Image Classifier
Image classifiers are computer vision systems designed to categorize images into predefined classes, with recent research focusing on improving their accuracy, robustness, and explainability. Current efforts involve developing more efficient architectures (like Vision Transformers and EfficientNets), mitigating biases through techniques such as counterfactual analysis and subgroup discovery, and enhancing interpretability using multimodal explanations that integrate visual and textual information. These advancements are crucial for building reliable and trustworthy image classifiers, impacting diverse fields from medical diagnosis to autonomous driving by improving both performance and user understanding of model decisions.
Papers
Adapt Anything: Tailor Any Image Classifiers across Domains And Categories Using Text-to-Image Diffusion Models
Weijie Chen, Haoyu Wang, Shicai Yang, Lei Zhang, Wei Wei, Yanning Zhang, Luojun Lin, Di Xie, Yueting Zhuang
On the stability, correctness and plausibility of visual explanation methods based on feature importance
Romain Xu-Darme, Jenny Benois-Pineau, Romain Giot, Georges Quénot, Zakaria Chihani, Marie-Christine Rousset, Alexey Zhukov
Neglected Free Lunch -- Learning Image Classifiers Using Annotation Byproducts
Dongyoon Han, Junsuk Choe, Seonghyeok Chun, John Joon Young Chung, Minsuk Chang, Sangdoo Yun, Jean Y. Song, Seong Joon Oh
Mole Recruitment: Poisoning of Image Classifiers via Selective Batch Sampling
Ethan Wisdom, Tejas Gokhale, Chaowei Xiao, Yezhou Yang