CLIP这类模型认画风还是认画家？这篇论文用“艺术家分离”测试发现，超现实主义识别会掉20个点。搞艺术分类的值得看。
作者在320幅二十世纪绘画上测试艺术家分离协议，5-NN风格准确率从0.87降至0.77，超现实主义下降20个百分点。印象派和立体主义准确率几乎不变，超现实主义的下降在四个图像编码器中一致出现。这一模式甚至出现在视觉自监督模型中，说明问题源于视觉结构而非语言。结果表明现有随机划分夸大了风格理解能力。
Style or Signature? Artist-Disjoint Evaluation of Style Classification in Frozen Vision Embeddings
Frozen image embeddings from models such as CLIP are increasingly used to classify paintings by art-historical style, with high reported accuracy. We ask whether this accuracy reflects an understanding of style or the recognition of individual artists. Standard evaluation uses random splits in which works by the same artist appear on both sides, so a classifier can succeed by recognising the painter rather than the movement. We re-evaluate style classification under an artist-disjoint protocol, holding out every artist in turn so that no work is ever classified using other works by its own painter. On a balanced dataset of 320 paintings across four twentieth-century movements, 5-NN style accuracy falls from 0.87 to 0.77 under this protocol, and the drop is sharply uneven. Impressionism and Cubism barely move, while Surrealism falls twenty points. The pattern holds across four image encoders, including a vision-only self-supervised model, which places the effect in visual structure rather than language. Where an encoder captures genuine shared form, individual artists are barely recognisable yet style is robust, while Surrealism shows the opposite. We argue that artist-disjoint evaluation is necessary to measure stylistic understanding in frozen embeddings.