3 papers
cs.CV2022
Reducing Annotation Effort by Identifying and Labeling Contextually Diverse Classes for Semantic Segmentation Under Domain Shift
Sharat Agarwal, Saket Anand, Chetan Arora
In Active Domain Adaptation (ADA), one uses Active Learning (AL) to select a subset of images from the target domain, which are then annotated and used for supervised domain adapta…
cs.CV2021
Does Data Repair Lead to Fair Models? Curating Contextually Fair Data To Reduce Model Bias
Sharat Agarwal, Sumanyu Muku, Saket Anand +1
Contextual information is a valuable cue for Deep Neural Networks (DNNs) to learn better representations and improve accuracy. However, co-occurrence bias in the training dataset m…
cs.CV2020
Contextual Diversity for Active Learning
Sharat Agarwal, Himanshu Arora, Saket Anand +1
Requirement of large annotated datasets restrict the use of deep convolutional neural networks (CNNs) for many practical applications. The problem can be mitigated by using active…