Feature Isolation and Noise Robustness in Human and Computer Vision
This project is funded through multiple sources, including an NSF-funded REU site with the HMC Computer Science Department. You can read more about the mentors and projects taking part at this link.
If you would like to be considered for a position funded through the REU (US citizens and permanent residents only), you must apply through the ETAP website.
If you would like to be considered for a position funded via other sources, please apply here.
If you would like to be considered for either, you may submit an application both here and to the ETAP website, but you must indicate at the top of your application through the URO website that you also applied to the REU program.
Project Description:
Over the past decade, deep learning has become the predominant approach to computer vision problems. While deep neural networks have demonstrated highly impressive results in many areas, they still sometimes exhibit surprising brittleness and vulnerability to noise and data variation. There have been numerous studies comparing human visual robustness to noise and other manipulations of input images with the robustness of deep learning models, but the vast majority of these studies have focused on object recognition or detection. However, there are many other visual tasks of great importance, such as depth perception and action recognition in video. It is unclear if the findings of this prior literature extend to these other visual tasks. This project will investigate both human and computer model robustness in tasks beyond object detection, with the aim of improving not only our understanding of human vision, but also establishing whether techniques aimed at improving vision model robustness extend across problem domains, or if they will need to be developed in a more domain-specific manner.
Applying to Work in the Lab for CATS:
If you are applying through the URO portal, please be sure that your application addresses the following questions:
- Write several (e.g. 3-5) sentences on why you are interested in this specific project. What do you hope to learn by participating?
- Please also provide a few sentences describing any relevant experience you have had that will assist with getting started on that project (this can be relevant course work, past research or professional experience, or other things you think are relevant).
The Lab for CATS seeks to understand visual cognition, and help build more robust and unbiased artificial visual agents. There is a lot of hype in the world of computer vision and machine learning, and we seek to keep a grounded focus on fair and realistic evaluations of model behaviour with the goal of identifying when common benchmarking and evaluation practices might result in unanticipated deficits in novel or unconstrained environments.
If you want to get a better sense of the lab culture and what working in the Lab for CATS might be like, I encourage you to speak to my current and former students! I'd be happy to facilitate contact.