← Image Classification
Papers with Code · CC BY-SA 4.0

mini WebVision 1.0

아카이브 평가 47건 · 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
DivideMix (Inception-ResNet-v2)
Top-1 Accuracy
77.32
Top-5 Accuracy
91.64
ImageNet Top-1 Accuracy
75.20
ImageNet Top-5 Accuracy
91.64
DivideMix: Learning with Noisy Labels as Semi-supervised Learning
2020-02-18
코드 1 · 코드 2
NCR (ResNet-50)
Top-1 Accuracy
77.1
Learning with Neighbor Consistency for Noisy Labels
2022-02-04
코드 1
DivideMix (ResNet-50)
Top-1 Accuracy
76.32 ±0.36
Top-5 Accuracy
90.65 ±0.16
ImageNet Top-1 Accuracy
74.42 ±0.29
ImageNet Top-5 Accuracy
91.21 ±0.12
DivideMix: Learning with Noisy Labels as Semi-supervised Learning
2020-02-18
코드 1 · 코드 2
DivideMix (ResNet-18)
Top-1 Accuracy
76.08
DivideMix: Learning with Noisy Labels as Semi-supervised Learning
2020-02-18
코드 1 · 코드 2
MentorMix (Inception-ResNet-v2)
Top-1 Accuracy
76.0
Top-5 Accuracy
90.2
ImageNet Top-1 Accuracy
72.9
ImageNet Top-5 Accuracy
91.1
Beyond Synthetic Noise: Deep Learning on Controlled Noisy Labels
2019-11-21
코드 1 · 코드 2 · 코드 3
NCT (Inception-ResNet-v2)
Top-1 Accuracy
75.16
Top-5 Accuracy
90.77
ImageNet Top-1 Accuracy
71.73
ImageNet Top-5 Accuracy
91.61
Noisy Concurrent Training for Efficient Learning under Label Noise
2020-09-17
코드 1 · 코드 2
ODD (Inception-ResNet-v2)
Top-1 Accuracy
74.6
Top-5 Accuracy
90.6
ImageNet Top-1 Accuracy
66.7
ImageNet Top-5 Accuracy
86.3
Robust and On-the-fly Dataset Denoising for Image Classification
2020-03-24
연결 없음
Crust (Inception-ResNet-v2)
Top-1 Accuracy
72.40
Top-5 Accuracy
89.56
ImageNet Top-1 Accuracy
67.36
ImageNet Top-5 Accuracy
87.84
Coresets for Robust Training of Neural Networks against Noisy Labels
2020-11-15
연결 없음
Iterative-CV (Inception-ResNet-v2)
Top-1 Accuracy
65.2
Top-5 Accuracy
85.3
ImageNet Top-1 Accuracy
61.6
ImageNet Top-5 Accuracy
85.0
Understanding and Utilizing Deep Neural Networks Trained with Noisy Labels
2019-05-13
코드 1 · 코드 2 · 코드 3
Co-teaching (Inception-ResNet-v2)
Top-1 Accuracy
63.58
Top-5 Accuracy
85.20
ImageNet Top-1 Accuracy
61.48
ImageNet Top-5 Accuracy
84.70
Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels
2018-04-18
코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5
D2L (Inception-ResNet-v2)
Top-1 Accuracy
62.68
Top-5 Accuracy
84.00
ImageNet Top-1 Accuracy
57.80
ImageNet Top-5 Accuracy
81.36
Dimensionality-Driven Learning with Noisy Labels
2018-06-07
코드 1 · 코드 2 · 코드 3
F-Correction (Inception-ResNet-v2)
Top-1 Accuracy
61.12
Top-5 Accuracy
82.68
ImageNet Top-1 Accuracy
57.36
ImageNet Top-5 Accuracy
82.36
Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach
2016-09-13
코드 1 · 코드 2
RTE (Inception-ResNet-v2)
ImageNet Top-1 Accuracy
80.84
ImageNet Top-5 Accuracy
97.24
Robust Temporal Ensembling for Learning with Noisy Labels
2021-09-29
연결 없음
MentorNet (Inception-ResNet-v2)
ImageNet Top-1 Accuracy
63.8
ImageNet Top-5 Accuracy
85.8
MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels
2017-12-14
코드 1
NCE+RCE (ResNet-50)
ImageNet Top-1 Accuracy
62.64
Normalized Loss Functions for Deep Learning with Noisy Labels
2020-06-24
코드 1 · 코드 2 · 코드 3 · 코드 4
NCE+MAE (ResNet-50)
ImageNet Top-1 Accuracy
62.36
Normalized Loss Functions for Deep Learning with Noisy Labels
2020-06-24
코드 1 · 코드 2 · 코드 3 · 코드 4
CDR (Inception-ResNet-v2)
ImageNet Top-1 Accuracy
61.85
Robust early-learning: Hindering the memorization of noisy labels
2021-01-01
연결 없음