Papers with Code · CC BY-SA 4.0

ImageNet-LT

아카이브 평가 69건 · 마지막 적재/변경 2026-10-30

평가 기록

과거 수집 기록이며 최신 순위가 아닙니다. 데이터셋 버전·split·실험 조건과 지표 방향이 검증되지 않은 결과는 직접 비교할 수 없습니다. 날짜는 논문 날짜이며 최신 평가일을 뜻하지 않습니다.

표가 화면보다 넓으면 좌우로 스크롤하여 논문과 구현 링크를 확인하세요.

원본 기록 순서 · 순위 미부여
모델	원본 지표·값	논문	구현
RIDE-DiVE	Top-1 Accuracy 57.12	Distilling Virtual Examples for Long-tailed Recognition 2021-03-28	코드 1
BCL(ResNeXt-50)	Top-1 Accuracy 57.1	Balanced Contrastive Learning for Long-Tailed Visual Recognition 2022-07-19	코드 1
RIDE (ResNeXt-50)	Top-1 Accuracy 56.4	Long-tailed Recognition by Routing Diverse Distribution-Aware Experts 2020-10-05	코드 1 · 코드 2
GLMC (ResNeXt-50)	Top-1 Accuracy 56.3	Global and Local Mixture Consistency Cumulative Learning for Long-tailed Visual Recognitions 2023-05-15	코드 1 · 코드 2
BatchFormer(ResNet-50, RIDE)	Top-1 Accuracy 55.7	BatchFormer: Learning to Explore Sample Relationships for Robust Representation Learning 2022-03-03	코드 1
CBD-ENS (ResNet-50)	Top-1 Accuracy 55.6	Class-Balanced Distillation for Long-Tailed Visual Recognition 2021-04-12	코드 1 · 코드 2 · 코드 3
ResLT(ResNeXt101-32x4d)	Top-1 Accuracy 55.1	ResLT: Residual Learning for Long-tailed Recognition 2021-01-26	코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5
OPeN (ResNeXt-50)	Top-1 Accuracy 55.1	Pure Noise to the Rescue of Insufficient Data: Improving Imbalanced Classification by Training on Random Noise Images 2021-12-16	코드 1
RIDE (ResNet-50)	Top-1 Accuracy 54.9	Long-tailed Recognition by Routing Diverse Distribution-Aware Experts 2020-10-05	코드 1 · 코드 2
Difficulty-Net (ResNet-50 w/o using RandAugment, single model)	Top-1 Accuracy 54.0	Difficulty-Net: Learning to Predict Difficulty for Long-Tailed Recognition 2022-09-07	코드 1
LTR-weight-balancing(ResNeXt-50)	Top-1 Accuracy 53.9	Long-Tailed Recognition via Weight Balancing 2022-03-27	코드 1 · 코드 2
DRO-LT	Top-1 Accuracy 53.5	Distributional Robustness Loss for Long-tail Learning 2021-04-07	연결 없음
DisAlign	Top-1 Accuracy 53.4	Distribution Alignment: A Unified Framework for Long-tail Visual Recognition 2021-03-30	코드 1
DiVE	Top-1 Accuracy 53.1	Distilling Virtual Examples for Long-tailed Recognition 2021-03-28	코드 1
LDAM + DRW + SAM	Top-1 Accuracy 53.1	Escaping Saddle Points for Effective Generalization on Class-Imbalanced Data 2022-12-28	코드 1
LADE	Top-1 Accuracy 53.0	Disentangling Label Distribution for Long-tailed Visual Recognition 2020-12-01	코드 1 · 코드 2
ResLT(ResNeXt50)	Top-1 Accuracy 52.9	ResLT: Residual Learning for Long-tailed Recognition 2021-01-26	코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5
MiSLAS	Top-1 Accuracy 52.7	Improving Calibration for Long-Tailed Recognition 2021-04-01	코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5
TSC(ResNet-50)	Top-1 Accuracy 52.4	Targeted Supervised Contrastive Learning for Long-Tailed Recognition 2021-11-27	코드 1
LDAM-DRS-RSG	Top-1 Accuracy 51.8	RSG: A Simple but Effective Module for Learning Imbalanced Datasets 2021-06-18	코드 1
De-confound-TDE	Top-1 Accuracy 51.8	Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect 2020-09-28	코드 1 · 코드 2
KCL	Top-1 Accuracy 51.5	Exploring Balanced Feature Spaces for Representation Learning 2021-01-01	연결 없음
cRT + SSP	Top-1 Accuracy 51.3	Rethinking the Value of Labels for Improving Class-Imbalanced Learning 2020-06-13	코드 1
Logit adjustment	Top-1 Accuracy 51.3	Long-tail learning via logit adjustment 2020-07-14	코드 1 · 코드 2 · 코드 3
MetaSAug (ResNet-152)	Top-1 Accuracy 50.03	MetaSAug: Meta Semantic Augmentation for Long-Tailed Visual Recognition 2021-03-23	코드 1
MetaSAug with CE loss	Top-1 Accuracy 47.39	MetaSAug: Meta Semantic Augmentation for Long-Tailed Visual Recognition 2021-03-23	코드 1
BLT (DenseNet-121)	Top-1 Accuracy 44.7	BLT: Balancing Long-Tailed Datasets with Adversarially-Perturbed Images 2020-10-30	코드 1
Difficulty-Net (ResNet-10 w/o using RandAugment, single model	Top-1 Accuracy 44.6	Difficulty-Net: Learning to Predict Difficulty for Long-Tailed Recognition 2022-09-07	코드 1
IEM	Top-1 Accuracy 43.2	Inflated Episodic Memory With Region Self-Attention for Long-Tailed Visual Recognition 2020-06-01	연결 없음
smDRAGON	Top-1 Accuracy 42.0	From Generalized zero-shot learning to long-tail with class descriptors 2020-04-05	코드 1