Papers with Code · CC BY-SA 4.0

CIFAR-100-LT (ρ=100)

아카이브 평가 66건 · 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
LPT	Error Rate 10.9	LPT: Long-tailed Prompt Tuning for Image Classification 2022-10-03	코드 1
LIFT (ViT-B/16, ImageNet-21K pre-training)	Error Rate 10.9	Long-Tail Learning with Foundation Model: Heavy Fine-Tuning Hurts 2023-09-18	코드 1
LIFT (ViT-B/16, CLIP)	Error Rate 18.3	Long-Tail Learning with Foundation Model: Heavy Fine-Tuning Hurts 2023-09-18	코드 1
VPT	Error Rate 19	Visual Prompt Tuning 2022-03-23	코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6
BALLAD (ViT-B/16)	Error Rate 22.2	A Simple Long-Tailed Recognition Baseline via Vision-Language Model 2021-11-29	코드 1
GLMC + SAM	Error Rate 40.99	Escaping Saddle Points for Effective Generalization on Class-Imbalanced Data 2022-12-28	코드 1
GLMC+MaxNorm (ResNet-34, channel x4)	Error Rate 41.59	Global and Local Mixture Consistency Cumulative Learning for Long-tailed Visual Recognitions 2023-05-15	코드 1 · 코드 2
GLMC (ResNet-34, channel x4)	Error Rate 42.01	Global and Local Mixture Consistency Cumulative Learning for Long-tailed Visual Recognitions 2023-05-15	코드 1 · 코드 2
SURE(ResNet-32)	Error Rate 43.66	SURE: SUrvey REcipes for building reliable and robust deep networks 2024-03-01	코드 1
MDCS	Error Rate 43.9	MDCS: More Diverse Experts with Consistency Self-distillation for Long-tailed Recognition 2023-08-19	코드 1
DeiT-LT	Error Rate 44.4	DeiT-LT Distillation Strikes Back for Vision Transformer Training on Long-Tailed Datasets 2024-04-03	코드 1 · 코드 2
NCL* + WGCC (ensemble)	Error Rate 44.9	Weight-guided class complementing for long-tailed image recognition 2023-02-03	연결 없음
OPeN (WideResNet-28-10)	Error Rate 45.8	Pure Noise to the Rescue of Insufficient Data: Improving Imbalanced Classification by Training on Random Noise Images 2021-12-16	코드 1
GML (ResNet-32)	Error Rate 46.0	Long-Tailed Recognition by Mutual Information Maximization between Latent Features and Ground-Truth Labels 2023-05-02	코드 1
BCL(ResNet-32)	Error Rate 46.1	Balanced Contrastive Learning for Long-Tailed Visual Recognition 2022-07-19	코드 1
LTR-weight-balancing	Error Rate 46.45	Long-Tailed Recognition via Weight Balancing 2022-03-27	코드 1 · 코드 2
PC	Error Rate 46.59	Learning Prototype Classifiers for Long-Tailed Recognition 2023-02-01	코드 1
NCL(ResNet32)	Error Rate 46.7	Nested Collaborative Learning for Long-Tailed Visual Recognition 2022-03-29	코드 1
ConCutMix	Error Rate 46.84	Enhanced Long-Tailed Recognition with Contrastive CutMix Augmentation 2024-07-06	코드 1 · 코드 2
VS + ADRW + TLA	Error Rate 46.95	A Unified Generalization Analysis of Re-Weighting and Logit-Adjustment for Imbalanced Learning. paper with code 2023-10-07	코드 1
PaCo + SAM	Error Rate 47.0	Escaping Saddle Points for Effective Generalization on Class-Imbalanced Data 2022-12-28	코드 1
Difficulty-Net	Error Rate 47.04	Difficulty-Net: Learning to Predict Difficulty for Long-Tailed Recognition 2022-09-07	코드 1
Paco + BatchFormer	Error Rate 47.6	BatchFormer: Learning to Explore Sample Relationships for Robust Representation Learning 2022-03-03	코드 1
GLAG	Error Rate 48.3	Long-Tailed Classification with Gradual Balanced Loss and Adaptive Feature Generation 2022-02-28	연결 없음
Balanced + BatchFormer	Error Rate 48.3	BatchFormer: Learning to Explore Sample Relationships for Robust Representation Learning 2022-03-03	코드 1
PCL	Error Rate 49.10	Parametric Contrastive Learning 2021-07-26	코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5
RIDE + CMO + Curvature Regularization	Error Rate 49.3	Predicting and Enhancing the Fairness of DNNs with the Curvature of Perceptual Manifolds 2023-03-22	코드 1 · 코드 2
RIDE 3 experts + CMO	Error Rate 50	The Majority Can Help The Minority: Context-rich Minority Oversampling for Long-tailed Classification 2021-12-01	코드 1
TADE	Error Rate 50.2	Self-Supervised Aggregation of Diverse Experts for Test-Agnostic Long-Tailed Recognition 2021-07-20	코드 1 · 코드 2
TLC (4 Experts)	Error Rate 50.2	Trustworthy Long-Tailed Classification 2021-11-17	코드 1 · 코드 2