4 papers
Directional Neural Collapse Explains Few-Shot Transfer in Self-Supervised Learning
Achleshwar Luthra, Yash Salunkhe, Tomer Galanti
Frozen self-supervised representations often transfer well with only a few labels across many semantic tasks. We argue that a single geometric quantity, \emph{directional} CDNV (de…
Self-Supervised Contrastive Learning is Approximately Supervised Contrastive Learning
Achleshwar Luthra, Tianbao Yang, Tomer Galanti
Despite its empirical success, the theoretical foundations of self-supervised contrastive learning (CL) are not yet fully established. In this work, we address this gap by showing…
On the Alignment Between Supervised and Self-Supervised Contrastive Learning
Achleshwar Luthra, Priyadarsi Mishra, Tomer Galanti
Self-supervised contrastive learning (CL) has achieved remarkable empirical success, often producing representations that rival supervised pre-training on downstream tasks. Recent…
OccludeNeRF: Geometric-aware 3D Scene Inpainting with Collaborative Score Distillation in NeRF
Jingyu Shi, Achleshwar Luthra, Jiazhi Li +5
With Neural Radiance Fields (NeRFs) arising as a powerful 3D representation, research has investigated its various downstream tasks, including inpainting NeRFs with 2D images. Desp…