# Separating Knowledge and Perception with Procedural Data Source: [Separating Knowledge and Perception with Procedural Data]() Collection index: [llms.txt]() Data updated: 2025-10-26T05:24:53.663Z Authors: Adri\\'an Rodr\\'iguez-Mu\\~noz, Manel Baradad, Phillip Isola, Antonio Torralba Published: 2025-08-12T19:48:35.000Z ## Abstract We train representation models with procedural data only, and apply them on visual similarity, classification, and semantic segmentation tasks without further training by using visual memory -- an explicit database of reference image embeddings. Unlike prior work on visual memory, our approach achieves full compartmentalization with respect to all real-world images while retaining strong performance. Compared to a model trained on Places, our procedural model performs within $1\\%$ on NIGHTS visual similarity, outperforms by $8\\%$ and $15\\%$ on CUB200 and Flowers102 fine-grained classification, and is within $10\\%$ on ImageNet-1K classification. It also demonstrates strong zero-shot segmentation, achieving an $R^2$ on COCO within $10\\%$ of the models trained on real data. Finally, we analyze procedural versus real data models, showing that parts of the same object have dissimilar representations in procedural models, resulting in incorrect searches in memory and explaining the remaining performance gap. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()