English
Related papers

Related papers: Once-for-All: Train One Network and Specialize it …

200 papers

Once-for-All (OFA) is a Neural Architecture Search (NAS) framework designed to address the problem of searching efficient architectures for devices with different resources constraints by decoupling the training and the searching stages.…

Neural and Evolutionary Computing · Computer Science 2023-03-27 Rafael C. Ito , Fernando J. Von Zuben

Deploying Deep Neural Networks (DNNs) on different hardware platforms is challenging due to varying resource constraints. Besides handcrafted approaches aiming at making deep models hardware-friendly, Neural Architectures Search is rising…

Machine Learning · Computer Science 2024-09-11 Maxime Girard , Victor Quétu , Samuel Tardieu , Van-Tam Nguyen , Enzo Tartaglione

The use of Neural Architecture Search (NAS) techniques to automate the design of neural networks has become increasingly popular in recent years. The proliferation of devices with different hardware characteristics using such neural…

Machine Learning · Computer Science 2023-02-06 Simone Sarti , Eugenio Lomurno , Andrea Falanti , Matteo Matteucci

Neural Architecture Search has proven an effective method of automating architecture engineering. Recent work in the field has been to look for architectures subject to multiple objectives such as accuracy and latency to efficiently deploy…

Machine Learning · Computer Science 2020-12-15 Vidhur Kumar , Andrew Szidon

The emergence of CNNs in mainstream deployment has necessitated methods to design and train efficient architectures tailored to maximize the accuracy under diverse hardware & latency constraints. To scale these resource-intensive tasks with…

Computer Vision and Pattern Recognition · Computer Science 2021-04-27 Manas Sahni , Shreya Varshini , Alind Khare , Alexey Tumanov

Neural Architecture Search (NAS) has enabled the possibility of automated machine learning by streamlining the manual development of deep neural network architectures defining a search space, search strategy, and performance estimation…

Machine Learning · Computer Science 2021-01-05 Muhtadyuzzaman Syed , Arvind Akpuram Srinivasan

Weight-sharing neural architecture search aims to optimize a configurable neural network model (supernet) for a variety of deployment scenarios across many devices with different resource constraints. Existing approaches use evolutionary…

Machine Learning · Computer Science 2023-07-04 Achintya Kundu , Laura Wynter , Rhui Dih Lee , Luis Angel Bathen

The Once-For-All (OFA) method offers an excellent pathway to deploy a trained neural network model into multiple target platforms by utilising the supernet-subnet architecture. Once trained, a subnet can be derived from the supernet (both…

Machine Learning · Computer Science 2022-04-21 Jordan Shipard , Arnold Wiliem , Clinton Fookes

We address the challenge of training a large supernet for the object detection task, using a relatively small amount of training data. Specifically, we propose an efficient supernet-based neural architecture search (NAS) method that uses…

Computer Vision and Pattern Recognition · Computer Science 2023-10-20 Yuiko Sakuma , Masato Ishii , Takuya Narihira

We propose an efficient once-for-all budgeted pruning framework (OFARPruning) to find many compact network structures close to winner tickets in the early training stage considering the effect of input resolution during the pruning process.…

Computer Vision and Pattern Recognition · Computer Science 2020-12-03 Wenyu Sun , Jian Cao , Pengtao Xu , Xiangcheng Liu , Pu Li

Current techniques for deep neural network (DNN) pruning often involve intricate multi-step processes that require domain-specific expertise, making their widespread adoption challenging. To address the limitation, the Only-Train-Once (OTO)…

Computer Vision and Pattern Recognition · Computer Science 2024-03-25 Xidong Wu , Shangqian Gao , Zeyu Zhang , Zhenzhen Li , Runxue Bao , Yanfu Zhang , Xiaoqian Wang , Heng Huang

Designing a single model to address multiple tasks has been a long-standing objective in artificial intelligence. Recently, large language models have demonstrated exceptional capability in solving different tasks within the language…

Machine Learning · Computer Science 2024-07-16 Hao Liu , Jiarui Feng , Lecheng Kong , Ningyue Liang , Dacheng Tao , Yixin Chen , Muhan Zhang

Foundation models characterized by extensive parameters and trained on large-scale datasets have demonstrated remarkable efficacy across various downstream tasks for remote sensing data. Current remote sensing foundation models typically…

Computer Vision and Pattern Recognition · Computer Science 2024-05-29 Zhitong Xiong , Yi Wang , Fahong Zhang , Xiao Xiang Zhu

Mobile and embedded platforms are increasingly required to efficiently execute computationally demanding DNNs across heterogeneous processing elements. At runtime, the available hardware resources to DNNs can vary considerably due to other…

Computer Vision and Pattern Recognition · Computer Science 2021-05-12 Wei Lou , Lei Xun , Amin Sabet , Jia Bi , Jonathon Hare , Geoff V. Merrett

Multimodal instruction tuning is the de facto recipe for adapting vision language models (VLMs), yet instruction data are highly redundant, making data selection critical for training efficiency. Existing methods derive selection signals…

Computer Vision and Pattern Recognition · Computer Science 2026-05-27 Mingkang Dong , Hongyi Cai , Xiwen Lei , Jie Li , Tao Zhang , Muxin Pu

Large Language Models (LLMs) have advanced rapidly but face significant memory demands. While quantization has shown promise for LLMs, current methods typically require lengthy training to alleviate the performance degradation from…

Artificial Intelligence · Computer Science 2024-05-31 Ke Yi , Yuhui Xu , Heng Chang , Chen Tang , Yuan Meng , Tong Zhang , Jia Li

In this work, we pursue a unified paradigm for multimodal pretraining to break the scaffolds of complex task/modality-specific customization. We propose OFA, a Task-Agnostic and Modality-Agnostic framework that supports Task…

Computer Vision and Pattern Recognition · Computer Science 2022-06-02 Peng Wang , An Yang , Rui Men , Junyang Lin , Shuai Bai , Zhikang Li , Jianxin Ma , Chang Zhou , Jingren Zhou , Hongxia Yang

Structured pruning is a commonly used technique in deploying deep neural networks (DNNs) onto resource-constrained devices. However, the existing pruning methods are usually heuristic, task-specified, and require an extra fine-tuning…

Machine Learning · Computer Science 2021-11-15 Tianyi Chen , Bo Ji , Tianyu Ding , Biyi Fang , Guanyi Wang , Zhihui Zhu , Luming Liang , Yixin Shi , Sheng Yi , Xiao Tu

Once-for-All (OFA) training enables a single super-net to generate multiple sub-nets tailored to diverse deployment scenarios, supporting flexible trade-offs among accuracy, robustness, and model-size without retraining. However, as the…

Machine Learning · Computer Science 2025-09-23 Shaharyar Ahmed Khan Tareen , Lei Fan , Xiaojing Yuan , Qin Lin , Bin Hu

Acoustic Event Classification (AEC) has been widely used in devices such as smart speakers and mobile phones for home safety or accessibility support. As AEC models run on more and more devices with diverse computation resource constraints,…

Sound · Computer Science 2023-03-21 Guan-Ting Lin , Qingming Tang , Chieh-Chi Kao , Viktor Rozgic , Chao Wang
‹ Prev 1 2 3 10 Next ›