Papers › Disentangling Label Distribution for Long-tailed Visual Recognition
Disentangling Label Distribution for Long-tailed Visual Recognition
Youngkyu Hong, Seungju Han, Kwanghee Choi, Seokjun Seo, Beomsu Kim, Buru Chang
The current evaluation protocol of long-tailed visual recognition trains the classification model on the long-tailed source label distribution and evaluates its performance on the uniform target label distribution. Such protocol has questionable practicality since the target may also be long-tailed. Therefore, we formulate long-tailed visual recognition as a label shift problem where the target and source label distributions are different. One of the significant hurdles in dealing with the label shift problem is the entanglement between the source label distribution and the model prediction. In this paper, we focus on disentangling the source label distribution from the model prediction. We first introduce a simple but overlooked baseline method that matches the target label distribution by post-processing the model prediction trained by the cross-entropy loss and the Softmax function. Although this method surpasses state-of-the-art methods on benchmark datasets, it can be further improved by directly disentangling the source label distribution from the model prediction in the training phase. Thus, we propose a novel method, LAbel distribution DisEntangling (LADE) loss based on the optimal bound of Donsker-Varadhan representation. LADE achieves state-of-the-art performance on benchmark datasets such as CIFAR-100-LT, Places-LT, ImageNet-LT, and iNaturalist 2018. Moreover, LADE outperforms existing methods on various shifted target label distributions, showing the general adaptability of our proposed method.
In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.
Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
For agents, on Syntology's MCP service (how to connect):
get_citation_path(paper_1="2012.00321", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2012.00321")
Code
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.
A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Image Classification | iNaturalist 2018 | LADE | Top-1 Accuracy | 70.0% | #38 of 60 | Archive leaderboard | report |
| Long-tail Learning | CIFAR-10-LT (ρ=10) | LADE | Error Rate | 11.22 | #31 of 50 | Archive leaderboard | report |
| Long-tail Learning | CIFAR-100-LT (ρ=10) | LADE | Error Rate | 38.3 | #21 of 31 | Archive leaderboard | report |
| Long-tail Learning | CIFAR-100-LT (ρ=100) | LADE | Error Rate | 54.6 | #48 of 66 | Archive leaderboard | report |
| Long-tail Learning | ImageNet-LT | LADE | Top-1 Accuracy | 53.0 | #46 of 69 | Archive leaderboard | report |
| Long-tail Learning | Places-LT | LADE | Top-1 Accuracy | 38.8 | #22 of 29 | Archive leaderboard | report |
| Long-tail Learning | iNaturalist 2018 | LADE | Top-1 Accuracy | 70.0% | #35 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
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