Salient ImageNet: How to discover spurious features in Deep Learning?

Deep neural networks can be unreliable in the real world especially when they heavily use it spurious features for their predictions. Focusing on image classifications, we define it core features as the set of visual features that are always a part of the object definition while it spurious features are the ones that are likely to it co-occur with the object but not a part of it (e.g., attribute "fingers" for class "band aid"). 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 it general framework to discover a subset of spurious and core visual features 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 this key idea: to identify spurious or core textitvisual features used in model predictions, we identify spurious or core textitneural features (penultimate layer neurons of a robust model) via limited human supervision (e.g., using top 5 activating images per feature). We then show that these neural feature annotations it generalize extremely well to many more images it without any human supervision. We use the activation maps for these neural features as the soft masks to highlight spurious or core visual features. Using this methodology, we introduce the it Salient Imagenet dataset containing core and spurious 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. Code and dataset for reproducing all experiments in the paper is available at urlhttps://github.com/singlasahil14/salientimagenet.