English
Related papers

Related papers: FCOS: A Two-Stage Recoverable Model Pruning Framew…

200 papers

Convolutional neural networks have shown tremendous performance capabilities in computer vision tasks, but their excessive amounts of weight storage and arithmetic operations prevent them from being adopted in embedded environments. One of…

Neural and Evolutionary Computing · Computer Science 2020-09-08 Hyeong-Ju Kang

Recent works have indicated redundancy across transformer blocks, prompting the research of depth compression to prune less crucial blocks. However, current ways of entire-block pruning suffer from risks of discarding meaningful cues…

Computer Vision and Pattern Recognition · Computer Science 2026-02-10 Ruihan Xu , Qingpei Guo , Yao Zhu , Xiangyang Ji , Ming Yang , Shiliang Zhang

In frequency division duplex (FDD) systems, acquiring channel state information (CSI) at the base station (BS) traditionally relies on limited feedback from mobile terminals (MTs). However, the accuracy of channel reconstruction from…

Information Theory · Computer Science 2025-03-10 Yunseo Nam , Jiwook Choi

Channel pruning is widely accepted to accelerate modern convolutional neural networks (CNNs). The resulting pruned model benefits from its immediate deployment on general-purpose software and hardware resources. However, its large pruning…

Computer Vision and Pattern Recognition · Computer Science 2024-03-11 Mincheol Park , Dongjin Kim , Cheonjun Park , Yuna Park , Gyeong Eun Gong , Won Woo Ro , Suhyun Kim

Model pruning has become a useful technique that improves the computational efficiency of deep learning, making it possible to deploy solutions in resource-limited scenarios. A widely-used practice in relevant work assumes that a…

Machine Learning · Computer Science 2018-02-06 Jianbo Ye , Xin Lu , Zhe Lin , James Z. Wang

Driven by significant improvements in architectural design and training pipelines, computer vision has recently experienced dramatic progress in terms of accuracy on classic benchmarks such as ImageNet. These highly-accurate models are…

Computer Vision and Pattern Recognition · Computer Science 2023-06-01 Denis Kuznedelev , Eldar Kurtic , Elias Frantar , Dan Alistarh

Camouflaged Object Segmentation (COS) remains challenging because camouflaged objects exhibit only subtle visual differences from their backgrounds and single-modality RGB methods provide limited cues, leading researchers to explore…

Computer Vision and Pattern Recognition · Computer Science 2025-05-20 Chengyu Fang , Chunming He , Longxiang Tang , Yuelin Zhang , Chenyang Zhu , Yuqi Shen , Chubin Chen , Guoxia Xu , Xiu Li

As an emerging technology, federated learning (FL) involves training machine learning models over distributed edge devices, which attracts sustained attention and has been extensively studied. However, the heterogeneity of client data…

Machine Learning · Computer Science 2022-12-29 Hao Zhang , Tingting Wu , Siyao Cheng , Jie Liu

In this paper, a new communication-efficient federated learning (FL) framework is proposed, inspired by vector quantized compressed sensing. The basic strategy of the proposed framework is to compress the local model update at each device…

Information Theory · Computer Science 2023-07-04 Yongjeong Oh , Yo-Seb Jeon , Mingzhe Chen , Walid Saad

Embedded and personal IoT devices are powered by microcontroller units (MCUs), whose extreme resource scarcity is a major obstacle for applications relying on on-device deep learning inference. Orders of magnitude less storage, memory and…

Machine Learning · Computer Science 2022-12-09 Edgar Liberis , Nicholas D. Lane

This paper introduces an Algebraic MultiScale method for simulation of flow in heterogeneous porous media with embedded discrete Fractures (F-AMS). First, multiscale coarse grids are independently constructed for both porous matrix and…

Numerical Analysis · Mathematics 2017-05-17 Matei Tene , Mohammed Saad Al Kobaisi , Hadi Hajibeygi

Compression techniques for deep neural network models are becoming very important for the efficient execution of high-performance deep learning systems on edge-computing devices. The concept of model compression is also important for…

Overparametrized transformer networks are the state-of-the-art architecture for Large Language Models (LLMs). However, such models contain billions of parameters making large compute a necessity, while raising environmental concerns. To…

Machine Learning · Computer Science 2024-10-22 Yang Zhang , Yawei Li , Xinpeng Wang , Qianli Shen , Barbara Plank , Bernd Bischl , Mina Rezaei , Kenji Kawaguchi

Deep convolutional neural networks have achieved remarkable success in face recognition (FR), partly due to the abundant data availability. However, the current training benchmarks exhibit an imbalanced quality distribution; most images are…

Computer Vision and Pattern Recognition · Computer Science 2023-08-21 Sahar Rahimi Malakshan , Mohammad Saeed Ebrahimi Saadabadi , Nima Najafzadeh , Nasser M. Nasrabadi

To address the limitations of existing magnitude-based pruning algorithms in cases where model weights or activations are of large and similar magnitude, we propose a novel perspective to discover parameter redundancy among channels and…

Machine Learning · Computer Science 2019-08-08 Yunxiang Zhang , Chenglong Zhao , Bingbing Ni , Jian Zhang , Haoran Deng

Large Language Models (LLMs) exhibit strong reasoning abilities, but their high computational costs limit their practical deployment. Recent studies reveal significant redundancy in LLMs layers, making layer pruning an active research…

Computation and Language · Computer Science 2026-02-17 Hao Liu , Guangyan Li , Wensheng Zhang , Yongqiang Tang

We propose Cluster Pruning (CUP) for compressing and accelerating deep neural networks. Our approach prunes similar filters by clustering them based on features derived from both the incoming and outgoing weight connections. With CUP, we…

Computer Vision and Pattern Recognition · Computer Science 2019-11-21 Rahul Duggal , Cao Xiao , Richard Vuduc , Jimeng Sun

Transformer-based speech recognition (ASR) model with deep layers exhibited significant performance improvement. However, the model is inefficient for deployment on resource-constrained devices. Layer pruning (LP) is a commonly used…

Audio and Speech Processing · Electrical Eng. & Systems 2023-09-22 Wei Liu , Zhiyuan Peng , Tan Lee

The rapid growth of resource-constrained mobile platforms, including mobile robots, wearable systems, and Internet-of-Things devices, has increased the demand for computationally efficient neural network controllers (NNCs) that can operate…

Robotics · Computer Science 2025-08-12 Ganesh Sundaram , Jonas Ulmen , Amjad Haider , Daniel Görges

This work evaluates the compression techniques on ConvNeXt models in image classification tasks using the CIFAR-10 dataset. Structured pruning, unstructured pruning, and dynamic quantization methods are evaluated to reduce model size and…

Machine Learning · Computer Science 2024-09-05 Samer Francy , Raghubir Singh
‹ Prev 1 8 9 10 Next ›