1 code implementation • 1 Feb 2024 • Simar Kareer, Vivek Vijaykumar, Harsh Maheshwari, Prithvijit Chattopadhyay, Judy Hoffman, Viraj Prabhu
While the vast majority of prior work has studied this as a frame-level Image-DAS problem, a few Video-DAS works have sought to additionally leverage the temporal signal present in adjacent frames.
no code implementations • 11 Dec 2023 • Prithvijit Chattopadhyay, Bharat Goyal, Boglarka Ecsedi, Viraj Prabhu, Judy Hoffman
Synthetic data (SIM) drawn from simulators have emerged as a popular alternative for training models where acquiring annotated real-world images is difficult.
2 code implementations • NeurIPS 2023 • Micah Goldblum, Hossein Souri, Renkun Ni, Manli Shu, Viraj Prabhu, Gowthami Somepalli, Prithvijit Chattopadhyay, Mark Ibrahim, Adrien Bardes, Judy Hoffman, Rama Chellappa, Andrew Gordon Wilson, Tom Goldstein
Battle of the Backbones (BoB) makes this choice easier by benchmarking a diverse suite of pretrained models, including vision-language models, those trained via self-supervised learning, and the Stable Diffusion backbone, across a diverse set of computer vision tasks ranging from classification to object detection to OOD generalization and more.
1 code implementation • ICCV 2023 • Sriram Yenamandra, Pratik Ramesh, Viraj Prabhu, Judy Hoffman
Computer vision datasets frequently contain spurious correlations between task-relevant labels and (easy to learn) latent task-irrelevant attributes (e. g. context).
no code implementations • 7 Jun 2023 • Sruthi Sudhakar, Viraj Prabhu, Olga Russakovsky, Judy Hoffman
As computer vision systems are being increasingly deployed at scale in high-stakes applications like autonomous driving, concerns about social bias in these systems are rising.
2 code implementations • NeurIPS 2023 • Viraj Prabhu, Sriram Yenamandra, Prithvijit Chattopadhyay, Judy Hoffman
We propose an automated algorithm to stress-test a trained visual model by generating language-guided counterfactual test images (LANCE).
no code implementations • 9 Feb 2023 • Viraj Prabhu, David Acuna, Andrew Liao, Rafid Mahmood, Marc T. Law, Judy Hoffman, Sanja Fidler, James Lucas
Sim2Real domain adaptation (DA) research focuses on the constrained setting of adapting from a labeled synthetic source domain to an unlabeled or sparsely labeled real target domain.
no code implementations • 8 Feb 2023 • Sruthi Sudhakar, Viraj Prabhu, Arvindkumar Krishnakumar, Judy Hoffman
We visualize the feature space of the transformer self-attention modules and discover that a significant portion of the bias is encoded in the query matrix.
1 code implementation • 16 Jun 2022 • Viraj Prabhu, Sriram Yenamandra, Aaditya Singh, Judy Hoffman
Inspired by the design of recent SSL approaches based on learning from partial image inputs generated via masking or cropping -- either by learning to predict the missing pixels, or learning representational invariances to such augmentations -- we propose PACMAC, a simple two-stage adaptation algorithm for self-supervised ViTs.
no code implementations • 23 Apr 2022 • Viraj Prabhu, Ramprasaath R. Selvaraju, Judy Hoffman, Nikhil Naik
Despite the rapid progress in deep visual recognition, modern computer vision datasets significantly overrepresent the developed world and models trained on such datasets underperform on images from unseen geographies.
1 code implementation • 29 Oct 2021 • Arvindkumar Krishnakumar, Viraj Prabhu, Sruthi Sudhakar, Judy Hoffman
Deep learning models have been shown to learn spurious correlations from data that sometimes lead to systematic failures for certain subpopulations.
no code implementations • 21 Jul 2021 • Viraj Prabhu, Shivam Khare, Deeksha Kartik, Judy Hoffman
Most modern approaches for domain adaptive semantic segmentation rely on continued access to source data during adaptation, which may be infeasible due to computational or privacy constraints.
2 code implementations • ICCV 2021 • Viraj Prabhu, Shivam Khare, Deeksha Kartik, Judy Hoffman
Many existing approaches for unsupervised domain adaptation (UDA) focus on adapting under only data distribution shift and offer limited success under additional cross-domain label distribution shift.
Ranked #14 on Domain Adaptation on Office-Home
1 code implementation • ICCV 2021 • Viraj Prabhu, Arjun Chandrasekaran, Kate Saenko, Judy Hoffman
Generalizing deep neural networks to new target domains is critical to their real-world utility.
no code implementations • 7 Oct 2019 • Viraj Prabhu, Anitha Kannan, Geoffrey J. Tso, Namit Katariya, Manish Chablani, David Sontag, Xavier Amatriain
Machine-learned diagnosis models have shown promise as medical aides but are trained under a closed-set assumption, i. e. that models will only encounter conditions on which they have been trained.
no code implementations • 7 Nov 2018 • Viraj Prabhu, Anitha Kannan, Murali Ravuri, Manish Chablani, David Sontag, Xavier Amatriain
We consider the problem of image classification for the purpose of aiding doctors in dermatological diagnosis.
no code implementations • EMNLP 2018 • Arjun Chandrasekaran, Viraj Prabhu, Deshraj Yadav, Prithvijit Chattopadhyay, Devi Parikh
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).
no code implementations • 27 Oct 2018 • Utsav Garg, Viraj Prabhu, Deshraj Yadav, Ram Ramrakhya, Harsh Agrawal, Dhruv Batra
We present Fabrik, an online neural network editor that provides tools to visualize, edit, and share neural networks from within a browser.
no code implementations • 17 Aug 2017 • Prithvijit Chattopadhyay, Deshraj Yadav, Viraj Prabhu, Arjun Chandrasekaran, Abhishek Das, Stefan Lee, Dhruv Batra, Devi Parikh
This suggests a mismatch between benchmarking of AI in isolation and in the context of human-AI teams.
1 code implementation • EMNLP 2017 • Aroma Mahendru, Viraj Prabhu, Akrit Mohapatra, Dhruv Batra, Stefan Lee
In this paper, we make a simple observation that questions about images often contain premises - objects and relationships implied by the question - and that reasoning about premises can help Visual Question Answering (VQA) models respond more intelligently to irrelevant or previously unseen questions.
no code implementations • 3 Apr 2017 • Arjun Chandrasekaran, Deshraj Yadav, Prithvijit Chattopadhyay, Viraj Prabhu, Devi Parikh
Surprisingly, we find that having access to the model's internal states - its confidence in its top-k predictions, explicit or implicit attention maps which highlight regions in the image (and words in the question) the model is looking at (and listening to) while answering a question about an image - do not help people better predict its behavior.