Abhimanyu Dubey

I am a second-year graduate student in the Human Dynamics group at MIT, supervised by Alex Pentland. My research interests are in artificial intelligence, deep learning and computational social science. I am supported by an Emerging Worlds Fellowship. Prior to this, I received a master's degree in Computer Science and bachelor's degree in Electrical Engineering at IIT Delhi, where I was supervised by Sumeet Agarwal.

dubeya[at]mit.edu | github | quora | scholar | linkedin


Updates

Sept 2018          1 paper accepted to NIPS 2018!
July 2018          2 papers accepted to ECCV 2018!
May 2018          TuringBox has been accepted to FAT/ML 2018 as a full talk!
April 2018          TuringBox has been accepted to IJCAI 2018 as a demo!

Experience

Summer 2018 2017 - present 2016 - 2017 Summer 2016 2011 - 2016

Research

Maximum-Entropy Fine-Grained Classification

Abhimanyu Dubey, Otkrist Gupta, Ramesh Raskar and Nikhil Naik
We explore maximum-entropy discriminative training to reduce overfitting in fine-grained visual classification, where samples from different classes tend to be very similar.
Neural Information Processing Systems (NIPS), 2018
[arxiv]
 

Sparsely-Networked Evolution Strategies

Dhaval Adjodah, Dan Calacci, Abhimanyu Dubey, Peter Krafft, Esteban Moro and Alex Pentland
We modify the popular evolution strategies algorithm for deep reinforcement learning to introduce sparse network topologies of communication and demonstrate that sparse networks produce significantly higher average rewards as well as reduced communication costs.
International Conference on Computational Social Science (IC2S2), 2018 (abstract)
International Conference on Network Science (NetSci), 2018 (lightning talk)
PDF and code coming soon!
 

Coreset-Based Neural Network Compression

Abhimanyu Dubey*, Moitreya Chatterjee* and Narendra Ahuja
We propose a method to compress neural network filters by recovering a sparse linear decomposition at the filter-level in CNNs, along with a data-dependent filter pruning algorithm to reduce memory usage and prediction run-time.
European Conference on Computer Vision (ECCV), 2018
[proceedings] [arxiv] [code]
 

Pairwise Confusion for Fine-Grained Visual Classification

Abhimanyu Dubey, Otkrist Gupta, Pei Guo, Ramesh Raskar, Ryan Farrell and Nikhil Naik
To reduce overfitting to sample-specific local artefacts in fine-grained visual classification, we propose a siamese-like architecture that attempts to bring inter-class logits closer to each other.
European Conference on Computer Vision (ECCV), 2018
[proceedings] [arxiv] [code]
 

Prediction Propagation for Domain Adaptation

Bjarke Felbo, Michiel Bakker, Abhimanyu Dubey, Sadhika Malladi, Alex Pentland and Iyad Rahwan
We tackle the problem of domain adaptation in natural language processing with imbalanced training data, using a label-based bootstrapping technique that attempts to learn large-scale domain differences by improving the correlation between predicted labels and domains.
Workshop on Towards learning with limited labels: Equivariance, Invariance, and Beyond
International Conference on Machine Learning (ICML), 2018
 

TuringBox: An Experimental Platform for the Evaluation of AI Systems

Ziv Epstein, Blakeley Hoffman Payne, Judy Hanwen Shen, Casey Jisoo Hong, Bjarke Felbo, Abhimanyu Dubey, Matthew Groh, Nick Obradovich, Manuel Cebrian and Iyad Rahwan
We introduce a platform to democratize the study of artificial intelligence. On one side of the platform, contributors upload existing and novel algorithms to be studied scientifically by others. On the other side, examiners develop tasks to evaluate and characterize the outputs of algorithms.
International Joint Conference on Artifical Intelligence (IJCAI), 2018 (Demo)
Fairness, Accountability, and Transparency in Machine Learning (FAT/ML), 2018 (Full Paper)
[proceedings] [website]
 

Sparse Matching for Embedding Image Macros

Abhimanyu Dubey, Esteban Moro, Manuel Cebrian and Iyad Rahwan
We create an algorithm to generate embeddings to capture the propagation and mutation of images on the internet, by decoupling underlying macros from overlaid adjustments and then combining decouple deep features. Our method opens up the possibility of obtaining the first large-scale understanding of the evolution and propagation of memetic imagery.
International World Wide Web Conference (WWW), 2018
[proceedings] [arxiv]
 

Modeling Image Virality with Pairwise Spatial Transformer Networks

Abhimanyu Dubey and Sumeet Agarwal
To understand the regions of images that are responsible for promoting virality in images, we utilize pairwise spatial transformer networks that operate on a pyramid of multi-resolution images, and are hence able to capture image cues at different scales.
ACM on Multimedia Conference (MM), 2017
[proceedings] [arxiv]
 

Deep Learning the City: Quantifying Global Urban Perception

Abhimanyu Dubey, Nikhil Naik, Devi Parikh, Ramesh Raskar and Cesar Hidalgo
We model urban perception of city scenes using a dataset of 1.3M pairwise comparisons over 6 perceptual attributes. We formulate the problem as a pairwise learning problem and use a siamese-like CNN architecture that learns to ''vote'' for images containing stronger attributes.
European Conference on Computer Vision (ECCV), 2016
[proceedings] [arxiv] [website] [code]
 

Examining Representational Similarity in ConvNets and the Primate Visual Cortex

Abhimanyu Dubey, Jayadeva and Sumeet Agarwal
We compare neural network representations with representations from the mammalian IT cortex and observe that improved performance on tasks like ImageNet corresponds to higher representational similarity to IT cortex.
Workshop on Biological and Artificial Vision (spotlight)
European Conference on Computer Vision (ECCV), 2016
[arxiv]
 

Deep Convolutional Networks for Modeling Image Virality

Abhimanyu Dubey and Sumeet Agarwal
We design a convolutional neural network architecture to model image virality on the internet.
Workshop on Web-scale Vision and Social Media
European Conference on Computer Vision (ECCV), 2016
[proceedings]
 

Coreset-Based Adaptive Tracking

Abhimanyu Dubey, Nikhil Naik, Dan Raviv, Rahul Sukthankar and Ramesh Raskar
We propose a constant-time method for real-time object tracking using coreset-tree representations of frames.
Preprint, 2015
[arxiv] [code]


(c) 2018 Abhimanyu Dubey , last updated November 8, 2018. Hits:web counter