ACSL : adaptive correlation-driven sparsity learning for deep neural network compression

• Main Authors: He, Wei, Wu, Meiqing, Lam, Siew-Kei
• Other Authors: School of Computer Science and Engineering
• Format: Article
• Language: English
• Published: 2021
• Subjects: Engineering::Computer science and engineering; Network Pruning; Channel Correlation
• Online Access: https://hdl.handle.net/10356/152852
• Institution: Nanyang Technological University

Deep convolutional neural network compression has attracted lots of attention due to the need to deploy accurate models on resource-constrained edge devices. Existing techniques mostly focus on compressing networks for image-level classification, and it is not clear if they generalize well on networ...