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
ACE (4 experts)	Error Rate 50.4	ACE: Ally Complementary Experts for Solving Long-Tailed Recognition in One-Shot 2021-08-05	연결 없음
RIDE+distill	Error Rate 50.9	Long-tailed Recognition by Routing Diverse Distribution-Aware Experts 2020-10-05	코드 1 · 코드 2
GCL	Error Rate 51.29	Long-tailed Visual Recognition via Gaussian Clouded Logit Adjustment 2023-05-19	코드 1
DirMixE	Error Rate 51.62	Harnessing Hierarchical Label Distribution Variations in Test Agnostic Long-tail Recognition 2024-05-13	코드 1
MetaSAug-LDAM	Error Rate 51.99	MetaSAug: Meta Semantic Augmentation for Long-Tailed Visual Recognition 2021-03-23	코드 1
RIDE	Error Rate 52	Long-tailed Recognition by Routing Diverse Distribution-Aware Experts 2020-10-05	코드 1 · 코드 2
DRO-LT	Error Rate 52.67	Distributional Robustness Loss for Long-tail Learning 2021-04-07	연결 없음
LDAM-DRW + CMO	Error Rate 52.8	The Majority Can Help The Minority: Context-rich Minority Oversampling for Long-tailed Classification 2021-12-01	코드 1
MiSLAS	Error Rate 53	Improving Calibration for Long-Tailed Recognition 2021-04-01	코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5
Balanced Softmax + CMO	Error Rate 53.4	The Majority Can Help The Minority: Context-rich Minority Oversampling for Long-tailed Classification 2021-12-01	코드 1
VS + SAM	Error Rate 53.4	Escaping Saddle Points for Effective Generalization on Class-Imbalanced Data 2022-12-28	코드 1
CBD+TailCalibX	Error Rate 53.41	Feature Generation for Long-tail Classification 2021-11-10	코드 1
Prior-LT	Error Rate 53.59	Towards Calibrated Model for Long-Tailed Visual Recognition from Prior Perspective 2021-11-06	코드 1
OTLM+CE (Resnet-32)	Error Rate 53.90	Optimal Transport for Long-Tailed Recognition with Learnable Cost Matrix 2021-09-29	연결 없음
SSD	Error Rate 54.00	Self Supervision to Distillation for Long-Tailed Visual Recognition 2021-09-09	코드 1
MBJ	Error Rate 54.2	Memory-based Jitter: Improving Visual Recognition on Long-tailed Data with Diversity In Memory 2020-08-22	연결 없음
UniMix+Bayias (ResNet-32)	Error Rate 54.55	Towards Calibrated Model for Long-Tailed Visual Recognition from Prior Perspective 2021-11-06	코드 1
LADE	Error Rate 54.6	Disentangling Label Distribution for Long-tailed Visual Recognition 2020-12-01	코드 1 · 코드 2
ETF Classifier + DR (Resnet)	Error Rate 54.7	Inducing Neural Collapse in Imbalanced Learning: Do We Really Need a Learnable Classifier at the End of Deep Neural Network? 2022-03-17	코드 1
FBL (Resnet-32)	Error Rate 54.78	Feature-Balanced Loss for Long-Tailed Visual Recognition 2023-05-18	코드 1
Hybrid-PSC	Error Rate 55.03	Contrastive Learning based Hybrid Networks for Long-Tailed Image Classification 2021-03-26	연결 없음
LDAM-DRW-RSG	Error Rate 55.5	RSG: A Simple but Effective Module for Learning Imbalanced Datasets 2021-06-18	코드 1
CE+DRS+GIT	Error Rate 55.65	Do Deep Networks Transfer Invariances Across Classes? 2022-03-18	코드 1
TSC(ResNet-32)	Error Rate 56.2	Targeted Supervised Contrastive Learning for Long-Tailed Recognition 2021-11-27	코드 1
LDAM-DRW + WGCC	Error Rate 56.4	Weight-guided class complementing for long-tailed image recognition 2023-02-03	연결 없음
smDRAGON	Error Rate 56.50	From Generalized zero-shot learning to long-tail with class descriptors 2020-04-05	코드 1
LDAM-DRW + SSP	Error Rate 56.57	Rethinking the Value of Labels for Improving Class-Imbalanced Learning 2020-06-13	코드 1
CE-DRW-IC	Error Rate 56.9	Posterior Re-calibration for Imbalanced Datasets 2020-10-22	연결 없음
CDB-loss	Error Rate 57.43	Class-Wise Difficulty-Balanced Loss for Solving Class-Imbalance 2020-10-05	코드 1
ELP	Error Rate 57.6	A Simple Episodic Linear Probe Improves Visual Recognition in the Wild 2022-01-01	코드 1 · 코드 2