{"ID":2842952,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.11716","arxiv_id":"2511.11716","title":"CompressNAS : A Fast and Efficient Technique for Model Compression using Decomposition","abstract":"Deep Convolutional Neural Networks (CNNs) are increasingly difficult to deploy on microcontrollers (MCUs) and lightweight NPUs (Neural Processing Units) due to their growing size and compute demands. Low-rank tensor decomposition, such as Tucker factorization, is a promising way to reduce parameters and operations with reasonable accuracy loss. However, existing approaches select ranks locally and often ignore global trade-offs between compression and accuracy. We introduce CompressNAS, a MicroNAS-inspired framework that treats rank selection as a global search problem. CompressNAS employs a fast accuracy estimator to evaluate candidate decompositions, enabling efficient yet exhaustive rank exploration under memory and accuracy constraints. In ImageNet, CompressNAS compresses ResNet-18 by 8x with less than 4% accuracy drop; on COCO, we achieve 2x compression of YOLOv5s without any accuracy drop and 2x compression of YOLOv5n with a 2.5% drop. Finally, we present a new family of compressed models, STResNet, with competitive performance compared to other efficient models.","short_abstract":"Deep Convolutional Neural Networks (CNNs) are increasingly difficult to deploy on microcontrollers (MCUs) and lightweight NPUs (Neural Processing Units) due to their growing size and compute demands. Low-rank tensor decomposition, such as Tucker factorization, is a promising way to reduce parameters and operations with...","url_abs":"https://arxiv.org/abs/2511.11716","url_pdf":"https://arxiv.org/pdf/2511.11716v1","authors":"[\"Sudhakar Sah\",\"Nikhil Chabbra\",\"Matthieu Durnerin\"]","published":"2025-11-12T18:25:46Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"LoRA\",\"Convolutional Neural Network\"]","has_code":false}