Abstract: We present a simple self-training method that achieves 88.4% top-1 accuracy on ImageNet, which is 2.0% better than the state-of-the-art model that requires 3.5B weakly labeled Instagram ...
1 Department of Mathematics and Information Technology, The Education University of Hong Kong, Hong Kong, China 2 Faculty of Education, The University of Hong Kong, Hong Kong, China Mathematics is one ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback