🤖 AI Summary
Deep convolutional neural networks (CNNs) face persistent challenges in balancing representational capacity with deployment efficiency across diverse domains—including vision, language, healthcare, and speech—especially under resource constraints and data-limited regimes. Method: This work systematically surveys CNN architectural evolution from 2015 to 2025 and proposes a novel seven-dimensional unified taxonomy (covering spatial modeling, multi-path design, dimensional expansion, attention integration, etc.), alongside a synergistic optimization framework integrating sparse convolutions, depthwise separable convolutions, and attention mechanisms. It further incorporates Fourier-based preprocessing, low-precision computation, and weight compression for lightweight deployment. Contribution/Results: We comprehensively characterize the applicability boundaries of over 100 CNN variants, quantify the trade-off between computational efficiency and representation fidelity, formalize adaptation strategies for few-shot, weakly supervised, and federated learning settings, and prospectively identify emerging directions—including CNN-Transformer hybrids, vision-language joint modeling, and generative CNNs—establishing reusable design paradigms for edge deployment and cross-domain generalization.
📝 Abstract
Deep Convolutional Neural Networks (CNNs) have significantly advanced deep learning, driving breakthroughs in computer vision, natural language processing, medical diagnosis, object detection, and speech recognition. Architectural innovations including 1D, 2D, and 3D convolutional models, dilated and grouped convolutions, depthwise separable convolutions, and attention mechanisms address domain-specific challenges and enhance feature representation and computational efficiency. Structural refinements such as spatial-channel exploitation, multi-path design, and feature-map enhancement contribute to robust hierarchical feature extraction and improved generalization, particularly through transfer learning. Efficient preprocessing strategies, including Fourier transforms, structured transforms, low-precision computation, and weight compression, optimize inference speed and facilitate deployment in resource-constrained environments. This survey presents a unified taxonomy that classifies CNN architectures based on spatial exploitation, multi-path structures, depth, width, dimensionality expansion, channel boosting, and attention mechanisms. It systematically reviews CNN applications in face recognition, pose estimation, action recognition, text classification, statistical language modeling, disease diagnosis, radiological analysis, cryptocurrency sentiment prediction, 1D data processing, video analysis, and speech recognition. In addition to consolidating architectural advancements, the review highlights emerging learning paradigms such as few-shot, zero-shot, weakly supervised, federated learning frameworks and future research directions include hybrid CNN-transformer models, vision-language integration, generative learning, etc. This review provides a comprehensive perspective on CNN's evolution from 2015 to 2025, outlining key innovations, challenges, and opportunities.