3 citations · 7 across the 4 of their papers we have counts for
4 papers
Learning to Retain while Acquiring: Combating Distribution-Shift in Adversarial Data-Free Knowledge Distillation
Gaurav Patel, Konda Reddy Mopuri, Qiang Qiu
Data-free Knowledge Distillation (DFKD) has gained popularity recently, with the fundamental idea of carrying out knowledge transfer from a Teacher neural network to a Student neur…
Seq-UPS: Sequential Uncertainty-aware Pseudo-label Selection for Semi-Supervised Text Recognition
Gaurav Patel, Jan Allebach, Qiang Qiu
This paper looks at semi-supervised learning (SSL) for image-based text recognition. One of the most popular SSL approaches is pseudo-labeling (PL). PL approaches assign labels to…
Weakly supervised segmentation with cross-modality equivariant constraints
Gaurav Patel, Jose Dolz
Weakly supervised learning has emerged as an appealing alternative to alleviate the need for large labeled datasets in semantic segmentation. Most current approaches exploit class…
Switching Loss for Generalized Nucleus Detection in Histopathology
Deepak Anand, Gaurav Patel, Yaman Dang +1
The accuracy of deep learning methods for two foundational tasks in medical image analysis -- detection and segmentation -- can suffer from class imbalance. We propose a `switching…