AI Paper Atlas

Research map / Learning theory and algorithms / Fairness

Unveiling and Mitigating Generalized Biases of DNNs Through the Intrinsic Dimensions of Perceptual Manifolds

Yanbiao Ma, Licheng Jiao, Fang Liu, Lingling Li, Wenping Ma, Shuyuan Yang, Xu Liu, Puhua Chen

TPAMI 2024 · Learning theory and algorithms › Fairness · approach: Fairness-constrained classification

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
add Intrinsic Dimension Regularization (IDR) to the training lossCNN and transformer image classifiers · CIFAR-10, CIFAR-100, Mini-ImageNet and a fourth benchmark (class-balanced)overall accuracy and class-accuracy biasImproved
use IDR instead of Focal Loss or SeeSaw Lossbaseline classifiers · four class-balanced datasetsoverall performance and model biasImproved
increase the weight of L_ID in mid-to-late training (smaller alpha schedule) (ablation)IDR · benchmark image datasetsoverall performanceImproved

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