3 papers
cs.CV2026
Multiple Domain Generalization Using Category Information Independent of Domain Differences
Reiji Saito, Kazuhiro Hotta
Domain generalization is a technique aimed at enabling models to maintain high accuracy when applied to new environments or datasets (unseen domains) that differ from the datasets…
cs.CV2026
Novel Anomaly Detection Scenarios and Evaluation Metrics to Address the Ambiguity in the Definition of Normal Samples
Reiji Saito, Satoshi Kamiya, Kazuhiro Hotta
In conventional anomaly detection, training data consist of only normal samples. However, in real-world scenarios, the definition of a normal sample is often ambiguous. For example…
cs.CV2024
Reducing Catastrophic Forgetting in Online Class Incremental Learning Using Self-Distillation
Kotaro Nagata, Hiromu Ono, Kazuhiro Hotta
In continual learning, there is a serious problem of catastrophic forgetting, in which previous knowledge is forgotten when a model learns new tasks. Various methods have been prop…