PUAD: Frustratingly Simple Method for Robust Anomaly Detection

1 code implementation • 23 Feb 2024 • Shota Sugawara, Ryuji Imamura

However, we argue that logical anomalies, such as the wrong number of objects, can not be well-represented by the spatial feature maps and require an alternative approach.

Anomaly Detection Out-of-Distribution Detection

Expert Human-Level Driving in Gran Turismo Sport Using Deep Reinforcement Learning with Image-based Representation

no code implementations • 11 Nov 2021 • Ryuji Imamura, Takuma Seno, Kenta Kawamoto, Michael Spranger

We demonstrate that the proposed method performs expert human-level vehicle control under high-speed driving scenarios even with game screen images as high-dimensional inputs.

MLF-SC: Incorporating multi-layer features to sparse coding for anomaly detection

1 code implementation • 9 Apr 2021 • Ryuji Imamura, Kohei Azuma, Atsushi Hanamoto, Atsunori Kanemura

The proposed method, multi-layer feature sparse coding (MLF-SC), employs a neural network for feature extraction, and feature maps from intermediate layers of the network are given to sparse coding, whereas the standard sparse-coding-based anomaly detection method directly works on given images.

Anomaly Detection

Self-supervised Hyperspectral Image Restoration using Separable Image Prior

no code implementations • 1 Jul 2019 • Ryuji Imamura, Tatsuki Itasaka, Masahiro Okuda

Another notable feature of our method is the use of a separable convolutional layer.

Denoising Image Restoration +1