Datasets › ImageNet-LT

ImageNet-LT (ImageNet Long-Tailed)

Introduced by Ziwei Liu et al. in Large-Scale Long-Tailed Recognition in an Open World archive 2025-07-28

ImageNet Long-Tailed is a subset of /dataset/imagenet dataset consisting of 115.8K images from 1000 categories, with maximally 1280 images per class and minimally 5 images per class. The additional classes of images in ImageNet-2010 are used as the open set.

Source: Large-Scale Long-Tailed Recognition in an Open World

Homepage Benchmarks Papers JSON

Benchmarks archive 2025-07-28

All 3 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

		First row (archive order)	Paper	Code
Long-tail Learning	ImageNet-LT	LIFT (ViT-L/14) Top-1 Accuracy 82.9	Long-Tail Learning with Foundation Model: Heavy Fine-Tuning Hurts	shijxcs/lift	69	Compare
Long-tail learning with class descriptors	ImageNet-LT-d	DRAGON + Bal'Loss Per-Class Accuracy 53.5	From Generalized zero-shot learning to long-tail with...	dvirsamuel/DRAGON	5	Compare
Conditional Image Generation	ImageNet-LT	StyleGAN2 + NoisyTwins FID 21.29	NoisyTwins: Class-Consistent and Diverse Image...	val-iisc/NoisyTwins	1	Compare

Papers archive 2025-07-28

30 shown of 51 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 219. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

			Date	Samples run Syntology
Adaptive Parametric Activation	1	2	11 Jul 2024	not harvested
Harnessing Hierarchical Label Distribution Variations in Test Agnostic Long-tail Recognition	1	1	13 May 2024	ran 1 of 1 samples (0 unverified; 1 pointer-only for licence)
DeiT-LT Distillation Strikes Back for Vision Transformer Training on Long-Tailed Datasets	2	1	3 Apr 2024	not harvested
Probabilistic Contrastive Learning for Long-Tailed Visual Recognition	1	2	11 Mar 2024	ran 6 of 9 samples (3 unverified)
Long-Tail Learning with Foundation Model: Heavy Fine-Tuning Hurts	1	2	18 Sep 2023	ran 5 of 8 samples (3 unverified; 8 pointer-only for licence)
MDCS: More Diverse Experts with Consistency Self-distillation for Long-tailed Recognition	1	1	19 Aug 2023	ran 7 of 8 samples (1 unverified; 8 pointer-only for licence)
Global and Local Mixture Consistency Cumulative Learning for Long-tailed Visual Recognitions	2	1	15 May 2023	ran 7 of 10 samples (3 unverified; 5 pointer-only for licence)
Long-Tailed Recognition by Mutual Information Maximization between Latent Features and Ground-Truth Labels	1	1	2 May 2023	ran 1 of 1 samples (0 unverified)
NoisyTwins: Class-Consistent and Diverse Image Generation through StyleGANs	1	1	12 Apr 2023	not harvested
Improving Image Recognition by Retrieving from Web-Scale Image-Text Data	0	1	11 Apr 2023	not harvested
Escaping Saddle Points for Effective Generalization on Class-Imbalanced Data	1	1	28 Dec 2022	not harvested
Generalized Parametric Contrastive Learning	4	1	26 Sep 2022	not harvested
A Continual Development Methodology for Large-scale Multitask Dynamic ML Systems	1	1	15 Sep 2022	not harvested
Difficulty-Net: Learning to Predict Difficulty for Long-Tailed Recognition	1	3	7 Sep 2022	not harvested
Balanced Contrastive Learning for Long-Tailed Visual Recognition	1	1	19 Jul 2022	ran 1 of 1 samples (0 unverified)
Nested Collaborative Learning for Long-Tailed Visual Recognition	1	2	29 Mar 2022	ran 2 of 2 samples (0 unverified)
Long-Tailed Recognition via Weight Balancing	2	1	27 Mar 2022	ran 5 of 14 samples (9 unverified; 13 pointer-only for licence)
BatchFormer: Learning to Explore Sample Relationships for Robust Representation Learning	1	2	3 Mar 2022	ran 2 of 2 samples (0 unverified; 2 pointer-only for licence)
Pure Noise to the Rescue of Insufficient Data: Improving Imbalanced Classification by Training on Random Noise Images	1	1	16 Dec 2021	not harvested
The Majority Can Help The Minority: Context-rich Minority Oversampling for Long-tailed Classification	1	1	1 Dec 2021	ran 3 of 5 samples (2 unverified; 2 pointer-only for licence)
A Simple Long-Tailed Recognition Baseline via Vision-Language Model	1	4	29 Nov 2021	not harvested
Targeted Supervised Contrastive Learning for Long-Tailed Recognition	1	1	27 Nov 2021	ran 1 of 14 samples (13 unverified)
VL-LTR: Learning Class-wise Visual-Linguistic Representation for Long-Tailed Visual Recognition	1	2	26 Nov 2021	not harvested
Parametric Contrastive Learning	5	2	26 Jul 2021	ran 1 of 3 samples (2 unverified; 1 pointer-only for licence)
Self-Supervised Aggregation of Diverse Experts for Test-Agnostic Long-Tailed Recognition	2	2	20 Jul 2021	ran 4 of 6 samples (2 unverified)
RSG: A Simple but Effective Module for Learning Imbalanced Datasets	1	1	18 Jun 2021	ran 1 of 1 samples (0 unverified)
Class-Balanced Distillation for Long-Tailed Visual Recognition	3	2	12 Apr 2021	not harvested
Distributional Robustness Loss for Long-tail Learning	0	1	7 Apr 2021	not harvested
Improving Calibration for Long-Tailed Recognition	5	1	1 Apr 2021	ran 4 of 9 samples (5 unverified)
Distribution Alignment: A Unified Framework for Long-tail Visual Recognition	1	1	30 Mar 2021	ran 0 of 3 samples (3 unverified; 3 pointer-only for licence)

The full list of 51 is in the JSON twin.

Dataset loaders archive 2025-07-28

www.tensorflow.org/datasets/catalog/imagenet_lt tensorflow/datasetstfpytorchjax

1 loader as listed in the archive; links are outbound and not re-checked here.

Tasks archive 2025-07-28

Long-tail Learning Conditional Image Generation Long-tail learning with class descriptors Test Agnostic Long-Tailed Learning

License archive 2025-07-28

Unknown

Modalities archive 2025-07-28

No modality tagged.

Languages archive 2025-07-28

Chinese

Variants archive 2025-07-28

ImageNet-LT
ImageNet-LT-d

2 variant names, as the archive lists them.

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