Prithvijit Chattopadhyay

I am a 2^nd year CS PhD student at Georgia Tech, advised by Prof. Judy Hoffman. I also collaborate with Prof. Devi Parikh and Prof. Dhruv Batra. I recently earned my Masters in Computer Science (focus on Machine Learning) from Georgia Tech, advised by Prof. Devi Parikh. Prior to joining Georgia Tech, I was working as a Research Assistant in the Computer Vision Machine Learning and Perception Lab (CVMLP) at Virginia Tech, advised by Prof. Devi Parikh and Prof. Dhruv Batra. I earned my Bachelors in Electrical Engineering in 2016 from Delhi Technological University, India.

In the past couple of years, I have had the fortune to intern / conduct research at Deep Learning Group, Microsoft Research Redmond (Summer 2018) mentored by Hamid Palangi; Robotics Research Lab, IIIT Hyderabad (Winter 2014) mentored by Dr. K. Madhava Krishna and Indian Association for the Cultivation of Science (IACS), Kolkata (Summer 2014) mentored by Dr. Soumitra Sengupta on a diverse set of topics - ranging from vision & language to robotics to theoretical physics.

I occasionally play the percussion instrument Tabla. I am very passionate about movies. I love to break them down shot-by-shot and analyze them. Every single frame is important.

Email  /  CV  /  Google Scholar  /  LinkedIn  /  Github  /  Twitter  /  Instagram

I am interested in developing reliable computer vision systems (including applications of Machine Learning and Reinforcement Learning) that

• can perceive and reason based on multimodal sensory information
• are interpretable so that predictions made by such systems can be explained
• are transferable so that they can be adapted across different domains with ease and limited supervision

Representative papers are listed under Papers.

• Recognized as an outstanding reviewer for CVPR 2021!
• Recognized to be among the top 33 percent reviewers for ICML 2020!
• Likelihood Landscapes received the NVIDIA Best Runner Up paper award at AROW, ECCV 2020!
• Awarded the College of Computing's CS7001 Research Award at Georgia Tech!
• Recognized as one of the highest-scoring reviewers for NeurIPS 2019!
• Recognized as an outstanding reviewer for ICLR 2019!
• Recognized to be among the top 30 percent highest scoring reviewers for NeurIPS 2018!
• Awarded the College of Computing's MS Research Award at Georgia Tech!
• Our team won VT Hacks 2017, a Major League Hacking Event, 2017!
• Our undergraduate team, DTU-AUV, qualified for the semi-finals at AUVSI Robosub 2014!
• Awarded Merit Scholarships from 2012-2014 for undergraduate academic performance!
• Selected for KVPY and INSPIRE Fellowships, 2012 for undergraduate studies in basic sciences!
• Placed among the top 1 percent students in the country in INPhO 2012!
• Selected for rigorous mathematical training camps conducted by mathematicians from Bhabha Atomic Research Center (BARC) and Indian Institute of Science (IISc) in 2012!
• Selected for CSIR Programme on Youth Leadership in Science, 2010!

• May 2020: I'll be interning in the PRIOR Team at Allen Institute of Artificial Intelligence.
• Serving as a reviewer for CVPR 2018, ECCV 2018, NeurIPS 2018-19-20, ICLR 2019-20, ICML 2019-20, ACL 2019.
• May 2019: Presented our work on Discovery of Decision States through Intrinsic Control at the Task-Agnostic Reinforcement Learning (TARL) Workshop at ICLR 2019.
• May 2019: Completed my Masters in Computer Science (focus on Machine Learning) with a thesis centered on Evaluating Visual Conversational Agents in the Context of Human-AI Cooperative Games!
• Feb 2019: Our technical report describing EvalAI - an open source platform to evaluate and compare AI algorithms at scale - is out on ArXiv!
• Dec 2018: Presented our work interpretable zero-shot learning at the Continual Learning and Visually Grounded Interaction and Language (ViGIL) workshops at NeurIPS 2018.
• Aug 2018: Our paper titled 'Do explanation modalities make VQA models more predictable to a human?' was accepted in EMNLP, 2018!
• Jul 2018: Our paper titled 'Choose Your Neuron: Incorporating Domain Knowledge through Neuron-Importance' was accepted in ECCV, 2018!
• Apr 2018: I was awarded the College of Computing's MS Research Award at Georgia Tech!
• Feb 2018: I'll intern in the Deep Learning Group at Microsoft Research, Redmond in summer 2018.
• Aug 2017: Our paper titled 'Evaluating Visual Conversational Agents via Cooperative Human-AI Games' was accepted in HCOMP 2017 as an oral!
• Jul 2017: I will be joining Georgia Tech as a Masters of Computer Science student in Fall 2017.
• May 2017: I will be presenting 'Counting Everyday Objects in Everyday Scenes' at the LDV Vision Summit, 2017.
• Mar 2017: Our paper titled 'It Takes Two to Tango: Towards Theory of AI's Mind' is out on ArXiv!
• Feb 2017: Our paper titled 'Counting Everyday Objects in Everyday Scenes' was accepted in CVPR 2017 as a spotlight!
• Feb 2017: Our team built FilterAI - an image retrival engine - and won VT Hacks 2017, a Major League Hacking Event!
• Dec 2016: 'Counting Everyday Objects in Everyday Scenes' received an Amazon Academic Research Award, 2016!

