11 citations · 18 across the 9 of their papers we have counts for
11 papers
Which Tasks Survive Self-Supervised Learning?
Achleshwar Luthra, Lucas Bryant, Tracy Zhu +1
Same-instance self-supervised learning (SSL) learns representations by enforcing consistency across two views of the same underlying instance. This principle alone, however, does n…
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…
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…
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…
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…
LVRNet: Lightweight Image Restoration for Aerial Images under Low Visibility
Esha Pahwa, Achleshwar Luthra, Pratik Narang
Learning to recover clear images from images having a combination of degrading factors is a challenging task. That being said, autonomous surveillance in low visibility conditions…
DroneAttention: Sparse Weighted Temporal Attention for Drone-Camera Based Activity Recognition
Santosh Kumar Yadav, Achleshwar Luthra, Esha Pahwa +4
Human activity recognition (HAR) using drone-mounted cameras has attracted considerable interest from the computer vision research community in recent years. A robust and efficient…
SWTF: Sparse Weighted Temporal Fusion for Drone-Based Activity Recognition
Santosh Kumar Yadav, Esha Pahwa, Achleshwar Luthra +3
Drone-camera based human activity recognition (HAR) has received significant attention from the computer vision research community in the past few years. A robust and efficient HAR…
Tracking Grow-Finish Pigs Across Large Pens Using Multiple Cameras
Aniket Shirke, Aziz Saifuddin, Achleshwar Luthra +10
Increasing demand for meat products combined with farm labor shortages has resulted in a need to develop new real-time solutions to monitor animals effectively. Significant progres…
ABO: Dataset and Benchmarks for Real-World 3D Object Understanding
Jasmine Collins, Shubham Goel, Kenan Deng +9
We introduce Amazon Berkeley Objects (ABO), a new large-scale dataset designed to help bridge the gap between real and virtual 3D worlds. ABO contains product catalog images, metad…
Eformer: Edge Enhancement based Transformer for Medical Image Denoising
Achleshwar Luthra, Harsh Sulakhe, Tanish Mittal +2
In this work, we present Eformer - Edge enhancement based transformer, a novel architecture that builds an encoder-decoder network using transformer blocks for medical image denois…