← Long-tail Learning
Papers with Code · CC BY-SA 4.0

iNaturalist 2018

아카이브 평가 43건 · 마지막 적재/변경

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
모델원본 지표·값논문구현
LIFT (ViT-L/14@336px)
Top-1 Accuracy
87.4%
Long-Tail Learning with Foundation Model: Heavy Fine-Tuning Hurts
2023-09-18
코드 1
LIFT (ViT-L/14)
Top-1 Accuracy
85.2%
Long-Tail Learning with Foundation Model: Heavy Fine-Tuning Hurts
2023-09-18
코드 1
GML (ViT-B-16)
Top-1 Accuracy
82.1%
Long-Tailed Recognition by Mutual Information Maximization between Latent Features and Ground-Truth Labels
2023-05-02
코드 1
VL-LTR (ViT-B-16)
Top-1 Accuracy
81.0%
VL-LTR: Learning Class-wise Visual-Linguistic Representation for Long-Tailed Visual Recognition
2021-11-26
코드 1
LIFT (ViT-B/16)
Top-1 Accuracy
80.4%
Long-Tail Learning with Foundation Model: Heavy Fine-Tuning Hurts
2023-09-18
코드 1
RAC (ViT-B-16)
Top-1 Accuracy
80.24%
Retrieval Augmented Classification for Long-Tail Visual Recognition
2022-02-22
연결 없음
GPaCo (2-R152)
Top-1 Accuracy
79.8%
Generalized Parametric Contrastive Learning
2022-09-26
코드 1 · 코드 2 · 코드 3 · 코드 4
GPaCo (ResNet-152)
Top-1 Accuracy
78.1%
Generalized Parametric Contrastive Learning
2022-09-26
코드 1 · 코드 2 · 코드 3 · 코드 4
TADE(ResNet-152)
Top-1 Accuracy
77%
Self-Supervised Aggregation of Diverse Experts for Test-Agnostic Long-Tailed Recognition
2021-07-20
코드 1 · 코드 2
ProCo (ResNet50)
Top-1 Accuracy
75.8%
Probabilistic Contrastive Learning for Long-Tailed Visual Recognition
2024-03-11
코드 1
MDCS(Resnet50)
Top-1 Accuracy
75.6%
MDCS: More Diverse Experts with Consistency Self-distillation for Long-tailed Recognition
2023-08-19
코드 1
GPaCo (ResNet-50)
Top-1 Accuracy
75.4%
Generalized Parametric Contrastive Learning
2022-09-26
코드 1 · 코드 2 · 코드 3 · 코드 4
CBD-ENS (ResNet-101)
Top-1 Accuracy
75.3%
Class-Balanced Distillation for Long-Tailed Visual Recognition
2021-04-12
코드 1 · 코드 2 · 코드 3
PaCo(ResNet-152)
Top-1 Accuracy
75.2%
Parametric Contrastive Learning
2021-07-26
코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5
DeiT-LT
Top-1 Accuracy
75.1%
DeiT-LT Distillation Strikes Back for Vision Transformer Training on Long-Tailed Datasets
2024-04-03
코드 1 · 코드 2
APA (SE-ResNet-50)
Top-1 Accuracy
74.8
Adaptive Parametric Activation
2024-07-11
코드 1
VL-LTR (ResNet-50)
Top-1 Accuracy
74.6%
VL-LTR: Learning Class-wise Visual-Linguistic Representation for Long-Tailed Visual Recognition
2021-11-26
코드 1
GML (ResNet-50)
Top-1 Accuracy
74.5%
Long-Tailed Recognition by Mutual Information Maximization between Latent Features and Ground-Truth Labels
2023-05-02
코드 1
NCL(ResNet-50)
Top-1 Accuracy
74.2%
Nested Collaborative Learning for Long-Tailed Visual Recognition
2022-03-29
코드 1
BatchFormer(ResNet-50, RIDE)
Top-1 Accuracy
74.1%
BatchFormer: Learning to Explore Sample Relationships for Robust Representation Learning
2022-03-03
코드 1
CBD-ENS (ResNet-50)
Top-1 Accuracy
73.6%
Class-Balanced Distillation for Long-Tailed Visual Recognition
2021-04-12
코드 1 · 코드 2 · 코드 3
RIDE-DiVE
Top-1 Accuracy
73.44%
Distilling Virtual Examples for Long-tailed Recognition
2021-03-28
코드 1
DirMixE
Top-1 Accuracy
73.21%
Harnessing Hierarchical Label Distribution Variations in Test Agnostic Long-tail Recognition
2024-05-13
코드 1
TADE
Top-1 Accuracy
72.9%
Self-Supervised Aggregation of Diverse Experts for Test-Agnostic Long-Tailed Recognition
2021-07-20
코드 1 · 코드 2
ResLT(3 experts)
Top-1 Accuracy
72.9%
ResLT: Residual Learning for Long-tailed Recognition
2021-01-26
코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5
RIDE
Top-1 Accuracy
72.2%
Long-tailed Recognition by Routing Diverse Distribution-Aware Experts
2020-10-05
코드 1 · 코드 2
BCL(ResNet-50)
Top-1 Accuracy
71.8%
Balanced Contrastive Learning for Long-Tailed Visual Recognition
2022-07-19
코드 1
DiVE
Top-1 Accuracy
71.71%
Distilling Virtual Examples for Long-tailed Recognition
2021-03-28
코드 1
MiSLAS
Top-1 Accuracy
71.6%
Improving Calibration for Long-Tailed Recognition
2021-04-01
코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5
DisAlign
Top-1 Accuracy
70.6%
Distribution Alignment: A Unified Framework for Long-tail Visual Recognition
2021-03-30
코드 1