Vijay Veerabadran

Hello! I am a Research Scientist at Reality Labs Research @ Meta working on egocentric video language models for wearable devices. Previously, I was a Ph.D. student advised by Dr. Virginia de Sa at the UCSD Cognitive Science department where I worked on computer vision and human vision. My main contributions from my PhD research are (1) a bio-inspired adaptive RNN architecture that learned to dynamically scale its computation with input task-difficulty (see NeurIPS23), and (2) studying human vision’s sensitivity to adversarial image perturbations (see NatComm23).

During my PhD, I did internships at Google Brain, Facebook AI Research and Qualcomm AI Research working on adversarial images, human visual perception, self-supervised learning and unsupervised video representation learning.

news

09/23	Paper on “Adaptive recurrent vision performs zero-shot computation scaling to unseen difficulty levels” accepted at NeurIPS 2023!
08/23	Paper on “Subtle adversarial image manipulations influence both human and machine perception” accepted at Nature Communications!
06/23	Joined as a Research Scientist Intern at Meta Reality Labs advised by Michael L. Iuzzolino.
02/23	Poster on “Cortically motivated recurrence enables task extrapolation” accepted at the COSYNE 2023.
05/22	Poster on “Bio-inspired divisive normalization improves object recognition performance in ANNs” accepted at VSS 2022.
12/21	Poster on “Bio-inspired learnable divisive normalization for ANNs” accepted at the SVRHM workshop at NeurIPS 2021.
06/21	Joined as a Research Intern at Facebook AI advised by Yann Lecun, Yubei Chen and Stephane Deny.
02/21	Poster on “Human susceptibility to subtle adversarial image manipulations with unlimited exposure time” accepted at COSYNE 2021.
06/20	Joining as a Research Intern at Google Brain, Mountain View, USA working with Gamaleldin Elsayed.
06/20	Short paper on learned adversarial video compression accepted at the Learned Image Compression (CLIC) workshop at CVPR 2020.
12/19	Short paper introducing V1Net, a model of horizontal connections accepted at the SVRHM workshop @ NeurIPS 2019
10/19	Kavli Symposium Inspired Proposal award (2019) for my thesis project on research at the intersection of AI and Neuroscience.

selected publications

2023

NeurIPS 2023

Adaptive recurrent vision performs zero-shot computation scaling to unseen difficulty levels

Vijay Veerabadran, Srinivas Ravishankar, Yuan Tang, and 2 more authors

Proceedings of the 37th International Conference on Neural Information Processing Systems, 2023

Abs HTML PDF

Humans solving algorithmic (or) reasoning problems typically exhibit solution times that grow as a function of problem difficulty. Adaptive recurrent neural networks have been shown to exhibit this property for various language-processing tasks. However, little work has been performed to assess whether such adaptive computation can also enable vision models to extrapolate solutions beyond their training distribution’s difficulty level, with prior work focusing on very simple tasks. In this study, we investigate a critical functional role of such adaptive processing using recurrent neural networks: to dynamically scale computational resources conditional on input requirements that allow for zero-shot generalization to novel difficulty levels not seen during training using two challenging visual reasoning tasks: PathFinder and Mazes. We combine convolutional recurrent neural networks (ConvRNNs) with a learnable halting mechanism based on Graves (2016). We explore various implementations of such adaptive ConvRNNs (AdRNNs) ranging from tying weights across layers to more sophisticated biologically inspired recurrent networks that possess long/short-range lateral connections and gating. We show that 1) AdRNNs learn to dynamically halt processing early (or late) to solve easier (or harder) problems, 2) these RNNs zero-shot generalize to more difficult problem settings not shown during training by dynamically increasing the number of recurrent iterations at test time. Our study provides modeling evidence supporting the hypothesis that recurrent processing enables the functional advantage of adaptively allocating compute resources conditional on input requirements and hence allowing generalization to harder difficulty levels of a visual reasoning problem without training.
VSS 2023

Cortically motivated recurrence enables visual task extrapolation

Vijay Veerabadran, Yuan Tang, Ritik Raina, and 1 more author

J. Vis., Aug 2023

Abs HTML PDF

Feedforward deep neural networks have become the standard class of models in computer vision. Yet, they possess a striking difference relative to their biological counterparts which predominantly perform...
Nature 2023

Subtle adversarial image manipulations influence both human and machine perception

Vijay Veerabadran, Josh Goldman, Shreya Shankar, and 8 more authors

Nature Communications, Aug 2023

Abs HTML PDF

Although artificial neural networks (ANNs) were inspired by the brain, ANNs exhibit a brittleness not generally observed in human perception. One shortcoming of ANNs is their susceptibility to adversarial perturbations-subtle modulations of natural images that result in changes to classification decisions, such as confidently mislabelling an image of an elephant, initially classified correctly, as a clock. In contrast, a human observer might well dismiss the perturbations as an innocuous imaging artifact. This phenomenon may point to a fundamental difference between human and machine perception, but it drives one to ask whether human sensitivity to adversarial perturbations might be revealed with appropriate behavioral measures. Here, we find that adversarial perturbations that fool ANNs similarly bias human choice. We further show that the effect is more likely driven by higher-order statistics of natural images to which both humans and ANNs are sensitive, rather than by the detailed architecture of the ANN.

2021

NeurIPS 2021

Bio-inspired learnable divisive normalization for ANNs

Vijay Veerabadran, Ritik Raina, and Virginia R De Sa

3rd Workshop on Shared Visual Representations in Human and Machine Intelligence (SVRHM), NeurIPS, Aug 2021

Abs HTML PDF

In this work we introduce DivNormEI, a novel bio-inspired convolutional network that performs divisive normalization, a canonical cortical computation, along with lateral …

2020

CVPRW 2020

Adversarial distortion for learned video compression

Vijay Veerabadran, R Pourreza, and others

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, Aug 2020

Abs HTML PDF

In this paper, we present a novel adversarial lossy video compression model. At extremely low bit-rates, standard video coding schemes suffer from unpleasant reconstruction artifacts …

2018

NeurIPS 2018

Learning long-range spatial dependencies with horizontal gated recurrent units

D Linsley, J Kim, Vijay Veerabadran, and 1 more author

Proceedings of the 32nd International Conference on Neural Information Processing Systems, Aug 2018

Abs HTML PDF

Progress in deep learning has spawned great successes in many engineering applications. As a prime example, convolutional neural networks, a type of feedforward neural networks …