Search Results

Art reinterpretation is the practice of creating a variation of a reference work, making a paired artwork that exhibits a distinct artistic style. We ask if such an image pair can be used to customize a generative model to capture the demonstrated ...

Model customization introduces new concepts to existing text-to-image models, enabling the generation of these new concepts/objects in novel contexts. However, such methods lack accurate camera view control with respect to the new object, and users must ...

The growing proliferation of customized and pretrained generative models has made it infeasible for a user to be fully cognizant of every model in existence. To address this need, we introduce the task of content-based model search: given a query and a ...

Interpretability is an emerging area of research in trustworthy machine learning. Safe deployment of machine learning system mandates that the prediction and its explanation be reliable and robust. Recently, it has been shown that the explanations ...$$$$

We present ShapeVis, a scalable visualization technique for point cloud data inspired from topological data analysis. Our method captures the underlying geometric and topological structure of the data in a compressed graphical representation. Much ...

Neural networks are vulnerable to adversarial attacks - small visually imperceptible crafted noise which when added to the input drastically changes the output. The most effective method of defending against adversarial attacks is to use the methodology ...

Neural networks have been shown to be vulnerable to adversarial perturbations. Although adversarially crafted examples look visually similar to the unaltered original image, neural networks behave abnormally on these modified images. Image ...