Interactive Visual Feature Search
This tool addresses the need for reusable, adaptable visualizations to interpret CNN behavior for researchers, though it is incremental as it builds on existing interactive methods.
The paper tackles the problem of limited interpretability in static visualizations for computer vision models by introducing Visual Feature Search, an interactive tool that allows users to highlight image regions and find similar features across datasets, demonstrating its utility in applications like medical imaging and wildlife classification.
Many visualization techniques have been created to explain the behavior of computer vision models, but they largely consist of static diagrams that convey limited information. Interactive visualizations allow users to more easily interpret a model's behavior, but most are not easily reusable for new models. We introduce Visual Feature Search, a novel interactive visualization that is adaptable to any CNN and can easily be incorporated into a researcher's workflow. Our tool allows a user to highlight an image region and search for images from a given dataset with the most similar model features. We demonstrate how our tool elucidates different aspects of model behavior by performing experiments on a range of applications, such as in medical imaging and wildlife classification.