no code implementations • 21 Mar 2024 • Saksham Suri, Matthew Walmer, Kamal Gupta, Abhinav Shrivastava
We present a simple self-supervised method to enhance the performance of ViT features for dense downstream tasks.
1 code implementation • 17 Nov 2023 • Matthew Walmer, Rose Kanjirathinkal, Kai Sheng Tai, Keyur Muzumdar, Taipeng Tian, Abhinav Shrivastava
In this work, we advance the state-of-the-art for this area by re-examining the design of transformer architectures for video representation learning.
no code implementations • ICCV 2023 • Indranil Sur, Karan Sikka, Matthew Walmer, Kaushik Koneripalli, Anirban Roy, Xiao Lin, Ajay Divakaran, Susmit Jha
We present a Multimodal Backdoor Defense technique TIJO (Trigger Inversion using Joint Optimization).
1 code implementation • CVPR 2023 • Matthew Walmer, Saksham Suri, Kamal Gupta, Abhinav Shrivastava
We compare ViTs trained through different methods of supervision, and show that they learn a diverse range of behaviors in terms of their attention, representations, and downstream performance.
1 code implementation • CVPR 2022 • Matthew Walmer, Karan Sikka, Indranil Sur, Abhinav Shrivastava, Susmit Jha
This is challenging for the attacker as the detector can distort or ignore the visual trigger entirely, which leads to models where backdoors are over-reliant on the language trigger.
1 code implementation • ECCV 2020 • A. Braunegg, Amartya Chakraborty, Michael Krumdick, Nicole Lape, Sara Leary, Keith Manville, Elizabeth Merkhofer, Laura Strickhart, Matthew Walmer
Physical adversarial attacks threaten to fool object detection systems, but reproducible research on the real-world effectiveness of physical patches and how to defend against them requires a publicly available benchmark dataset.