Deep Neural Network Compression for Image Classification and Object Detection
This addresses the problem of deploying deep neural networks on resource-constrained devices for applications like real-time image processing, though it appears incremental as it builds on existing compression techniques.
The paper tackles the problem of deep neural networks being computationally expensive and memory-intensive, especially for embedded devices and real-time tasks like image classification and object detection, by proposing a network-agnostic compression method with dynamical clustering. The result includes pruning 95% of parameters in classification networks and reducing YOLOv3 parameters by 59.70% with 110X less memory while maintaining accuracy.
Neural networks have been notorious for being computationally expensive. This is mainly because neural networks are often over-parametrized and most likely have redundant nodes or layers as they are getting deeper and wider. Their demand for hardware resources prohibits their extensive use in embedded devices and puts restrictions on tasks like real-time image classification or object detection. In this work, we propose a network-agnostic model compression method infused with a novel dynamical clustering approach to reduce the computational cost and memory footprint of deep neural networks. We evaluated our new compression method on five different state-of-the-art image classification and object detection networks. In classification networks, we pruned about 95% of network parameters. In advanced detection networks such as YOLOv3, our proposed compression method managed to reduce the model parameters up to 59.70% which yielded 110X less memory without sacrificing much in accuracy.