# Compressing the Input for CNNs with the First-Order Scattering Transform Source: [Compressing the Input for CNNs with the First-Order Scattering Transform]() Collection index: [llms.txt]() Data updated: 2025-10-28T13:56:36.986Z Authors: Edouard Oyallon, Eugene Belilovsky, Sergey Zagoruyko, Michal Valko Published: 2018-09-27T10:14:46.000Z ## Abstract We study the first-order scattering transform as a candidate for reducing the signal processed by a convolutional neural network (CNN). We show theoretical and empirical evidence that in the case of natural images and sufficiently small translation invariance, this transform preserves most of the signal information needed for classification while substantially reducing the spatial resolution and total signal size. We demonstrate that cascading a CNN with this representation performs on par with ImageNet classification models, commonly used in downstream tasks, such as the ResNet-50. We subsequently apply our trained hybrid ImageNet model as a base model on a detection system, which has typically larger image inputs. On Pascal VOC and COCO detection tasks we demonstrate improvements in the inference speed and training memory consumption compared to models trained directly on the input image. ## 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. - [Image Classification on ImageNet (val) (Top-1/Top-5 Accuracy)](): Image Classification; ImageNet (val); Top-1 Accuracy: 25.5. ## Original sources and implementation [Original paper]() [PDF]()