Papers › Distilling Virtual Examples for Long-tailed Recognition

Distilling Virtual Examples for Long-tailed Recognition

28 Mar 2021ICCV 2021 10arXiv:2103.15042archive 2025-07-28

Yin-Yin He, Jianxin Wu, Xiu-Shen Wei

We tackle the long-tailed visual recognition problem from the knowledge distillation perspective by proposing a Distill the Virtual Examples (DiVE) method. Specifically, by treating the predictions of a teacher model as virtual examples, we prove that distilling from these virtual examples is equivalent to label distribution learning under certain constraints. We show that when the virtual example distribution becomes flatter than the original input distribution, the under-represented tail classes will receive significant improvements, which is crucial in long-tailed recognition. The proposed DiVE method can explicitly tune the virtual example distribution to become flat. Extensive experiments on three benchmark datasets, including the large-scale iNaturalist ones, justify that the proposed DiVE method can significantly outperform state-of-the-art methods. Furthermore, additional analyses and experiments verify the virtual example interpretation, and demonstrate the effectiveness of tailored designs in DiVE for long-tailed problems.

PaperPDFConference PDFCode

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

Code

yangyucheng000/DiVE mindsporeApache-2.0 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

Knowledge DistillationLong-tail Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Long-tail Learning ImageNet-LT RIDE-DiVE Top-1 Accuracy 57.12 #31 of 69 Archive leaderboard report
Long-tail Learning ImageNet-LT DiVE Top-1 Accuracy 53.1 #44 of 69 Archive leaderboard report
Long-tail Learning iNaturalist 2018 RIDE-DiVE Top-1 Accuracy 73.44% #22 of 43 Archive leaderboard report
Long-tail Learning iNaturalist 2018 DiVE Top-1 Accuracy 71.71% #28 of 43 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

Knowledge Distillation

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