Ishan Misra

Ishan is a research scientist at Facebook. He is currently working on Computer Vision and Machine Learning. His research interest is in reducing the need for supervision in visual learning. He holds a PhD from the Robotics Institute at Carnegie Mellon University and graduated in 2018 when he joined FAIR.

Ishan's Publications

June 19, 2020

COMPUTER VISION

ML APPLICATIONS

Self-Supervised Learning of Pretext-Invariant Representations

The goal of self-supervised learning from images is to construct image representations that are semantically meaningful via pretext tasks that do not require semantic…

Ishan Misra, Laurens-van der Maaten

June 19, 2020

June 16, 2019

RESEARCH

COMPUTER VISION

Does Object Recognition Work for Everyone?

The paper analyzes the accuracy of publicly available object-recognition systems on a geographically diverse dataset. This dataset contains household items and was designed to have a more representative geographical coverage than commonly used…

Terrance DeVries, Ishan Misra, Changhan Wang, Laurens van der Maaten

June 16, 2019

June 18, 2018

RESEARCH

Learning by Asking Questions

We introduce an interactive learning framework for the development and testing of intelligent visual systems, called learning-by-asking (LBA). We explore LBA in context of the Visual Question Answering (VQA) task. LBA differs from standard VQA…

Ishan Misra, Ross Girshick, Rob Fergus, Martial Hebert, Abhinav Gupta, Laurens van der Maaten

June 18, 2018

June 14, 2020

RESEARCH

COMPUTER VISION

In Defense of Grid Features for Visual Question Answering

Popularized as ‘bottom-up’ attention, bounding box (or region) based visual features have recently surpassed vanilla grid-based convolutional features as the de facto standard for vision and language tasks like visual question answering (VQA).

Huaizu Jiang, Ishan Misra, Marcus Rohrbach, Erik Learned-Miller, Xinlei Chen

June 14, 2020

May 19, 2020

RESEARCH

COMPUTER VISION

ClusterFit: Improving Generalization of Visual Representations

Pre-training convolutional neural networks with weakly supervised and self-supervised strategies is becoming increasingly popular for several computer vision tasks.

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

May 19, 2020

October 27, 2019

RESEARCH

COMPUTER VISION

Scaling and Benchmarking Self-Supervised Visual Representation Learning

Priya Goyal, Dhruv Mahajan, Abhinav Gupta, Ishan Misra

October 27, 2019