Papers › Learning From Multiple Experts: Self-paced Knowledge Distillation for Long-tailed...

Learning From Multiple Experts: Self-paced Knowledge Distillation for Long-tailed Classification

6 Jan 2020ECCV 2020 8arXiv:2001.01536archive 2025-07-28

Liuyu Xiang, Guiguang Ding, Jungong Han

In real-world scenarios, data tends to exhibit a long-tailed distribution, which increases the difficulty of training deep networks. In this paper, we propose a novel self-paced knowledge distillation framework, termed Learning From Multiple Experts (LFME). Our method is inspired by the observation that networks trained on less imbalanced subsets of the distribution often yield better performances than their jointly-trained counterparts. We refer to these models as 'Experts', and the proposed LFME framework aggregates the knowledge from multiple 'Experts' to learn a unified student model. Specifically, the proposed framework involves two levels of adaptive learning schedules: Self-paced Expert Selection and Curriculum Instance Selection, so that the knowledge is adaptively transferred to the 'Student'. We conduct extensive experiments and demonstrate that our method is able to achieve superior performances compared to state-of-the-art methods. We also show that our method can be easily plugged into state-of-the-art long-tailed classification algorithms for further improvements.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

xiangly55/LFME officialpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

General ClassificationKnowledge DistillationLong-tail Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Long-tail Learning ImageNet-LT LFME + OLTR Top-1 Accuracy 38.8 #64 of 69 Archive leaderboard report
Long-tail Learning Places-LT LFME + OLTR Top-1 Accuracy 36.2 #27 of 29 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Introduced by this paper: LFME

Knowledge DistillationLFME

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections