Tensor Reordering for CNN Compression

التفاصيل البيبلوغرافية
العنوان: Tensor Reordering for CNN Compression
المؤلفون: Rozenn Dahyot, Vladimir A. Krylov, Matej Ulicny
المصدر: ICASSP
بيانات النشر: IEEE, 2021.
سنة النشر: 2021
مصطلحات موضوعية: FOS: Computer and information sciences, Computer Science - Machine Learning, Computer science, Computer Vision and Pattern Recognition (cs.CV), Computer Science - Computer Vision and Pattern Recognition, 02 engineering and technology, Convolutional neural network, Machine Learning (cs.LG), Memory management, Compression (functional analysis), 0202 electrical engineering, electronic engineering, information engineering, Redundancy (engineering), Discrete cosine transform, 020201 artificial intelligence & image processing, Pruning (decision trees), Tensor, Representation (mathematics), Algorithm
الوصف: We show how parameter redundancy in Convolutional Neural Network (CNN) filters can be effectively reduced by pruning in spectral domain. Specifically, the representation extracted via Discrete Co-sine Transform (DCT) is more conducive for pruning than the original space. By relying on a combination of weight tensor reshaping and reordering we achieve high levels of layer compression with just minor accuracy loss. Our approach is applied to compress pre-trained CNNs and we show that minor additional fine-tuning allows our method to recover the original model performance after a significant parameter reduction. We validate our approach on ResNet-50 and MobileNet-V2 architectures for ImageNet classification task.
DOI: 10.1109/icassp39728.2021.9413944
URL الوصول: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f701e2feaf7232d65ec55aa003dfc67f
https://doi.org/10.1109/icassp39728.2021.9413944
Rights: OPEN
رقم الانضمام: edsair.doi.dedup.....f701e2feaf7232d65ec55aa003dfc67f
قاعدة البيانات: OpenAIRE
الوصف
DOI:10.1109/icassp39728.2021.9413944