Pre-Warm: הסתגלות של פילטרי קונבולוציונליים מאוצרות פאצ'ים מהמיניבאט הראשון

תקציר מקורי באנגליתarXiv:2606.25256v2 Announce Type: replace-cross Abstract: Random initialization of convolutional filters does not use the training images. Previous work has shown that image patches can be copied into the first layer, and that k-means or principal components of patches can serve as filters. This paper compares four initializations of the first layer of a small convolutional network, with every other factor held fixed: He initialization, random mean-centered patches, principal components of those patches, and k-means centroids. Pre-Warm, our proposed methodology, is the rule-based use of both dictionaries: the patch count follows the filter count and a foreground density, both dictionaries are built from a single minibatch, and whichever of principal components or k-means better reconstruct