2022/11/03 by S Rakshith, Jayesh Rajkumar Vachhani, Rakshith, S +5
Computer Science · Engineering · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Gait Recognition and Analysis #Infrared Target Detection Methodologies #Machine Learning (cs.LG) #Neural Networks and Applications
paper · pdf · doi:10.48550/arxiv.2211.01814
openalex publication_date 2022/11/03 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
In recent years, most of the deep learning solutions are targeted to be deployed in mobile devices. This makes the need for development of lightweight models all the more imminent. Another solution is to optimize and prune regular deep learning models. In this paper, we tackle the problem of CNN model pruning with the help of Self-Similarity Matrix (SSM) computed from the 2D CNN filters. We propose two novel algorithms to rank and prune redundant filters which contribute similar activation maps to the output. One of the key features of our method is that there is no need of finetuning after training the model. Both the training and pruning process is completed simultaneously. We benchmark our method on two of the most popular CNN models - ResNet and VGG and record their performance on the CIFAR-10 dataset.