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  /  Google Scholar  /  LinkedIn  /  Twitter

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.

We present a simple, self-supervised method to boost the density of pretrained ViT features, which enhances their performance in a range of spatially dense downstream tasks. LiFT is trained quickly with a multi-scale feature reconstruction objective and can be applied iteratively to make pixel-dense features.

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.

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.

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.

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.

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.

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)