AI Paper Atlas

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

Transferring Annotator- and Instance-Dependent Transition Matrix for Learning From Crowds

Shikun Li, Xiaobo Xia, Jiankang Deng, Shiming Ge, Tongliang Liu

TPAMI 2024 · Label-efficient and robust learning › Noisy labels · approach: Crowdsourced label aggregation · 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 knowledge transfer between neighboring annotators (GCN) over fine-tuning (ablation)TAIDTM-FT · CIFAR10 (AIDN-40%)test accuracy: 77.19 -> 79.95Improved
add knowledge transfer between neighboring annotators (ablation)TAIDTM-FT · Musictest accuracy: 67.23 -> 69.39Improved
add global-to-individual transfer (TAIDTM-FT vs BLTM) (ablation)BLTM · CIFAR10 (AIDN-40%)test accuracy: 73.06 -> 77.19Improved
add global-to-individual transfer (TAIDTM-FT vs BLTM) (ablation)BLTM · LabelMetest accuracy: 86.16 -> 85.36Hurt
model annotators individually instead of one source (TAIDTM vs BLTM)BLTM · CIFAR10 (AIDN-50%)test accuracy: 60.51 -> 77.18Improved
TAIDTM vs BLTM on SVHN at high noiseBLTM · SVHN (AIDN-50%)test accuracy: 80.59 -> 94.48Improved
TAIDTM vs BLTM on F-MNIST at high noiseBLTM · F-MNIST (AIDN-50%)test accuracy: 81.10 -> 89.62Improved
use GCN instead of GAT mapping function (ablation)TAIDTM · real-world averagetest accuracy: 79.52 -> 80.02Improved
use GCN instead of Deepwalk mapping function (ablation)TAIDTM · real-world averagetest accuracy: 78.83 -> 80.02Improved
instance-dependent noise-pattern similarity instead of Jaccard, confusion or CBCC similarity (ablation)TAIDTM · real-world averagetest accuracy: 78.93 -> 80.02Improved
apply Graph Purifying with k=200 (ablation)TAIDTM · CIFAR10 (AIDN-40%)test accuracy: 75.33 -> 78.77Improved
vary number of neighbors k from 1 to 100 (ablation)TAIDTM · CIFAR10 (AIDN-40%)test accuracy: 79.90 / 80.16 / 80.19No clear effect

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