Abstract. We propose a novel Convolutional Neural Network (CNN)
compression algorithm based on coreset representations of filters. We
exploit the redundancies extant in the space of CNN weights and neuronal
activations (across samples) in order to obtain compression. Our method
requires no retraining, is easy to implement, and obtains state-of-the-art
compression performance across a wide variety of CNN architectures.
Coupled with quantization and Huffman coding, we create networks that
provide AlexNet-like accuracy, with a memory footprint that is 832×
smaller than the original AlexNet, while also introducing significant reductions in inference time as well. Additionally these compressed networks
when fine-tuned, successfully generalize to other domains as well