-
Adversarial Transformations for Semi-Supervised Learning
We propose a Regularization framework based on Adversarial Transformatio...
read it
-
Breaking Inter-Layer Co-Adaptation by Classifier Anonymization
This study addresses an issue of co-adaptation between a feature extract...
read it
-
Towards Human-Friendly Referring Expression Generation
This paper addresses the generation of referring expressions that not on...
read it
-
Canonical and Compact Point Cloud Representation for Shape Classification
We present a novel compact point cloud representation that is inherently...
read it
-
Binary-decomposed DCNN for accelerating computation and compressing model without retraining
Recent trends show recognition accuracy increasing even more profoundly....
read it
-
Pairwise Rotation Hashing for High-dimensional Features
Binary Hashing is widely used for effective approximate nearest neighbor...
read it

Ikuro Sato
is this you? claim profile