1. Is label smoothing truly incompatible with knowledge distillation: An empirical study;shen;International Conference on Learning Representations,0
2. Sliced recursive transformer;shen;ArXiv Preprint,2021
3. Binarizing MobileNet via Evolution-Based Searching
4. When does label smoothing help?;müller;Advances in neural information processing systems,2019
5. Shufflenet v2: Practical guidelines for efficient cnn architecture design;ma;Proceedings of the European Conference on Computer Vision (ECCV),0