no code implementations • 13 Oct 2023 • Junlei Zhou, Jiashi Gao, Ziwei Wang, Xuetao Wei
Previous work only focused on data attribution from the training data perspective, which is unsuitable for tracing and quantifying copyright infringement in practice because of the following reasons: (1) the training datasets are not always available in public; (2) the model provider is the responsible party, not the image.