As an attempt towards assessing the robustness of embodied navigation agents, we propose RobustNav, a framework to quantify the performance of embodied navigation agents when exposed to a wide variety of visual – affecting RGB inputs – and dynamics – affecting transition dynamics – corruptions. Most recent efforts in visual navigation have typically focused on generalizing to novel target environments with similar appearance and dynamics characteristics. With RobustNav, we find that some standard embodied navigation agents significantly underperform (or fail) in the presence of visual or dynamics corruptions. We systematically analyze the kind of idiosyncrasies that emerge in the behavior of such agents when operating under corruptions. Finally, for visual corruptions in RobustNav, we show that while standard techniques to improve robustness such as data-augmentation and self-supervised adaptation offer some zero-shot resistance and improvements in navigation performance, there is still a long way to go in terms of recovering lost performance relative to clean “non-corrupt” settings, warranting more research in this direction.

Convolutional Neural Networks (CNNs) have been shown to be vulnerable to adversarial examples, which are known to locate in subspaces close to where normal data lies but are not naturally occurring and have low probability. In this work, we investigate the potential effect defense techniques have on the geometry of the likelihood landscape - likelihood of the input images under the trained model. We first propose a way to visualize the likelihood landscape by leveraging an energy-based model interpretation of discriminative classifiers. Then we introduce a measure to quantify the flatness of the likelihood landscape. We observe that a subset of adversarial defense techniques results in a similar effect of flattening the likelihood landscape. We further explore directly regularizing towards a flat landscape for adversarial robustness.

We introduce Domain-specific Masks for Generalization, a model for improving both in-domain and out-of-domain generalization performance. For domain generalization, the goal is to learn from a set of source domains to produce a single model that will best generalize to an unseen target domain. As such, many prior approaches focus on learning representations which persist across all source domains with the assumption that these domain agnostic representations will generalize well. However, often individual domains contain characteristics which are unique and when leveraged can significantly aid in-domain recognition performance. To produce a model which best generalizes to both seen and unseen domains, we propose learning domain specific masks. The masks are encouraged to learn a balance of domain-invariant and domain-specific features, thus enabling a model which can benefit from the predictive power of specialized features while retaining the universal applicability of domain-invariant features. We demonstrate competitive performance compared to naive baselines and state-of-the-art methods on both PACS and DomainNet.

While generative visual dialog models trained with self-talk based RL perform better at the associated downstream task, they suffer from repeated interactions -- resulting in saturation in improvements as the number of rounds increase. To counter this, we devise a simple auxiliary objective that incentivizes Q-Bot to ask diverse questions, thus reducing repetitions and in turn enabling A-Bot to explore a larger state space during RL i.e., be exposed to more visual concepts to talk about, and varied questions to answer.

We learn to identify decision states, namely the parsimonious set of states where decisions meaningfully affect the future states an agent can reach in an environment. We utilize the VIC framework, which maximizes an agent's 'empowerment', i.e. the ability to reliably reach a diverse set of states -- and formulate a sandwich bound on the empowerment objective that allows identification of decision states. Unlike previous work, our decision states are discovered without extrinsic rewards -- simply by interacting with the world. Our results show that our decision states are: (1) often interpretable, and (2) lead to better exploration on downstream goal-driven tasks in partially observable environments.

We introduce EvalAI, an open source platform for evaluating and comparing machine learning (ML) and artificial intelligence algorithms (AI) at scale. EvalAI is built to provide a scalable solution to the research community to fulfill the critical need of evaluating machine learning models and agents acting in an environment against annotations or with a human-in-the-loop. This will help researchers, students, and data scientists to create, collaborate, and participate in AI challenges organized around the globe.

We introduce a simple, efficient zero-shot learning approach -- NIWT -- based on the observation that individual neurons in CNNs have been shown to implicitly learn a dictionary of semantically meaningful concepts (simple textures and shapes to whole or partial objects). NIWT learns to map domain knowledge about "unseen" classes onto this dictionary of learned concepts and optimizes for network parameters that can effectively combine these concepts - essentially learning classifiers by discovering and composing learned semantic concepts in deep networks.

A rich line of research attempts to make deep neural networks more transparent by generating human-interpretable 'explanations' of their decision process, especially for interactive tasks like Visual Question Answering (VQA). In this work, we analyze if existing explanations indeed make a VQA model -- its responses as well as failures -- more predictable to a human.

We design a cooperative game - GuessWhich - to measure human-AI team performance in the specific context of the AI being a visual conversational agent. GuessWhich involves live interaction between the human and the AI and is designed to gauge the extent to which progress in isolated metrics for AI (& AI-AI teams) transfers to human-AI collaborative scenarios.

To effectively leverage the progress in Artificial Intelligence (AI) to make our lives more productive, it is important for humans and AI to work well together in a team. In this work, we argue that for human-AI teams to be effective, in addition to making AI more accurate and human-like, humans must also develop a theory of AI's mind (ToAIM) - get to know its strengths, weaknesses, beliefs, and quirks.

We study the numerosity of object classes in natural, everyday images and build dedicated models for counting designed to tackle the large variance in counts, appearances, and scales of objects found in natural scenes. We propose a contextual counting approach inspired by the phenomenon of subitizing - the ability of humans to make quick assessments of counts given a perceptual signal, for small count values.

(Design and CSS courtesy: Jon Barron and Amlaan Bhoi)