5 papers
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…
Transformation Categorization Based on Group Decomposition Theory Using Parameter Division
Takayuki Komatsu, Yoshiyuki Ohmura, Yasuo Kuniyoshi
Representation learning seeks meaningful sensory representations without supervision and can model aspects of human development. Although many neural networks empirically learn use…
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…
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…
Ablation Study to Clarify the Mechanism of Object Segmentation in Multi-Object Representation Learning
Takayuki Komatsu, Yoshiyuki Ohmura, Yasuo Kuniyoshi
Multi-object representation learning aims to represent complex real-world visual input using the composition of multiple objects. Representation learning methods have often used un…