Papers › Improving Calibration for Long-Tailed Recognition
Improving Calibration for Long-Tailed Recognition
Zhisheng Zhong, Jiequan Cui, Shu Liu, Jiaya Jia
Deep neural networks may perform poorly when training datasets are heavily class-imbalanced. Recently, two-stage methods decouple representation learning and classifier learning to improve performance. But there is still the vital issue of miscalibration. To address it, we design two methods to improve calibration and performance in such scenarios. Motivated by the fact that predicted probability distributions of classes are highly related to the numbers of class instances, we propose label-aware smoothing to deal with different degrees of over-confidence for classes and improve classifier learning. For dataset bias between these two stages due to different samplers, we further propose shifted batch normalization in the decoupling framework. Our proposed methods set new records on multiple popular long-tailed recognition benchmark datasets, including CIFAR-10-LT, CIFAR-100-LT, ImageNet-LT, Places-LT, and iNaturalist 2018. Code will be available at https://github.com/Jia-Research-Lab/MiSLAS.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2104.00466")
Code
Syntology Ran 4 of 9 code samples harvested from 1 repository linked to this paper; 5 have no recorded run. Of those that ran: 3 ran · our draft was wrong; 1 ran · fixture could not drive it.
By repository: official repository: 9 samples from 1 repository, 4 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.
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
9 samples harvested; 4 ran; 0 honoured the contract we drafted; 5 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.
Licence: 0 of the 9 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.
Harvested from Jia-Research-Lab/MiSLAS. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.
Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.
Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.
d9def42110729a85 · report
160bb14bd76201b4 · report
97f484048ac03556 · report
345e624f9cc2e32a · report
830214b89e793de5 · report
722e0bb5cb9f0a0d · report
8e0350d0dc4d57da · report
bc07600de5b8bbda · report
11d038f53d77a8d2 · report
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Long-tail Learning | CIFAR-10-LT (ρ=10) | MiSLAS | Error Rate | 10 | #18 of 50 | Archive leaderboard | report |
| Long-tail Learning | CIFAR-10-LT (ρ=100) | MiSLAS | Error Rate | 17.9 | #18 of 28 | Archive leaderboard | report |
| Long-tail Learning | CIFAR-100-LT (ρ=10) | MiSLAS | Error Rate | 36.8 | #18 of 31 | Archive leaderboard | report |
| Long-tail Learning | CIFAR-100-LT (ρ=100) | MiSLAS | Error Rate | 53 | #39 of 66 | Archive leaderboard | report |
| Long-tail Learning | CIFAR-100-LT (ρ=50) | MiSLAS | Error Rate | 47.7 | #20 of 25 | Archive leaderboard | report |
| Long-tail Learning | ImageNet-LT | MiSLAS | Top-1 Accuracy | 52.7 | #48 of 69 | Archive leaderboard | report |
| Long-tail Learning | iNaturalist 2018 | MiSLAS | Top-1 Accuracy | 71.6% | #29 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