AI Paper Atlas

Research map / Label-efficient and robust learning / Noisy labels

Instance-dependent Label Distribution Estimation for Learning with Label Noise

Zehui Liao, Shishuai Hu, Yutong Xie, Yong Xia

IJCV 2024 · Label-efficient and robust learning › Noisy labels · approach: Instance-dependent noise modeling · 18 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
add the LD supervision loss L_LD to cross-entropy (ablation)ILDE · CIFAR-10 (asymmetric noise 0.5)test accuracy (%): 46.81 -> 70.19Improved
add the diagonally-dominant regularizer L_M (ablation)ILDE · CIFAR-10 (asymmetric noise 0.5)test accuracy (%): 70.19 -> 80.74Improved
add temporal ensembling of the estimated LD (ablation)ILDE · CIFAR-10 (asymmetric noise 0.5)test accuracy (%): 75.85 -> 79.71Improved
add sharpening of the estimated LD (ablation)ILDE · CIFAR-10 (asymmetric noise 0.5)test accuracy (%): 79.71 -> 80.74Improved
reduce batch size from 128 to 32 (ablation)ILDE · CIFAR-10 (asymmetric noise 0.5)test accuracy (%): 80.74 -> 84.43Improved
reduce batch size further from 32 to 8 (ablation)ILDE · CIFAR-10 (asymmetric noise 0.5)test accuracy (%): 84.43 -> 78.83Hurt
tune hyperparameters per noise rate (Ours* vs Ours) (ablation)ILDE · CIFAR-10 (symmetric noise 0.8)test accuracy (%): 56.25 -> 59.10Improved
use ILDE instead of MEIDTMILDE* · CIFAR-10 (symmetric noise 0.8)test accuracy (%): 55.84 -> 59.10Improved
use ILDE instead of MEIDTMILDE* · CIFAR-10 (asymmetric noise 0.5)test accuracy (%): 77.23 -> 80.74Improved
use ILDE instead of best competitorILDE · CIFAR-100Ntest accuracy (%): 55.06 -> 55.95Improved
use ILDE instead of MEIDTM on saturated MNISTILDE* · MNIST (symmetric noise 0.8)test accuracy (%): 98.35 -> 98.57No clear effect
use ILDE instead of TNLPADILDE · Clothing1Mtest accuracy (%): 71.51 -> 72.45Improved

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