer CNN · MNIST (sub)top-1 error: 5.93 -> 4.37Improved
add OptTransMix to Mixup11-layer CNN · F-MNIST (sub)top-1 error: 17.38 -> 17.10Improved
add OptTransMix to Mixup11-layer CNN · MNIST (sub)top-1 error: 6.17 -> 8.12Hurt

Later papers that compared with this method

4 later accepted papers report AutoMix as a baseline in their results tables; 4 of them report a better number on most of the results they share with it.

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