Compressed Object Detection

Abstract

Deep learning approaches have achieved unprecedented performance in visual recognition tasks such as object detection and pose estimation. However, state-of-the-art models have millions of parameters represented as floats which make them computationally expensive and constrain their deployment on hardware such as mobile phones and IoT nodes. Most commonly, activations of deep neural networks tend to be sparse thus proving that models are over parametrized with redundant neurons. Model compression techniques, such as pruning and quantization, have recently shown promising results by improving model complexity with little loss in performance. In this work, we extended pruning, a compression technique that discards unnecessary model connections, and weight sharing techniques for the task of object detection. With our approach, we are able to compress a state-of-the-art object detection model by 30.0% without a loss in performance. We also show that our compressed model can be easily initialized with existing pre-trained weights, and thus is able to fully utilize published state-of-the-art model zoos.

References in corpus (8)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• YOLOv3: An Incremental Improvement
• A Survey of Deep Learning-based Object Detection
• A Survey of Model Compression and Acceleration for Deep Neural Networks
• Binary Neural Networks: A Survey
• Trained Quantization Thresholds for Accurate and Efficient Fixed-Point Inference of Deep Neural Networks
• Bit Efficient Quantization for Deep Neural Networks
• On Iterative Neural Network Pruning, Reinitialization, and the Similarity of Masks