中文
相关论文

相关论文: Compiler-Aware Neural Architecture Search for On-M…

200 篇论文

Neural architecture search has shown its great potential in various areas recently. However, existing methods rely heavily on a black-box controller to search architectures, which suffers from the serious problem of lacking…

机器学习 · 计算机科学 2020-09-29 Xinyue Zheng , Peng Wang , Qigang Wang , Zhongchao Shi

Designing effective neural architectures poses a significant challenge in deep learning. While Neural Architecture Search (NAS) automates the search for optimal architectures, existing methods are often constrained by predetermined search…

计算机视觉与模式识别 · 计算机科学 2024-12-30 Zekang Yang , Wang Zeng , Sheng Jin , Chen Qian , Ping Luo , Wentao Liu

In recent years, neural architecture search (NAS) has received intensive scientific and industrial interest due to its capability of finding a neural architecture with high accuracy for various artificial intelligence tasks such as image…

机器学习 · 计算机科学 2021-01-18 Martin Ferianc , Hongxiang Fan , Miguel Rodrigues

Accurately segmenting temporal frames of cine magnetic resonance imaging (MRI) is a crucial step in various real-time MRI guided cardiac interventions. To achieve fast and accurate visual assistance, there are strict requirements on the…

图像与视频处理 · 电气工程与系统科学 2022-06-14 Qing Lu , Xiaowei Xu , Shunjie Dong , Cong Hao , Lei Yang , Cheng Zhuo , Yiyu Shi

Computing-in-memory (CIM) is an emerging computing paradigm, offering noteworthy potential for accelerating neural networks with high parallelism, low latency, and energy efficiency compared to conventional von Neumann architectures.…

神经与进化计算 · 计算机科学 2024-09-30 Kam Chi Loong , Shihao Han , Sishuo Liu , Ning Lin , Zhongrui Wang

Neural Architecture Search remains a very challenging meta-learning problem. Several recent techniques based on parameter-sharing idea have focused on reducing the NAS running time by leveraging proxy models, leading to architectures with…

机器学习 · 计算机科学 2022-02-08 Minsu Cho , Mohammadreza Soltani , Chinmay Hegde

Neural Architecture Search (NAS) has shown great potentials in automatically designing scalable network architectures for dense image predictions. However, existing NAS algorithms usually compromise on restricted search space and search on…

计算机视觉与模式识别 · 计算机科学 2021-03-30 Xiong Zhang , Hongmin Xu , Hong Mo , Jianchao Tan , Cheng Yang , Lei Wang , Wenqi Ren

Neural Architecture Search (NAS), together with model scaling, has shown remarkable progress in designing high accuracy and fast convolutional architecture families. However, as neither NAS nor model scaling considers sufficient hardware…

计算机视觉与模式识别 · 计算机科学 2021-02-11 Sheng Li , Mingxing Tan , Ruoming Pang , Andrew Li , Liqun Cheng , Quoc Le , Norman P. Jouppi

Deep Learning models have experienced exponential growth in complexity and resource demands in recent years. Accelerating these models for efficient execution on resource-constrained devices has become more crucial than ever. Two notable…

机器学习 · 计算机科学 2024-08-09 Inas Bachiri , Hadjer Benmeziane , Smail Niar , Riyadh Baghdadi , Hamza Ouarnoughi , Abdelkrime Aries

Recently, much attention has been spent on neural architecture search (NAS), aiming to outperform those manually-designed neural architectures on high-level vision recognition tasks. Inspired by the success, here we attempt to leverage NAS…

计算机视觉与模式识别 · 计算机科学 2021-10-12 Haokui Zhang , Ying Li , Hao Chen , Chengrong Gong , Zongwen Bai , Chunhua Shen

Convolutional neural networks (CNNs), such as the time-delay neural network (TDNN), have shown their remarkable capability in learning speaker embedding. However, they meanwhile bring a huge computational cost in storage size, processing,…

音频与语音处理 · 电气工程与系统科学 2022-06-22 Rui Wang , Zhihua Wei , Haoran Duan , Shouling Ji , Yang Long , Zhen Hong

Neural Architectures Search (NAS) becomes more and more popular over these years. However, NAS-generated models tends to suffer greater vulnerability to various malicious attacks. Lots of robust NAS methods leverage adversarial training to…

机器学习 · 计算机科学 2023-04-11 Xunyu Zhu , Jian Li , Yong Liu , Weiping Wang

Searching techniques in most of existing neural architecture search (NAS) algorithms are mainly dominated by differentiable methods for the efficiency reason. In contrast, we develop an efficient continuous evolutionary approach for…

计算机视觉与模式识别 · 计算机科学 2020-03-10 Zhaohui Yang , Yunhe Wang , Xinghao Chen , Boxin Shi , Chao Xu , Chunjing Xu , Qi Tian , Chang Xu

Neural architecture search (NAS) can have a significant impact in computer vision by automatically designing optimal neural network architectures for various tasks. A variant, binarized neural architecture search (BNAS), with a search space…

计算机视觉与模式识别 · 计算机科学 2020-02-12 Hanlin Chen , Li'an Zhuo , Baochang Zhang , Xiawu Zheng , Jianzhuang Liu , David Doermann , Rongrong Ji

Super-resolution (SR) is a coveted image processing technique for mobile apps ranging from the basic camera apps to mobile health. Existing SR algorithms rely on deep learning models with significant memory requirements, so they have yet to…

人机交互 · 计算机科学 2021-01-21 Xin Liu , Yuang Li , Josh Fromm , Yuntao Wang , Ziheng Jiang , Alex Mariakakis , Shwetak Patel

Image Super-Resolution (ISR), which aims at recovering High-Resolution (HR) images from the corresponding Low-Resolution (LR) counterparts. Although recent progress in ISR has been remarkable. However, they are way too computationally…

计算机视觉与模式识别 · 计算机科学 2022-06-07 Jie Cai , Zibo Meng , Jiaming Ding , Chiu Man Ho

Neural Architecture Search (NAS) yields state-of-the-art neural networks that outperform their best manually-designed counterparts. However, previous NAS methods search for architectures under one set of training hyper-parameters (i.e., a…

计算机视觉与模式识别 · 计算机科学 2021-04-01 Xiaoliang Dai , Alvin Wan , Peizhao Zhang , Bichen Wu , Zijian He , Zhen Wei , Kan Chen , Yuandong Tian , Matthew Yu , Peter Vajda , Joseph E. Gonzalez

We implement a differentiable Neural Architecture Search (NAS) method inspired by FBNet for discovering neural networks that are heavily optimized for a particular target device. The FBNet NAS method discovers a neural network from a given…

计算机视觉与模式识别 · 计算机科学 2019-06-19 Sai Vineeth Kalluru Srinivas , Harideep Nair , Vinay Vidyasagar

Hardware-aware Neural Architecture Search (NAS) is one of the most promising techniques for designing efficient Deep Neural Networks (DNNs) for resource-constrained devices. Surrogate models play a crucial role in hardware-aware NAS as they…

机器学习 · 计算机科学 2025-08-05 Azaz-Ur-Rehman Nasir , Samroz Ahmad Shoaib , Muhammad Abdullah Hanif , Muhammad Shafique

Intelligent mobile agents (e.g., UGVs and UAVs) typically demand low power/energy consumption when solving their machine learning (ML)-based tasks, since they are usually powered by portable batteries with limited capacity. A potential…

神经与进化计算 · 计算机科学 2025-04-21 Rachmad Vidya Wicaksana Putra , Muhammad Shafique