5 papers · 1 filter
LCM: Log Conformal Maps for Robust Representation Learning to Mitigate Perspective Distortion
Meenakshi Subhash Chippa, Prakash Chandra Chhipa, Kanjar De +2
Perspective distortion (PD) leads to substantial alterations in the shape, size, orientation, angles, and spatial relationships of visual elements in images. Accurately determining…
Open-Vocabulary Object Detectors: Robustness Challenges under Distribution Shifts
Prakash Chandra Chhipa, Kanjar De, Meenakshi Subhash Chippa +2
The challenge of Out-Of-Distribution (OOD) robustness remains a critical hurdle towards deploying deep vision models. Vision-Language Models (VLMs) have recently achieved groundbre…
Giving each task what it needs -- leveraging structured sparsity for tailored multi-task learning
Richa Upadhyay, Ronald Phlypo, Rajkumar Saini +1
In the Multi-task Learning (MTL) framework, every task demands distinct feature representations, ranging from low-level to high-level attributes. It is vital to address the specifi…
Möbius Transform for Mitigating Perspective Distortions in Representation Learning
Prakash Chandra Chhipa, Meenakshi Subhash Chippa, Kanjar De +3
Perspective distortion (PD) causes unprecedented changes in shape, size, orientation, angles, and other spatial relationships of visual concepts in images. Precisely estimating cam…
A Systematic Performance Analysis of Deep Perceptual Loss Networks: Breaking Transfer Learning Conventions
Gustav Grund Pihlgren, Konstantina Nikolaidou, Prakash Chandra Chhipa +4
In recent years, deep perceptual loss has been widely and successfully used to train machine learning models for many computer vision tasks, including image synthesis, segmentation…