4 papers · 1 filter
A Survey on Data Curation for Visual Contrastive Learning: Why Crafting Effective Positive and Negative Pairs Matters
Shasvat Desai, Debasmita Ghose, Deep Chakraborty
Visual contrastive learning aims to learn representations by contrasting similar (positive) and dissimilar (negative) pairs of data samples. The design of these pairs significantly…
Self-Supervised Learning to Guide Scientifically Relevant Categorization of Martian Terrain Images
Tejas Panambur, Deep Chakraborty, Melissa Meyer +3
Automatic terrain recognition in Mars rover images is an important problem not just for navigation, but for scientists interested in studying rock types, and by extension, conditio…
Pedestrian Detection in Thermal Images using Saliency Maps
Debasmita Ghose, Shasvat Mukeshkumar Desai, Sneha Bhattacharya +3
Thermal images are mainly used to detect the presence of people at night or in bad lighting conditions, but perform poorly at daytime. To solve this problem, most state-of-the-art…
Unsupervised Hard Example Mining from Videos for Improved Object Detection
SouYoung Jin, Aruni RoyChowdhury, Huaizu Jiang +4
Important gains have recently been obtained in object detection by using training objectives that focus on {\em hard negative} examples, i.e., negative examples that are currently…