Making Heads or Tails: Towards Semantically Consistent Visual Counterfactuals
Simon Vandenhende, Dhruv Mahajan, Filip Radenovic, Deepti Ghadiyaram
People
Dhruv Mahajan
Research Scientist
I am a Research Scientist on the Computer Vision team, which is part of Applied Machine Learning. I joined Meta Research in January 2017. Prior to joining Meta, I worked at Microsoft, MSR India and Yahoo! Research. My research interests lie in computer vision and large scale and distributed machine learning. In computer vision, I am interested in extreme classification and ranking problems with huge scale both in terms of number of data points and labels and video understanding. I am also interested in new and efficient distributed optimization algorithms respecting system constraints like communication and machine failures.
Interests
Computer vision, large scale and distributed machine learning, and extreme classification (with large number of labels)
Latest Publications
ECCV - 2022
What leads to generalization of object proposals?
Rui Wang, Dhruv Mahajan, Vignesh Ramanathan
Cluster and Re-Learn: Improving Generalization of Visual Representations
Xueting Yan, Ishan Misra, Abhinav Gupta, Deepti Ghadiyaram, Dhruv Mahajan
Self-Supervised Learning by Cross-Modal Audio-Video Clustering
Humam Alwassel, Dhruv Mahajan, Bruno Korbar, Lorenzo Torresani, Bernard Ghanem, Du Tran
DLWL: Improving Detection for Lowshot classes with Weakly Labelled data
Vignesh Ramanathan, Rui Wang, Dhruv Mahajan
From Patches to Pictures (PaQ-2-PiQ): Mapping the Perceptual Space of Picture Quality
Zhenqiang Ying, Haoran Niu, Praful Gupta, Dhruv Mahajan, Deepti Ghadiyaram, Alan Bovik
