Empowering Human-like Decision Making in AI Models through Explanations

Abstract: Deep neural networks have achieved remarkable results in several Computer Vision tasks, but their increasing complexity poses challenges in terms of interpretability. In this talk, I will present my research on explainability in deep learning models, ranging from convolutional neural networks (CNNs) to multi-modal transformers, for tasks ranging from static image analysis to active perception, and demonstrate how it can enhance their human-likeness. I will focus on how interpretability can establish user trust, identify failure modes, provide targeted human …

abstract ai models analysis challenges cnns complexity computer computer vision convolutional neural networks decision decision making deep learning explainability failure feedback focus human human feedback human-like identify image interpretability making networks neural networks perception reasoning research talk terms through transformers trust user trust vision