4 citations · 7 across the 3 of their papers we have counts for
3 papers
cs.CV2023★ 4 cited
Style Feature Extraction Using Contrastive Conditioned Variational Autoencoders with Mutual Information Constraints
Suguru Yasutomi, Toshihisa Tanaka
Extracting fine-grained features such as styles from unlabeled data is crucial for data analysis. Unsupervised methods such as variational autoencoders (VAEs) can extract styles th…
stat.ML2020★ 2 cited
Selective Forgetting of Deep Networks at a Finer Level than Samples
Tomohiro Hayase, Suguru Yasutomi, Takashi Katoh
Selective forgetting or removing information from deep neural networks (DNNs) is essential for continual learning and is challenging in controlling the DNNs. Such forgetting is cru…
eess.IV2019★ 1 cited
Shadow Detection for Ultrasound Images Using Unlabeled Data and Synthetic Shadows
Suguru Yasutomi, Tatsuya Arakaki, Ryuji Hamamoto
Medical ultrasound is widely used technique for diagnosing internal organs. As common artifacts, shadows often appear in ultrasound images. Detecting such shadows is curious becaus…