5 papers · 1 filter
Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI
Casey Wall, Longwei Wang, Rodrigue Rizk +1
Gradient-weighted Class Activation Mapping (Grad-CAM) is widely used to visualize model decisions, but it was originally formulated for convolutional neural networks, where spatial…
Explainable Novel Category Discovery in Semantic Concept Space
Ifrat Ikhtear Uddin, Yang Zhou, KC Santosh +1
Novel category discovery aims to identify unseen classes from unlabeled data by transferring knowledge from labeled categories, but most existing methods perform discovery in opaqu…
Winsor-CAM: Human-Tunable Visual Explanations from Deep Networks via Layer-Wise Winsorization
Casey Wall, Longwei Wang, Rodrigue Rizk +1
Interpreting Convolutional Neural Networks (CNNs) is critical for safety-sensitive applications such as healthcare and autonomous systems. Popular visual explanation methods like G…
Promoting Shape Bias in CNNs: Frequency-Based and Contrastive Regularization for Corruption Robustness
Robin Narsingh Ranabhat, Longwei Wang, Amit Kumar Patel +1
Convolutional Neural Networks (CNNs) excel at image classification but remain vulnerable to common corruptions that humans handle with ease. A key reason for this fragility is thei…
CoSwin: Convolution Enhanced Hierarchical Shifted Window Attention For Small-Scale Vision
Puskal Khadka, Rodrigue Rizk, Longwei Wang +1
Vision Transformers (ViTs) have achieved impressive results in computer vision by leveraging self-attention to model long-range dependencies. However, their emphasis on global cont…