English
Related papers

Related papers: FNA++: Fast Network Adaptation via Parameter Remap…

200 papers

Neural architecture search (NAS) aims to automate architecture design processes and improve the performance of deep neural networks. Platform-aware NAS methods consider both performance and complexity and can find well-performing…

Neural and Evolutionary Computing · Computer Science 2022-07-22 Yuhei Noda , Shota Saito , Shinichi Shirakawa

In this paper, we propose a new neural architecture search (NAS) problem of Symmetric Positive Definite (SPD) manifold networks, aiming to automate the design of SPD neural architectures. To address this problem, we first introduce a…

Machine Learning · Computer Science 2021-06-15 Rhea Sanjay Sukthanker , Zhiwu Huang , Suryansh Kumar , Erik Goron Endsjo , Yan Wu , Luc Van Gool

Recently, Neural Architecture Search (NAS) has successfully identified neural network architectures that exceed human designed ones on large-scale image classification. In this paper, we study NAS for semantic image segmentation. Existing…

Computer Vision and Pattern Recognition · Computer Science 2019-04-09 Chenxi Liu , Liang-Chieh Chen , Florian Schroff , Hartwig Adam , Wei Hua , Alan Yuille , Li Fei-Fei

Neural Architecture Search (NAS) is challenged by the trade-off between search space exploration and efficiency, especially for complex tasks. While recent LLM-based NAS methods have shown promise, they often suffer from static search…

Machine Learning · Computer Science 2025-07-29 Fei Kong , Xiaohan Shan , Yanwei Hu , Jianmin Li

Neural architecture search has attracted wide attentions in both academia and industry. To accelerate it, researchers proposed weight-sharing methods which first train a super-network to reuse computation among different operators, from…

Machine Learning · Computer Science 2020-12-16 Xin Chen , Lingxi Xie , Jun Wu , Longhui Wei , Yuhui Xu , Qi Tian

Optimizing resource utilization in target platforms is key to achieving high performance during DNN inference. While optimizations have been proposed for inference latency, memory footprint, and energy consumption, prior hardware-aware…

Machine Learning · Computer Science 2022-03-24 Ahmet Caner Yüzügüler , Nikolaos Dimitriadis , Pascal Frossard

One-Shot Neural Architecture Search (NAS) is a promising method to significantly reduce search time without any separate training. It can be treated as a Network Compression problem on the architecture parameters from an over-parameterized…

Machine Learning · Computer Science 2019-06-11 Hongpeng Zhou , Minghao Yang , Jun Wang , Wei Pan

In this work, we propose a Neural Architecture Search (NAS) for retinal layer segmentation in Optical Coherence Tomography (OCT) scans. We incorporate the Unet architecture in the NAS framework as its backbone for the segmentation of the…

Image and Video Processing · Electrical Eng. & Systems 2020-07-30 Saba Heidari Gheshlaghi , Omid Dehzangi , Ali Dabouei , Annahita Amireskandari , Ali Rezai , Nasser M Nasrabadi

Enabling efficient deep neural network (DNN) inference on edge devices with different hardware constraints is a challenging task that typically requires DNN architectures to be specialized for each device separately. To avoid the huge…

Artificial Intelligence · Computer Science 2026-03-17 Mark Deutel , Simon Geis , Axel Plinge

Search spaces hallmark the advancement of Neural Architecture Search (NAS). Large and complex search spaces with versatile building operators and structures provide more opportunities to brew promising architectures, yet pose severe…

Computer Vision and Pattern Recognition · Computer Science 2023-07-07 Bhavna Gopal , Arjun Sridhar , Tunhou Zhang , Yiran Chen

Deep Neural Networks (DNNs) are computationally and memory intensive, which makes their hardware implementation a challenging task especially for resource constrained devices such as IoT nodes. To address this challenge, this paper…

Computer Vision and Pattern Recognition · Computer Science 2021-05-10 Mohammed F. Tolba , Huruy Tekle Tesfai , Hani Saleh , Baker Mohammad , Mahmoud Al-Qutayri

Training neural networks requires increasing amounts of memory. Parameter sharing can reduce memory and communication costs, but existing methods assume networks have many identical layers and utilize hand-crafted sharing strategies that…

Machine Learning · Computer Science 2022-03-17 Bryan A. Plummer , Nikoli Dryden , Julius Frost , Torsten Hoefler , Kate Saenko

Deep learning methods have been successful in solving tasks in machine learning and have made breakthroughs in many sectors owing to their ability to automatically extract features from unstructured data. However, their performance relies…

Machine Learning · Computer Science 2022-03-18 Viet-Khoa Vo-Ho , Kashu Yamazaki , Hieu Hoang , Minh-Triet Tran , Ngan Le

Recently, dynamic inference has emerged as a promising way to reduce the computational cost of deep convolutional neural network (CNN). In contrast to static methods (e.g. weight pruning), dynamic inference adaptively adjusts the inference…

Computer Vision and Pattern Recognition · Computer Science 2019-12-18 Zhihang Yuan , Bingzhe Wu , Zheng Liang , Shiwan Zhao , Weichen Bi , Guangyu Sun

Deep neural networks have recently drawn considerable attention to build and evaluate artificial learning models for perceptual tasks. Here, we present a study on the performance of the deep learning models to deal with global optimization…

Neural and Evolutionary Computing · Computer Science 2020-12-18 Hojjat Rakhshani , Lhassane Idoumghar , Soheila Ghambari , Julien Lepagnot , Mathieu Brévilliers

Resource is an important constraint when deploying Deep Neural Networks (DNNs) on mobile and edge devices. Existing works commonly adopt the cell-based search approach, which limits the flexibility of network patterns in learned cell…

Machine Learning · Computer Science 2020-03-04 Tunhou Zhang , Hsin-Pai Cheng , Zhenwen Li , Feng Yan , Chengyu Huang , Hai Li , Yiran Chen

Recent works show that convolutional neural network (CNN) architectures have a spectral bias towards lower frequencies, which has been leveraged for various image restoration tasks in the Deep Image Prior (DIP) framework. The benefit of the…

Computer Vision and Pattern Recognition · Computer Science 2022-03-31 Metin Ersin Arican , Ozgur Kara , Gustav Bredell , Ender Konukoglu

Existing optical flow estimators usually employ the network architectures typically designed for image classification as the encoder to extract per-pixel features. However, due to the natural difference between the tasks, the architectures…

Computer Vision and Pattern Recognition · Computer Science 2022-07-05 Zhiwei Lin , Tingting Liang , Taihong Xiao , Yongtao Wang , Zhi Tang , Ming-Hsuan Yang

Training CNN for detection is time-consuming due to the large dataset and complex network modules, making it hard to search architectures on detection datasets directly, which usually requires vast search costs (usually tens and even…

Computer Vision and Pattern Recognition · Computer Science 2022-03-22 Xiaoxing Wang , Jiale Lin , Junchi Yan , Juanping Zhao , Xiaokang Yang

Deep learning has revolutionized computer vision, but it achieved its tremendous success using deep network architectures which are mostly hand-crafted and therefore likely suboptimal. Neural Architecture Search (NAS) aims to bridge this…

Computer Vision and Pattern Recognition · Computer Science 2025-02-10 Ondřej Týbl , Lukáš Neumann