4 citations · 14 across the 13 of their papers we have counts for
6 papers · 1 filter
Adversarial Training Makes Weight Loss Landscape Sharper in Logistic Regression
Masanori Yamada, Sekitoshi Kanai, Tomoharu Iwata +4
Adversarial training is actively studied for learning robust models against adversarial examples. A recent study finds that adversarially trained models degenerate generalization p…
Constraining Logits by Bounded Function for Adversarial Robustness
Sekitoshi Kanai, Masanori Yamada, Shin'ya Yamaguchi +2
We propose a method for improving adversarial robustness by addition of a new bounded function just before softmax. Recent studies hypothesize that small logits (inputs of softmax)…
Effective Data Augmentation with Multi-Domain Learning GANs
Shin'ya Yamaguchi, Sekitoshi Kanai, Takeharu Eda
For deep learning applications, the massive data development (e.g., collecting, labeling), which is an essential process in building practical applications, still incurs seriously…
Absum: Simple Regularization Method for Reducing Structural Sensitivity of Convolutional Neural Networks
Sekitoshi Kanai, Yasutoshi Ida, Yasuhiro Fujiwara +2
We propose Absum, which is a regularization method for improving adversarial robustness of convolutional neural networks (CNNs). Although CNNs can accurately recognize images, rece…
Autoencoding Binary Classifiers for Supervised Anomaly Detection
Yuki Yamanaka, Tomoharu Iwata, Hiroshi Takahashi +2
We propose the Autoencoding Binary Classifiers (ABC), a novel supervised anomaly detector based on the Autoencoder (AE). There are two main approaches in anomaly detection: supervi…
Sigsoftmax: Reanalysis of the Softmax Bottleneck
Sekitoshi Kanai, Yasuhiro Fujiwara, Yuki Yamanaka +1
Softmax is an output activation function for modeling categorical probability distributions in many applications of deep learning. However, a recent study revealed that softmax can…