Imaging Science Ph.D. Defense: Robik Shrestha
Ph.D. Dissertation Defense
Towards Bias-Resilient Deep Neural Networks
Robik Shrestha
Imaging Science Ph.D. Candidate
Chester F. Carlson Center for Imaging Science, RIT
Register Here for Zoom Link
Abstract:
While deep learning systems have brought about a paradigm shift in the field of artificial intelligence, there are numerous apprehensions regarding their robustness when deployed in the real world. Multiple studies have demonstrated that deep learning models tend to latch onto biases present in their training data instead of truly solving the tasks. Given the pervasive nature of this issue across various datasets and tasks, multiple techniques have been proposed to improve bias resilience. However, the evaluation protocols used in prior works leave many open questions regarding their true robustness and the primary goal of this dissertation is to explore these questions. Specifically, we develop improved evaluation frameworks to investigate if the systems are right for the right reasons and generalize to realistic forms of biases. Apart from such studies, we also make progress in method development with an emphasis on simplifying existing approaches while either matching or exceeding state-of-the-art performance.
Intended Audience:
Undergraduates, graduates, and experts. Those with interest in the topic.
To request an interpreter, please visit https://myaccess.rit.edu
Event Snapshot
When and Where
Who
Open to the Public
Interpreter Requested?
No