LinSlot: Exploiting Linear Representation hypothesis for unsupervised attribute discovery from slot based object representation
arXiv:2610.10722v1 Announce Type: new Abstract: This paper studies the problem of learning disentangled representations of objects and their attributes from raw, unstructured image data. Slot-based methods have shown considerable success in unsupervised learning of object representations from image…
Read the full story at arXiv cs.CV ↗