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
LIFT (ViT-L/14)	Top-1 Accuracy 82.9	Long-Tail Learning with Foundation Model: Heavy Fine-Tuning Hurts 2023-09-18	코드 1
µ2Net+ (ViT-L/16)	Top-1 Accuracy 82.5	A Continual Development Methodology for Large-scale Multitask Dynamic ML Systems 2022-09-15	코드 1
MAM (ViT-B/16)	Top-1 Accuracy 82.3	Improving Image Recognition by Retrieving from Web-Scale Image-Text Data 2023-04-11	연결 없음
LIFT (ViT-B/16)	Top-1 Accuracy 78.3	Long-Tail Learning with Foundation Model: Heavy Fine-Tuning Hurts 2023-09-18	코드 1
VL-LTR (ViT-B-16)	Top-1 Accuracy 77.2	VL-LTR: Learning Class-wise Visual-Linguistic Representation for Long-Tailed Visual Recognition 2021-11-26	코드 1
BALLAD(ResNet-50×16)	Top-1 Accuracy 76.5	A Simple Long-Tailed Recognition Baseline via Vision-Language Model 2021-11-29	코드 1
BALLAD(ViT-B-16)	Top-1 Accuracy 75.7	A Simple Long-Tailed Recognition Baseline via Vision-Language Model 2021-11-29	코드 1
BALLAD(ResNet-101)	Top-1 Accuracy 70.5	A Simple Long-Tailed Recognition Baseline via Vision-Language Model 2021-11-29	코드 1
VL-LTR (ResNet-50)	Top-1 Accuracy 70.1	VL-LTR: Learning Class-wise Visual-Linguistic Representation for Long-Tailed Visual Recognition 2021-11-26	코드 1
BALLAD(ResNet-50)	Top-1 Accuracy 67.2	A Simple Long-Tailed Recognition Baseline via Vision-Language Model 2021-11-29	코드 1
GPaCo (2-ResNeXt101-32x4d)	Top-1 Accuracy 63.2	Generalized Parametric Contrastive Learning 2022-09-26	코드 1 · 코드 2 · 코드 3 · 코드 4
MDCS (ResNeXt-50)	Top-1 Accuracy 61.8	MDCS: More Diverse Experts with Consistency Self-distillation for Long-tailed Recognition 2023-08-19	코드 1
TADE(ResNeXt101-32x4d)	Top-1 Accuracy 61.4	Self-Supervised Aggregation of Diverse Experts for Test-Agnostic Long-Tailed Recognition 2021-07-20	코드 1 · 코드 2
ProCo (ResNet50)	Top-1 Accuracy 60.2	Probabilistic Contrastive Learning for Long-Tailed Visual Recognition 2024-03-11	코드 1
PaCo(ResNeXt101-32x4d)	Top-1 Accuracy 60.0	Parametric Contrastive Learning 2021-07-26	코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5
DeiT-LT	Top-1 Accuracy 59.1	DeiT-LT Distillation Strikes Back for Vision Transformer Training on Long-Tailed Datasets 2024-04-03	코드 1 · 코드 2
APA (SE-ResNext-50)	Top-1 Accuracy 59.1	Adaptive Parametric Activation 2024-07-11	코드 1
TADE(ResNeXt-50)	Top-1 Accuracy 58.8	Self-Supervised Aggregation of Diverse Experts for Test-Agnostic Long-Tailed Recognition 2021-07-20	코드 1 · 코드 2
GML (ResNeXt-50)	Top-1 Accuracy 58.8	Long-Tailed Recognition by Mutual Information Maximization between Latent Features and Ground-Truth Labels 2023-05-02	코드 1
DirMixE(ResNeXt-50)	Top-1 Accuracy 58.61	Harnessing Hierarchical Label Distribution Variations in Test Agnostic Long-tail Recognition 2024-05-13	코드 1
NCL(ResNeXt-50)	Top-1 Accuracy 58.4	Nested Collaborative Learning for Long-Tailed Visual Recognition 2022-03-29	코드 1
PaCo(ResNeXt-50)	Top-1 Accuracy 58.2	Parametric Contrastive Learning 2021-07-26	코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5
BS-CMO (ResNet-50)	Top-1 Accuracy 58.0	The Majority Can Help The Minority: Context-rich Minority Oversampling for Long-tailed Classification 2021-12-01	코드 1
ProCo (ResNeXt50)	Top-1 Accuracy 58.0	Probabilistic Contrastive Learning for Long-Tailed Visual Recognition 2024-03-11	코드 1
APA (SE-ResNet-50)	Top-1 Accuracy 57.9	Adaptive Parametric Activation 2024-07-11	코드 1
CBD-ENS (ResNet-152)	Top-1 Accuracy 57.7	Class-Balanced Distillation for Long-Tailed Visual Recognition 2021-04-12	코드 1 · 코드 2 · 코드 3
ResLT(ResNeXt-50-3 experts)	Top-1 Accuracy 57.6	ResLT: Residual Learning for Long-tailed Recognition 2021-01-26	코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5
BatchFormer(ResNet-50, PaCo)	Top-1 Accuracy 57.4	BatchFormer: Learning to Explore Sample Relationships for Robust Representation Learning 2022-03-03	코드 1
NCL(ResNet-50)	Top-1 Accuracy 57.4	Nested Collaborative Learning for Long-Tailed Visual Recognition 2022-03-29	코드 1
Difficulty-Net (ResNet-50 using RandAugment, single model)	Top-1 Accuracy 57.4	Difficulty-Net: Learning to Predict Difficulty for Long-Tailed Recognition 2022-09-07	코드 1