Unsupervised Domain Adaptation on ImageNet-C

Metric: mean Corruption Error (mCE) (lower is better)

LeaderboardDataset

Loading chart...

Results

Hide extra data

Sort:

#	Model↕	mean Corruption Error (mCE)▲	Extra Data	Paper	Date↕	Code
1	EfficientNet-L2+RPL	22	Yes	If your data distribution shifts, use self-learn...	2021-04-27	Code
2	EfficientNet-L2+ENT	23	Yes	If your data distribution shifts, use self-learn...	2021-04-27	Code
3	ResNeXt101 32x8d + DeepAug + Augmix + RPL	34.8	No	If your data distribution shifts, use self-learn...	2021-04-27	Code
4	ResNeXt101 32x8d + DeepAug + Augmix + ENT	35.5	No	If your data distribution shifts, use self-learn...	2021-04-27	Code
5	ResNeXt101+DeepAug+AugMix, BatchNorm Adaptation, full adaptation	38	No	Improving robustness against common corruptions ...	2020-06-30	Code
6	ResNeXt101+DeepAug+AugMix, BatchNorm Adaptation, 8 samples	40.7	No	Improving robustness against common corruptions ...	2020-06-30	Code
7	ResNeXt101 32x8d + IG-3.5B + ENT	40.8	Yes	If your data distribution shifts, use self-learn...	2021-04-27	Code
8	ResNeXt101 32x8d + IG-3.5B + RPL	40.9	Yes	If your data distribution shifts, use self-learn...	2021-04-27	Code
9	ResNeXt101 32x8d + RPL	43.2	No	If your data distribution shifts, use self-learn...	2021-04-27	Code
10	ResNeXt101 32x8d + ENT	44.3	No	If your data distribution shifts, use self-learn...	2021-04-27	Code
11	ResNet50+DeepAug+AugMix, BatchNorm Adaptation, full adaptation	45.4	No	Improving robustness against common corruptions ...	2020-06-30	Code
12	ResNet50+DeepAug+AugMix, BatchNorm Adaptation, 8 samples	48.4	No	Improving robustness against common corruptions ...	2020-06-30	Code
13	ResNet50 + RPL	50.5	No	If your data distribution shifts, use self-learn...	2021-04-27	Code
14	ResNet50 + ENT	51.6	No	If your data distribution shifts, use self-learn...	2021-04-27	Code
15	ResNet50 (baseline), BatchNorm Adaptation, full adaptation	62.2	No	Improving robustness against common corruptions ...	2020-06-30	Code
16	ResNet50 (baseline), BatchNorm Adaptation, 8 samples	65	No	Improving robustness against common corruptions ...	2020-06-30	Code

#1EfficientNet-L2+RPLSOTA
22
mean Corruption Error (mCE)· Extra Data· 2021-04-27
If your data distribution shifts, use self-learning Code
#2EfficientNet-L2+ENTSOTA
23
mean Corruption Error (mCE)· Extra Data· 2021-04-27
If your data distribution shifts, use self-learning Code
#3ResNeXt101 32x8d + DeepAug + Augmix + RPLSOTA
34.8
mean Corruption Error (mCE)· 2021-04-27
If your data distribution shifts, use self-learning Code
#4ResNeXt101 32x8d + DeepAug + Augmix + ENTSOTA
35.5
mean Corruption Error (mCE)· 2021-04-27
If your data distribution shifts, use self-learning Code
#5ResNeXt101+DeepAug+AugMix, BatchNorm Adaptation, full adaptationSOTA
38
mean Corruption Error (mCE)· 2020-06-30
Improving robustness against common corruptions by covariate shift adaptation Code
#6ResNeXt101+DeepAug+AugMix, BatchNorm Adaptation, 8 samplesSOTA
40.7
mean Corruption Error (mCE)· 2020-06-30
Improving robustness against common corruptions by covariate shift adaptation Code
#7ResNeXt101 32x8d + IG-3.5B + ENT
40.8
mean Corruption Error (mCE)· Extra Data· 2021-04-27
If your data distribution shifts, use self-learning Code
#8ResNeXt101 32x8d + IG-3.5B + RPL
40.9
mean Corruption Error (mCE)· Extra Data· 2021-04-27
If your data distribution shifts, use self-learning Code
#9ResNeXt101 32x8d + RPL
43.2
mean Corruption Error (mCE)· 2021-04-27
If your data distribution shifts, use self-learning Code
#10ResNeXt101 32x8d + ENT
44.3
mean Corruption Error (mCE)· 2021-04-27
If your data distribution shifts, use self-learning Code
#11ResNet50+DeepAug+AugMix, BatchNorm Adaptation, full adaptationSOTA
45.4
mean Corruption Error (mCE)· 2020-06-30
Improving robustness against common corruptions by covariate shift adaptation Code
#12ResNet50+DeepAug+AugMix, BatchNorm Adaptation, 8 samplesSOTA
48.4
mean Corruption Error (mCE)· 2020-06-30
Improving robustness against common corruptions by covariate shift adaptation Code
#13ResNet50 + RPL
50.5
mean Corruption Error (mCE)· 2021-04-27
If your data distribution shifts, use self-learning Code
#14ResNet50 + ENT
51.6
mean Corruption Error (mCE)· 2021-04-27
If your data distribution shifts, use self-learning Code
#15ResNet50 (baseline), BatchNorm Adaptation, full adaptationSOTA
62.2
mean Corruption Error (mCE)· 2020-06-30
Improving robustness against common corruptions by covariate shift adaptation Code
#16ResNet50 (baseline), BatchNorm Adaptation, 8 samplesSOTA
65
mean Corruption Error (mCE)· 2020-06-30
Improving robustness against common corruptions by covariate shift adaptation Code