Virtual London Machine Learning Meetup -[masked] @ 18:30
We would like to invite you to our next Virtual Machine Learning Meetup.
- 18:25: Virtual doors open
- 18:30: Talk
- 19:10: Q&A session
- 19:30: Close
https://evolution.ai/ : Machines that Read - Intelligent data extraction from corporate and financial documents.
* Title: Salient Imagenet: How to discover spurious features in deep learning? (Sahil Singla is a fourth year PhD student at the University of Maryland)
Abstract: A key reason for the lack of reliability of deep neural networks in the real world is their heavy reliance on spurious input features that are not essential to the true label (e.g., attribute “flower” for the class “butterfly”). Traditional methods for discovering spurious features either require extensive human annotations (thus not scalable), or are useful on specific models. In this work, we introduce a general framework to discover a subset of spurious visual attributes used in inferences of a general model and localize them on a large number of images with minimal human supervision. Our methodology is based on using the penultimate layer neurons of a robust model as interpretable visual attribute detectors. Using this methodology, we introduce the Salient Imagenet dataset containing such masks for a large set of samples from Imagenet. Using this dataset, we show that several popular Imagenet models rely heavily on various spurious features in their predictions, indicating the standard accuracy alone is not sufficient to fully assess model’ performance especially in safety-critical applications.
Bio: Sahil Singla is a fourth year PhD student at the University of Maryland, College Park. Earlier, he received his undergraduate degree in Computer Science from IIT Delhi. His primary research interests are adversarial robustness and interpretability of deep neural networks. Most of his recent work has focused on provable defenses against adversarial attacks and diagnosis of failure modes using robust models.