Events
PhD DefenseObject-Centric Representation Learning: Methods and Applications |
|
||
Monday, March 31, 2025, 08:30am - 10:00pm |
|||
Speaker: Jindong Jiang
Bio
Location : CBIM 22
Committee:
Professor Sungjin Ahn (advisor/chair)
Professor Hao Wang
Professor Ruixiang Tang
Event Type: PhD Defense
Abstract: Deep learning has revolutionized machine learning and computer vision. However, conventional approaches often overlook the inherent compositional and modular nature of the physical world, making it difficult to express modularity, compositionality, and interpretability in the representations. This dissertation addresses this challenge by developing object-centric learning methods that decompose raw visual inputs into individual entities and represent them as modular components. We further demonstrate the effectiveness of these learned representations in applications such as image generation, editing, and visual reasoning. The core contributions of this dissertation include four novel architectures: (1) SCALOR, which employs parallelizable spatial attention to significantly improve scalability in object-centric video understanding; (2) GNM, which integrates distributed and object-centric representations to enable both interpretable representations and density-based generation; (3) LSD, which integrates diffusion models with object-centric learning to handle complex naturalistic scenes and enable real-world image generation and editing applications; and (4) SlotSSMs, which incorporates object-centric principles into state-space models for improved temporal reasoning and long-context video understanding. Together, these contributions advance the field of object-centric learning, addressing critical limitations in existing methods and expanding the applicability of object-centric representations to real-world tasks.
Organization:
Contact Professor Sungjin Ahn
https://rutgers.zoom.us/j/98921331802?pwd=D6vEPc3sE0mXnlHa5JHzYWV4iR0dQp.1