1 code implementation • 19 May 2022 • Minh Tran, Viet-Khoa Vo-Ho, Ngan T. H. Le
Capsule network is a recent new architecture that has achieved better robustness in part-whole representation learning by replacing pooling layers with dynamic routing and convolutional strides, which has shown potential results on popular tasks such as digit classification and object segmentation.
no code implementations • 20 Feb 2021 • Duc Quang Vu, Ngan T. H. Le, Jia-Ching Wang
We use the learned models in pretext tasks as the pre-trained models and fine-tune them to recognize human actions in the downstream task.