# Trainable Spectrally Initializable Matrix Transformations in Convolutional Neural Networks Source: [Trainable Spectrally Initializable Matrix Transformations in Convolutional Neural Networks]() Collection index: [llms.txt]() Data updated: 2025-10-25T21:56:21.324Z Authors: Michele Alberti, Angela Botros, Narayan Schuez, Rolf Ingold, Marcus Liwicki, Mathias Seuret Published: 2019-11-12T18:06:52.000Z ## Abstract In this work, we investigate the application of trainable and spectrally initializable matrix transformations on the feature maps produced by convolution operations. While previous literature has already demonstrated the possibility of adding static spectral transformations as feature processors, our focus is on more general trainable transforms. We study the transforms in various architectural configurations on four datasets of different nature: from medical (ColorectalHist, HAM10000) and natural (Flowers, ImageNet) images to historical documents (CB55) and handwriting recognition (GPDS). With rigorous experiments that control for the number of parameters and randomness, we show that networks utilizing the introduced matrix transformations outperform vanilla neural networks. The observed accuracy increases by an average of 2.2 across all datasets. In addition, we show that the benefit of spectral initialization leads to significantly faster convergence, as opposed to randomly initialized matrix transformations. The transformations are implemented as auto-differentiable PyTorch modules that can be incorporated into any neural network architecture. The entire code base is open-source. ## 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]()