3 papers
cs.LG2026
Unsupervised Learning of Inter-Object Relationships via Group Homomorphism
Kyotaro Ushida, Takayuki Komatsu, Yoshiyuki Ohmura +1
While current deep learning models achieve high performance by learning statistical correlations from vast datasets,which stands in stark contrast to human learning. They lack the…
cs.CV2025
Feature-Based Lie Group Transformer for Real-World Applications
Takayuki Komatsu, Yoshiyuki Ohmura, Kayato Nishitsunoi +1
The main goal of representation learning is to acquire meaningful representations from real-world sensory inputs without supervision. Representation learning explains some aspects…
cs.CV2025
Learning Conditionally Independent Transformations using Normal Subgroups in Group Theory
Kayato Nishitsunoi, Yoshiyuki Ohmura, Takayuki Komatsu +1
Humans develop certain cognitive abilities to recognize objects and their transformations without explicit supervision, highlighting the importance of unsupervised representation l…