1 code implementation • CVPR 2023 • Corentin Dancette, Spencer Whitehead, Rishabh Maheshwary, Ramakrishna Vedantam, Stefan Scherer, Xinlei Chen, Matthieu Cord, Marcus Rohrbach
In this work, we explore Selective VQA in both in-distribution (ID) and OOD scenarios, where models are presented with mixtures of ID and OOD data.
1 code implementation • 18 Apr 2023 • Karan Desai, Maximilian Nickel, Tanmay Rajpurohit, Justin Johnson, Ramakrishna Vedantam
Visual and linguistic concepts naturally organize themselves in a hierarchy, where a textual concept "dog" entails all images that contain dogs.
no code implementations • NeurIPS 2021 • Ramakrishna Vedantam, David Lopez-Paz, David J. Schwab
Recent work demonstrates that deep neural networks trained using Empirical Risk Minimization (ERM) can generalize under distribution shift, outperforming specialized training algorithms for domain generalization.
1 code implementation • 6 Oct 2020 • Ramakrishna Vedantam, Arthur Szlam, Maximilian Nickel, Ari Morcos, Brenden Lake
Humans can learn and reason under substantial uncertainty in a space of infinitely many concepts, including structured relational concepts ("a scene with objects that have the same color") and ad-hoc categories defined through goals ("objects that could fall on one's head").
1 code implementation • NeurIPS 2020 • Yann Dubois, Douwe Kiela, David J. Schwab, Ramakrishna Vedantam
We address the question of characterizing and finding optimal representations for supervised learning.
no code implementations • 25 Sep 2019 • Nirbhay Modhe, Prithvijit Chattopadhyay, Mohit Sharma, Abhishek Das, Devi Parikh, Dhruv Batra, Ramakrishna Vedantam
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.
no code implementations • 24 Jul 2019 • Nirbhay Modhe, Prithvijit Chattopadhyay, Mohit Sharma, Abhishek Das, Devi Parikh, Dhruv Batra, Ramakrishna Vedantam
We propose a novel framework to identify sub-goals useful for exploration in sequential decision making tasks under partial observability.
no code implementations • ICLR 2019 • Ramakrishna Vedantam, Karan Desai, Stefan Lee, Marcus Rohrbach, Dhruv Batra, Devi Parikh
We propose a new class of probabilistic neural-symbolic models, that have symbolic functional programs as a latent, stochastic variable.
no code implementations • ICLR 2018 • Ramakrishna Vedantam, Ian Fischer, Jonathan Huang, Kevin Murphy
It is easy for people to imagine what a man with pink hair looks like, even if they have never seen such a person before.
no code implementations • EMNLP 2017 • Ashwin K. Vijayakumar, Ramakrishna Vedantam, Devi Parikh
In this work, we treat sound as a first-class citizen, studying downstream textual tasks which require aural grounding.
1 code implementation • CVPR 2017 • Ramakrishna Vedantam, Samy Bengio, Kevin Murphy, Devi Parikh, Gal Chechik
We introduce an inference technique to produce discriminative context-aware image captions (captions that describe differences between images or visual concepts) using only generic context-agnostic training data (captions that describe a concept or an image in isolation).
2 code implementations • 22 Nov 2016 • Ramprasaath R. Selvaraju, Abhishek Das, Ramakrishna Vedantam, Michael Cogswell, Devi Parikh, Dhruv Batra
We propose a technique for making Convolutional Neural Network (CNN)-based models more transparent by visualizing input regions that are 'important' for predictions -- or visual explanations.
124 code implementations • ICCV 2017 • Ramprasaath R. Selvaraju, Michael Cogswell, Abhishek Das, Ramakrishna Vedantam, Devi Parikh, Dhruv Batra
For captioning and VQA, we show that even non-attention based models can localize inputs.
1 code implementation • CVPR 2017 • Prithvijit Chattopadhyay, Ramakrishna Vedantam, Ramprasaath R. Selvaraju, Dhruv Batra, Devi Parikh
In this work, we build dedicated models for counting designed to tackle the large variance in counts, appearances, and scales of objects found in natural scenes.
Ranked #1 on Object Counting on COCO count-test
no code implementations • ICCV 2015 • Ramakrishna Vedantam, Xiao Lin, Tanmay Batra, C. Lawrence Zitnick, Devi Parikh
We show that the commonsense knowledge we learn is complementary to what can be learnt from sources of text.
1 code implementation • CVPR 2016 • Satwik Kottur, Ramakrishna Vedantam, José M. F. Moura, Devi Parikh
While word embeddings trained using text have been extremely successful, they cannot uncover notions of semantic relatedness implicit in our visual world.
18 code implementations • 1 Apr 2015 • Xinlei Chen, Hao Fang, Tsung-Yi Lin, Ramakrishna Vedantam, Saurabh Gupta, Piotr Dollar, C. Lawrence Zitnick
In this paper we describe the Microsoft COCO Caption dataset and evaluation server.
24 code implementations • CVPR 2015 • Ramakrishna Vedantam, C. Lawrence Zitnick, Devi Parikh
We propose a novel paradigm for evaluating image descriptions that uses human consensus.
no code implementations • 12 Nov 2014 • Ramakrishna Vedantam, C. Lawrence Zitnick, Devi Parikh
We describe our two new datasets with images described by humans.