A Simple and Efficient Baseline for Data Attribution on Images
University of Maryland（马里兰大学）；New York University（纽约大学）；ELLIS Institute Tübingen（蒂宾根ELLIS研究所）；MPI for Intelligent Systems（马克斯·普朗克智能系统研究所）；Tübingen AI Center（蒂宾根人工智能中心）
Vasu Singla, Pedro Sandoval-Segura, Micah Goldblum, Jonas Geiping, Tom Goldstein
Data attribution methods play a crucial role in understanding machine learning models, providing insight into which training data points are most responsible for model outputs during deployment. However, current state-of-the-art approaches require a large ensemble of as many as 300,000 models to accurately attribute model predictions. These approaches therefore come at a high computational cost, are memory intensive, and are hard to scale to large models or datasets. In this work, we focus on a minimalist baseline, utilizing the feature space of a backbone pretrained via self-supervised learning to perform data attribution. Our method is model-agnostic and scales easily to large datasets. We show results on CIFAR-10 and ImageNet, achieving strong performance that rivals or outperforms state-of-the-art approaches at a fraction of the compute or memory cost. Contrary to prior work, our results reinforce the intuition that a model's prediction on one image is most impacted by visually similar training samples. Our approach serves as a simple and efficient baseline for data attribution on images.
Tracing Generated Samples to Training-Data Clusters in Flow-Matching Models
Forschungszentrum Jülich（于利希研究中心）；Technical University Dortmund（多特蒙德工业大学）；Reichman University（赖希曼大学）；Lamarr Institute（拉马尔研究所）；Institute for AI in Medicine, University Hospital Essen（埃森大学医院医学人工智能研究所）；Helmholtz AI（亥姆霍兹人工智能）；University of Cologne（科隆大学）
Generating Attribution Reports for Manipulated Facial Images: A Dataset and Baseline
Xi’an Jiaotong University（西安交通大学）；Hefei University of Technology（合肥工业大学）；CSIRO（澳大利亚联邦科学与工业研究组织）；Northwestern Polytechnical University（西北工业大学）；University of Macau（澳门大学）
Back to the Baseline: Examining Baseline Effects on Explainability Metrics
IRT Saint-Exupéry（圣埃克苏佩里技术研究院）；Artificial and Natural Intelligence Toulouse Institute, Université de Toulouse（图卢兹大学人工与自然智能图卢兹研究所）；Carney Institute for Brain Science, Brown University（布朗大学卡尼脑科学研究所）；Sorbonne Université（索邦大学）；CNRS（法国国家科学研究中心）；Harvard University（哈佛大学）
Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Beijing Academy of Artificial Intelligence（北京智源人工智能研究院）；University of Chinese Academy of Sciences（中国科学院大学）；Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））；Peking University（北京大学）
On the Evaluation Consistency of Attribution-based Explanations
College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）；Key Laboratory of Visual Perception (Zhejiang University), Ministry of Education and Microsoft（视觉感知重点实验室（浙江大学）教育部与微软联合实验室）；School of Software Technology, Zhejiang University（浙江大学软件学院）；Alibaba Group（阿里巴巴集团）；Hangzhou City University（杭州城市大学）；Ningbo Innovation Center, Zhejiang University（浙江大学宁波创新中心）
