AI Paper Atlas

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

Dual Compensation Residual Networks for Class Imbalanced Learning

Ruibing Hou, Hong Chang, Bingpeng Ma, Shiguang Shan, Xilin Chen

TPAMI 2023 · Label-efficient and robust learning › Recognition and long-tail · approach: Classifier rebalancing and margin losses · 11 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 DCRNets instead of ResLT residual mechanismResNet-10 backbone · ImageNet-LT (>180 epochs)top-1 accuracy (%): 43.8 -> 45.0Improved
use DCRNets instead of ResLT residual mechanismResNeXt-50 backbone · ImageNet-LT (>180 epochs)top-1 accuracy (%): 52.9 -> 55.0Improved
use DCRNets instead of SSP self-supervised initializationResNet-50 backbone · ImageNet-LTtop-1 accuracy (%): 51.3 -> 54.1Improved
use DCRNets instead of decoupled DisAlignResNet-50 backbone · ImageNet-LT (90 epochs)top-1 accuracy (%): 51.3 -> 53.2Improved
add DCRNets modules to RIDE multi-expert network (2 experts)RIDE ResNet-50 · ImageNet-LTtop-1 accuracy (%): 54.4 -> 55.7Improved
add DCRNets modules to RIDE multi-expert network (3 experts)RIDE ResNet-50 · ImageNet-LTtop-1 accuracy (%): 54.9 -> 56.9Improved
use DCRNets instead of Hybrid-PSCResNet-50 · iNaturalist18 (90 epochs)top-1 accuracy (%): 68.1 -> 70.3Improved
add DCRNets modules to RIDE (2 experts)RIDE ResNet-32 · CIFAR100-LTtop-1 accuracy (%): 47.0 -> 55.0Improved
train longer (90 to >180 epochs)DCRNets ResNet-50 · ImageNet-LTtop-1 accuracy (%): 53.2 -> 54.1Improved

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