A0441
Title: Understanding convolutional neural networks: Statistical generative models for unstructured image data
Authors: Guohao Shen - The Hong Kong Polytechnic University (Hong Kong) [presenting]
Abstract: Convolutional neural networks (CNNs) are foundational in modern image analysis due to their ability to efficiently learn feature representations. However, theoretical understanding of their efficiency remains limited, largely due to inadequate modeling of image structures and their interaction with CNNs. To address this, novel statistical generative models (SGMs) are introduced that decompose images into task-relevant signals and noise, capturing the complexities of natural image data. Based on these SGMs, a feature mapping approach (FMA) is proposed to characterize the transformation from raw image data to feature vectors. CNNs' approximation capabilities are analyzed, as their adaptation to low-dimensional structures and their efficiency in vision tasks, ultimately developing statistical learning theories for CNN-based image analysis. The findings reveal the challenges inherent in vision tasks and highlight CNNs' remarkable efficiency in addressing them, providing new insights into their theoretical and practical capabilities.
