no code implementations • CVPR 2022 • Dong-Hwan Jang, Sanghyeok Chu, Joonhyuk Kim, Bohyung Han
The size and shape of the receptive field determine how the network aggregates local information and affect the overall performance of a model considerably.
no code implementations • NeurIPS 2021 • Sanghyeok Chu, Dongwan Kim, Bohyung Han
By randomly eliminating certain class information in each training iteration, we effectively reduce feature dependencies among classes, and the model is able to learn more debiased and disentangled feature representations.