1 code implementation • NeurIPS 2019 • Yuan Liu, Zehong Shen, Zhixuan Lin, Sida Peng, Hujun Bao, Xiaowei Zhou
Instead of feature pooling, we use group convolutions to exploit underlying structures of the extracted features on the group, resulting in descriptors that are both discriminative and provably invariant to the group of transformations.
4 code implementations • ICLR 2020 • Zhixuan Lin, Yi-Fu Wu, Skand Vishwanath Peri, Weihao Sun, Gautam Singh, Fei Deng, Jindong Jiang, Sungjin Ahn
Previous approaches for unsupervised object-oriented scene representation learning are either based on spatial-attention or scene-mixture approaches and limited in scalability which is a main obstacle towards modeling real-world scenes.
no code implementations • ICML 2020 • Zhixuan Lin, Yi-Fu Wu, Skand Peri, Bofeng Fu, Jindong Jiang, Sungjin Ahn
The G-SWM not only unifies the key properties of previous models in a principled framework but also achieves two crucial new abilities, multi-modal uncertainty and situated behavior.
no code implementations • 5 Oct 2020 • Zhixuan Lin, Yi-Fu Wu, Skand Peri, Bofeng Fu, Jindong Jiang, Sungjin Ahn
Third, a few key abilities for more faithful temporal imagination such as multimodal uncertainty and situation-awareness are missing.