2 papers
cs.CV2026
LinSlot: Exploiting Linear Representation hypothesis for unsupervised attribute discovery from slot based object representation
Sanket Gandhi, Utkarsh Giri, Varun Subramanium +3
This paper studies the problem of learning disentangled representations of objects and their attributes from raw, unstructured image data. Slot-based methods have shown considerabl…
cs.CV2024
Learning Disentangled Representation in Object-Centric Models for Visual Dynamics Prediction via Transformers
Sanket Gandhi, Atul, Samanyu Mahajan +4
Recent work has shown that object-centric representations can greatly help improve the accuracy of learning dynamics while also bringing interpretability. In this work, we take thi…