Image Retrieval on Caltech-UCSD Birds 200-2011 (CUB) (test)
40.4mAPReViSE
Evaluation results
| Method | Links | ||
|---|---|---|---|
| ReViSETraining Data=labeled and unlabeled training data, Attribute Type=att, Backbone=GoogLeNet2017.03 | 40.4 | 57.6 | |
| CMT*Training Data=labeled and unlabeled training data, Attribute Type=att, Backbone=GoogLeNet, Note=with unsupervised-data adaptation2017.03 | 38 | 49.6 | |
| ReViSEcTraining Data=labeled and unlabeled training data, Attribute Type=att, Backbone=GoogLeNet, Note=without unsupervised-data adaptation (beta=0)2017.03 | 37.5 | 51.8 | |
| ReViSEbTraining Data=labeled training data only, Attribute Type=att, Backbone=GoogLeNet, Objective=supervised + unsupervised on labeled data2017.03 | 37.4 | 50.3 | |
| CMTTraining Data=labeled training data only, Attribute Type=att, Backbone=GoogLeNet2017.03 | 37 | 48.3 | |
| ReViSEaTraining Data=labeled training data only, Attribute Type=att, Backbone=GoogLeNet, Objective=supervised only (alpha=0)2017.03 | 32 | 46.4 | |
| DeViSETraining Data=labeled training data only, Attribute Type=att, Backbone=GoogLeNet2017.03 | 31.5 | 46.6 | |
| DeViSE*Training Data=labeled and unlabeled training data, Attribute Type=att, Backbone=GoogLeNet, Note=with unsupervised-data adaptation2017.03 | 31.3 | 47.8 |