Image Classification
Image classification, the task of assigning predefined labels to images, aims to develop robust and accurate algorithms for diverse applications. Current research emphasizes improving generalization to unseen data and handling challenges like data scarcity, class imbalance, and adversarial attacks, often employing deep learning models such as convolutional neural networks (CNNs), vision transformers (ViTs), and large language models (LLMs) integrated with techniques like self-supervised learning, data augmentation, and uncertainty quantification. These advancements are crucial for various fields, including medical diagnosis, autonomous driving, and environmental monitoring, where reliable and efficient image analysis is paramount.
Papers
Robust width: A lightweight and certifiable adversarial defense
Jonathan Peck, Bart Goossens
What Do You See? Enhancing Zero-Shot Image Classification with Multimodal Large Language Models
Abdelrahman Abdelhamed, Mahmoud Afifi, Alec Go
Exposing Image Classifier Shortcuts with Counterfactual Frequency (CoF) Tables
James Hinns, David Martens
Interpretable Network Visualizations: A Human-in-the-Loop Approach for Post-hoc Explainability of CNN-based Image Classification
Matteo Bianchi, Antonio De Santis, Andrea Tocchetti, Marco Brambilla
Class-relevant Patch Embedding Selection for Few-Shot Image Classification
Weihao Jiang, Haoyang Cui, Kun He