Matthew Walmer

I am a Computer Science PhD student at the University of Maryland, College Park, working with Professor Abhinav Shrivastava on research in Computer Vision and Machine Learning.

I previously completed a Bachelor’s and Master’s degree in Biomedical Engineering at Johns Hopkins University with a focus on computational biology. My previous studies in neuroscience and human learning led me to take a deep interest in Machine Learning and the amazing advances the field has seen in the past decade. My current research focuses on investigating how and what neural networks learn as well as their failure cases.

Email  /  Resume  /  Google Scholar  /  LinkedIn  /  Twitter

profile photo

My research focuses on understanding how Deep Neural Networks learn (or fail to learn). This includes research in Adversarial Attacks and Backdoored networks, and more recently has explored what and how Vision Transformers (ViTs) learn under different conditions.

mvformer Multi-entity Video Transformers for Fine-Grained Video Representation Learning
Matthew Walmer, Rose Kanjirathinkal, Kai Sheng Tai, Keyur Muzumdar, Taipeng Tian, Abhinav Shrivastava
Paper | Code

We revisit the design of transformer-based architectures for fine-grained video representation, and we present MV-Former, a Multi-entity Video Transformer that learns to parse video scenes as collections of salient entities.

vit_analysis Teaching Matters: Investigating the Role of Supervision in Vision Transformers
Matthew Walmer*, Saksham Suri*, Kamal Gupta, Abhinav Shrivastava
CVPR, 2023
Project Page | Paper | Code

A comparative study of Vision Transformers (ViTs) trained through different methods of supervision, including fully supervised and self-supervised methods. This analysis focuses on the networks’ attention, features, and downstream task performance.

dual_key_backdoor Dual-Key Multimodal Backdoors for Visual Question Answering
Matthew Walmer, Karan Sikka, Indranil Sur, Abhinav Shrivastava, Susmit Jha
CVPR, 2022
Paper | Code

Investigating ways to extend backdoor/trojan attacks into the multimodal domain, specifically Visual Question Answering (VQA). The proposed Dual-Key Backdoor Attack utilized multiple triggers in different modalities.

mvformer TIJO: Trigger Inversion with Joint Optimization for Defending Multimodal Backdoored Models
Indranil Sur, Karan Sikka, Matthew Walmer, Kaushik Koneripalli, Anirban Roy, Xiao Lin, Ajay Divakaran, Susmit Jha
ICCV, 2023

A defense strategy for Dual-Key Backdoor Attacks through Trigger Inversion using Joint Optimization (TIJO). We show that joint optimization of both triggers in both domains is essential to overcome multimodal backdoor attacks.

apricot_sample APRICOT: A Dataset of Physical Adversarial Attacks on Object Detection
Anneliese Braunegg, Amartya Chakraborty, Michael Krumdick, Nicole Lape, Sara Leary, Keith Manville, Elizabeth Merkhofer, Laura Strickhart, Matthew Walmer
ECCV, 2020
Project Page | Paper

An investigation of the “in-the-wild” effectiveness of Adversarial Patch Attacks on Object Detection models. This includes the creation of the APRICOT dataset, as well as a study of patch effectiveness and defenses.

neuronal_activity Neuronal Activity in Human Anterior Cingulate Cortex Modulates with Internal Cognitive State During Multi-Source Interference Task
Samuel Sklar*, Matthew Walmer*, Pierre Sacre, Catherine A Schevon, Shraddha Srinivasan, Garrett P Banks, Mark J Yates, Guy M McKhann, Sameer A Sheth, Sridevi V Sarma, Elliot H Smith
EMBC, 2017

We model the activity of single neurons recorded in human subjects participating in a multi-source interference task. We show that neural activation correlates with an estimated latent cognitive state variable for focus.

Website template by Jon Barron (Source Code)