Papers › Decoupling Representation and Classifier for Long-Tailed Recognition

Decoupling Representation and Classifier for Long-Tailed Recognition

21 Oct 2019ICLR 2020 1arXiv:1910.09217archive 2025-07-28

Bingyi Kang, Saining Xie, Marcus Rohrbach, Zhicheng Yan, Albert Gordo, Jiashi Feng, Yannis Kalantidis

The long-tail distribution of the visual world poses great challenges for deep learning based classification models on how to handle the class imbalance problem. Existing solutions usually involve class-balancing strategies, e.g., by loss re-weighting, data re-sampling, or transfer learning from head- to tail-classes, but most of them adhere to the scheme of jointly learning representations and classifiers. In this work, we decouple the learning procedure into representation learning and classification, and systematically explore how different balancing strategies affect them for long-tailed recognition. The findings are surprising: (1) data imbalance might not be an issue in learning high-quality representations; (2) with representations learned with the simplest instance-balanced (natural) sampling, it is also possible to achieve strong long-tailed recognition ability by adjusting only the classifier. We conduct extensive experiments and set new state-of-the-art performance on common long-tailed benchmarks like ImageNet-LT, Places-LT and iNaturalist, showing that it is possible to outperform carefully designed losses, sampling strategies, even complex modules with memory, by using a straightforward approach that decouples representation and classification. Our code is available at https://github.com/facebookresearch/classifier-balancing.

Paper PDF Conference PDF Code Code Syntology ran

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="1910.09217")

Code

Syntology Ran 2 of 2 code samples harvested from 1 repository linked to this paper; 0 have no recorded run. Of those that ran: 1 ran · honoured contract; 1 ran · violated contract.

By repository: official repository: 2 samples from 1 repository, 2 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

facebookresearch/classifier-balancing officialmentioned in papermentioned on GitHubpytorch report

PhilChina/classifier-balancing mentioned on GitHubpytorch report

jackhck/subclass-balancing-contrastive-learning mentioned on GitHubpytorch report

silicx/dlsa mentioned on GitHubpytorch 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

2 samples harvested; 2 ran; 1 honoured the contract we drafted; 0 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.

1ran · honoured contract

1ran · violated contract

Licence: 2 of the 2 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 facebookresearch/classifier-balancing. “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.

cos_similarity facebookresearch/classifier-balancing/tau_norm.py official repository ran · honoured contract fingerprinted licence not identified · pointer only · c06cc6143cfaf205 · report

logits2preds facebookresearch/classifier-balancing/tau_norm.py official repository ran · violated contract fingerprinted licence not identified · pointer only · bd8bc22f6fda003f · report

Tasks

Classification General Classification Long-tail Learning Long-tail learning with class descriptors Representation Learning Transfer Learning

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)	LWS	Error Rate	8.9	#12 of 50	Archive leaderboard	report
Long-tail Learning	CIFAR-10-LT (ρ=10)	cRT	Error Rate	9.0	#13 of 50	Archive leaderboard	report
Long-tail Learning	ImageNet-LT	CB LWS	Top-1 Accuracy	41.4	#62 of 69	Archive leaderboard	report
Long-tail Learning	Places-LT	CB LWS	Top-1 Accuracy	37.6	#25 of 29	Archive leaderboard	report
Long-tail Learning	iNaturalist 2018	CB-LWS	Top-1 Accuracy	69.5%	#37 of 43	Archive leaderboard	report
Long-tail learning with class descriptors	AWA-LT	LWS	Long-Tailed Accuracy	93.5	#4 of 5	Archive leaderboard	report
Long-tail learning with class descriptors	AWA-LT	LWS	Per-Class Accuracy	73.4	#4 of 5	Archive leaderboard	report
Long-tail learning with class descriptors	CUB-LT	LWS	Long-Tailed Accuracy	65.7	#3 of 5	Archive leaderboard	report
Long-tail learning with class descriptors	CUB-LT	LWS	Per-Class Accuracy	53.1	#3 of 5	Archive leaderboard	report
Long-tail learning with class descriptors	ImageNet-LT-d	LWS	Per-Class Accuracy	49.9	#3 of 5	Archive leaderboard	report
Long-tail learning with class descriptors	SUN-LT	LWS	Long-Tailed Accuracy	40.2	#3 of 5	Archive leaderboard	report
Long-tail learning with class descriptors	SUN-LT	LWS	Per-Class Accuracy	33.9	#3 of 5	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.

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