AI Paper Atlas

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

EntAugment: Entropy-Driven Adaptive Data Augmentation Framework for Image Classification

Suorong Yang, Furao Shen, Jian Zhao

ECCV 2024 · Label-efficient and robust learning › Recognition and long-tail · approach: Loss design and classifier theory · 13 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
add EntLoss to EntAugment (ablation)EntAugment · CIFAR-100 ResNet-50accuracy (%): 81.56 -> 82.49Improved
add EntLoss to EntAugment (ablation)EntAugment · CIFAR-10 ResNet-44accuracy (%): 95.76 -> 95.58Hurt
add EntLoss to Random Erasing (ablation)Random Erasing · CIFAR-100 ResNet-50accuracy (%): 77.79 -> 79.56Improved
add EntLoss to Random Erasing (ablation)Random Erasing · CIFAR-100 ResNet-18accuracy (%): 75.97 -> 75.98No clear effect
add EntLoss to FAA (ablation)FAA · CIFAR-10 ResNet-50accuracy (%): 96.69 -> 96.58Hurt
add EntLoss to TrivialAugment (ablation)TrivialAugment · CIFAR-100 ResNet-18accuracy (%): 78.67 -> 79.48Improved
reduce number of base transformations M from 14 to 2 (ablation)EntAugment · CIFAR-10 ResNet-18accuracy: 96.84% -> 96.36%Hurt
apply EntAugment and EntLoss to OLTROLTR on ImageNet-LT · ImageNet-LT closed-setoverall top-1 accuracy (%): 35.6 -> 39.6Improved
apply EntAugment versus MADAug on ImageNetEntAugment · ImageNet ResNet-50top-1 accuracy (%): 78.5 -> 78.2Hurt
add EntLoss to training with EntAugment (feature clustering) (ablation)ResNet-18 on CIFAR-10 · CIFAR-10Dunn index: 7.93e-5 -> 1.07e-4Improved

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