Multi-scale Unified Network for Image Classification

arXiv:2403.18294v1 Announce Type: new
Abstract: Convolutional Neural Networks (CNNs) have advanced significantly in visual representation learning and recognition. However, they face notable challenges in performance and computational efficiency when dealing with real-world, multi-scale image inputs. Conventional methods rescale all input images into a fixed size, wherein a larger fixed size favors performance but rescaling small size images to a larger size incurs digitization noise and increased computation cost. In this work, we carry out a comprehensive, layer-wise investigation of CNN …

abstract advanced arxiv challenges classification cnns computational convolutional neural networks cs.cv efficiency face however image images inputs network networks neural networks performance recognition representation representation learning rescale scale type visual world