AI Paper Atlas

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

Superclass Learning With Representation Enhancement

Zeyu Gan, Suyun Zhao, Jinlong Kang, Liyuan Shang, Hong Chen, Cuiping Li

CVPR 2023 · Label-efficient and robust learning › Recognition and long-tail · approach: Data augmentation and generalization bias · 1 citations (OpenAlex)

This paper tried a common change: Larger batch size

increase batch size from 64 to 512 · CIFAR100-7 · accuracy: 76.7 -> 77.9 Improved

What 785 accepted papers report for this change

See this change in detailMatched by the wording of each paper's own result, read by AI from the full text. Papers report gains more often than failures, so this shows what gets published, not the chance a change works.

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 SCLRE instead of SimCLRResNet-50 · CIFAR100-3accuracy: 79.0 -> 80.1Improved
use SCLRE instead of SimCLRResNet-50 · CIFAR100-4accuracy: 80.6 -> 84.0Improved
use SCLRE instead of SimCLRResNet-50 · CIFAR100-7accuracy: 73.9 -> 78.1Improved
use SCLRE instead of the strongest reported baseline, SimCLRResNet-50 · mini-ImageNetaccuracy: 90.1 -> 89.3Hurt
use SCLRE instead of SupConResNet-50 · FMoWaccuracy: 58.3 -> 64.8Improved
use SCLRE instead of the baselineResNet-50 · Adienceaccuracy: 65.7 -> 68.7Improved
use SCLRE instead of SimCLRResNet-50 · VOCaccuracy: 80.0 -> 81.5Improved
add cross-instance attention (CIA) to the baseline (ablation)SCLRE on CIFAR100-7 · CIFAR100-7accuracy: 68.9 -> 69.2Improved
add contrastive adjustment loss together with CIA (ablation)SCLRE on CIFAR100-7 · CIFAR100-7accuracy: 69.2 -> 75.1Improved
add targeted adjustment loss to CIA and contrastive adjustment loss (ablation)SCLRE on CIFAR100-7 · CIFAR100-7accuracy: 75.1 -> 77.9Improved
remove cross-entropy contribution by setting α=1 (ablation)SCLRE on CIFAR100-7 · CIFAR100-7accuracy: 75.1 -> -Hurt
increase batch size from 64 to 512 (ablation)SCLRE on CIFAR100-7 · CIFAR100-7accuracy: 76.7 -> 77.9Improved

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