1 code implementation • 30 Oct 2021 • Akira Sakai, Taro Sunagawa, Spandan Madan, Kanata Suzuki, Takashi Katoh, Hiromichi Kobashi, Hanspeter Pfister, Pawan Sinha, Xavier Boix, Tomotake Sasaki
While humans have a remarkable capability of recognizing objects in out-of-distribution (OoD) orientations and illuminations, Deep Neural Networks (DNNs) severely suffer in this case, even when large amounts of training examples are available.
1 code implementation • ICLR Workshop GTRL 2021 • Arseny Tolmachev, Akira Sakai, Masaru Todoriki, Koji Maruhashi
Most graph neural network architectures work by message-passing node vector embeddings over the adjacency matrix, and it is assumed that they capture graph topology by doing that.