Dhruv Mahajan

RESEARCH SCIENTIST | MENLO PARK, UNITED STATES

Dhruv Mahajan is a research scientist on the Computer Vision team, which is part of Applied Machine Learning. Dhruv joined Facebook Research in January 2017. Prior to joining Facebook, he worked at Microsoft, MSR India and Yahoo! Research. Dhruv's research interests lie in computer vision and large scale and distributed machine learning. In computer vision, he is interested in extreme classification and ranking problems with huge scale both in terms of number of data points and labels and video understanding. Dhruv is also interested in new and efficient distributed optimization algorithms respecting system constraints like communication and machine failures.

Dhruv's Publications

September 27, 2023

COMPUTER VISION

Emu: Enhancing Image Generation Models Using Photogenic Needles in a Haystack

Xiaoliang Dai, Ji Hou, Kevin Chih-Yao Ma, Sam Tsai, Jialiang Wang, Rui Wang, Peizhao Zhang, Simon Vandenhende, Xiaofang Wang, Abhimanyu Dubey, Matthew Yu, Abhishek Kadian, Filip Radenovic, Dhruv Mahajan, Kunpeng Li, Yue (R) Zhao, Vladan Petrovic, Mitesh Kumar Singh, Simran Motwani, Yiwen Song, Yi Wen, Roshan Sumbaly, Vignesh Ramanathan, Zijian He, Peter Vajda, Devi Parikh

September 27, 2023

November 10, 2022

HUMAN & MACHINE INTELLIGENCE

CORE MACHINE LEARNING

Scalable Interpretability via Polynomials

Abhimanyu Dubey, Dhruv Mahajan, Filip Radenovic

November 10, 2022

November 06, 2022

RESEARCH

COMPUTER VISION

Neural Basis Models for Interpretability

Filip Radenovic, Abhimanyu Dubey, Dhruv Mahajan

November 06, 2022

July 18, 2022

COMPUTER VISION

ML APPLICATIONS

Making Heads or Tails: Towards Semantically Consistent Visual Counterfactuals

Deepti Ghadiyaram, Dhruv Mahajan, Filip Radenovic, Simon Vandenhende

July 18, 2022

December 06, 2020

RESEARCH

COMPUTER VISION

Self-Supervised Learning by Cross-Modal Audio-Video Clustering

Du Tran, Bruno Korbar, Dhruv Mahajan, Lorenzo Torresani, Bernard Ghanem, Humam Alwassel

December 06, 2020

June 18, 2020

RESEARCH

COMPUTER VISION

DLWL: Improving Detection for Lowshot classes with Weakly Labelled data

Vignesh Ramanathan, Dhruv Mahajan, Rui Wang

June 18, 2020

May 18, 2020

RESEARCH

COMPUTER VISION

ClusterFit: Improving Generalization of Visual Representations

Dhruv Mahajan, Abhinav Gupta, Deepti Ghadiyaram, Ishan Misra, Xueting Yan

May 18, 2020

August 16, 2019

RESEARCH

COMPUTER VISION

Scaling and Benchmarking Self-Supervised Visual Representation Learning

Priya Goyal, Abhinav Gupta, Dhruv Mahajan, Ishan Misra

August 16, 2019