English
Related papers

Related papers: AlphaNet: Improved Training of Supernets with Alph…

200 papers

Neural architecture search (NAS) has shown great promise in automatically designing lightweight models. However, conventional approaches are insufficient in training the supernet and pay little attention to actual robot hardware resources.…

Robotics · Computer Science 2025-09-26 Shouren Mao , Minghao Qin , Wei Dong , Huajian Liu , Yongzhuo Gao

Training a supernet matters for one-shot neural architecture search (NAS) methods since it serves as a basic performance estimator for different architectures (paths). Current methods mainly hold the assumption that a supernet should give a…

Computer Vision and Pattern Recognition · Computer Science 2020-03-26 Shan You , Tao Huang , Mingmin Yang , Fei Wang , Chen Qian , Changshui Zhang

Weight sharing is a fundamental concept in neural architecture search (NAS), enabling gradient-based methods to explore cell-based architectural spaces significantly faster than traditional black-box approaches. In parallel,…

Machine Learning · Computer Science 2025-11-11 Rhea Sanjay Sukthanker , Arjun Krishnakumar , Mahmoud Safari , Frank Hutter

Binary Neural Networks (BNNs) have gained extensive attention for their superior inferencing efficiency and compression ratio compared to traditional full-precision networks. However, due to the unique characteristics of BNNs, designing a…

Computer Vision and Pattern Recognition · Computer Science 2024-08-29 Zhihao Lin , Yongtao Wang , Jinhe Zhang , Xiaojie Chu , Haibin Ling

Recently, self-attention operators have shown superior performance as a stand-alone building block for vision models. However, existing self-attention models are often hand-designed, modified from CNNs, and obtained by stacking one operator…

Computer Vision and Pattern Recognition · Computer Science 2021-11-16 Huaijin Pi , Huiyu Wang , Yingwei Li , Zizhang Li , Alan Yuille

Designing complex architectures has been an essential cogwheel in the revolution deep learning has brought about in the past decade. When solving difficult problems in a datadriven manner, a well-tried approach is to take an architecture…

Machine Learning · Computer Science 2021-10-14 Attila Nagy , Ábel Boros

This paper proposes a novel differentiable architecture search method by formulating it into a distribution learning problem. We treat the continuously relaxed architecture mixing weight as random variables, modeled by Dirichlet…

Machine Learning · Computer Science 2021-03-17 Xiangning Chen , Ruochen Wang , Minhao Cheng , Xiaocheng Tang , Cho-Jui Hsieh

Weight sharing promises to make neural architecture search (NAS) tractable even on commodity hardware. Existing methods in this space rely on a diverse set of heuristics to design and train the shared-weight backbone network, a.k.a. the…

Machine Learning · Computer Science 2020-06-18 Kaicheng Yu , Rene Ranftl , Mathieu Salzmann

Neural Architecture Search (NAS) is a powerful tool to automatically design deep neural networks for many tasks, including image classification. Due to the significant computational burden of the search phase, most NAS methods have focused…

Emerged as a biology-inspired method, Spiking Neural Networks (SNNs) mimic the spiking nature of brain neurons and have received lots of research attention. SNNs deal with binary spikes as their activation and therefore derive extreme…

Computer Vision and Pattern Recognition · Computer Science 2023-05-04 Yufei Guo , Weihang Peng , Yuanpei Chen , Liwen Zhang , Xiaode Liu , Xuhui Huang , Zhe Ma

In the past few years, neural architecture search (NAS) has become an increasingly important tool within the deep learning community. Despite the many recent successes of NAS, however, most existing approaches operate within highly…

Machine Learning · Computer Science 2022-11-14 Charles Jin , Phitchaya Mangpo Phothilimthana , Sudip Roy

Differential Neural Architecture Search (NAS) requires all layer choices to be held in memory simultaneously; this limits the size of both search space and final architecture. In contrast, Probabilistic NAS, such as PARSEC, learns a…

Computer Vision and Pattern Recognition · Computer Science 2021-04-01 Zhicheng Yan , Xiaoliang Dai , Peizhao Zhang , Yuandong Tian , Bichen Wu , Matt Feiszli

In few-shot recognition, a classifier that has been trained on one set of classes is required to rapidly adapt and generalize to a disjoint, novel set of classes. To that end, recent studies have shown the efficacy of fine-tuning with…

Computer Vision and Pattern Recognition · Computer Science 2023-06-16 Panagiotis Eustratiadis , Łukasz Dudziak , Da Li , Timothy Hospedales

Multiplication-less neural networks significantly reduce the time and energy cost on the hardware platform, as the compute-intensive multiplications are replaced with lightweight bit-shift operations. However, existing bit-shift networks…

Machine Learning · Computer Science 2022-04-12 Xiaoxuan Lou , Guowen Xu , Kangjie Chen , Guanlin Li , Jiwei Li , Tianwei Zhang

Neural architecture search (NAS) relies on a good controller to generate better architectures or predict the accuracy of given architectures. However, training the controller requires both abundant and high-quality pairs of architectures…

Machine Learning · Computer Science 2020-11-04 Renqian Luo , Xu Tan , Rui Wang , Tao Qin , Enhong Chen , Tie-Yan Liu

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

Neural Architecture Search (NAS) has shown promising performance in the automatic design of vision transformers (ViT) exceeding 1G FLOPs. However, designing lightweight and low-latency ViT models for diverse mobile devices remains a big…

Computer Vision and Pattern Recognition · Computer Science 2023-03-22 Chen Tang , Li Lyna Zhang , Huiqiang Jiang , Jiahang Xu , Ting Cao , Quanlu Zhang , Yuqing Yang , Zhi Wang , Mao Yang

In one-shot weight sharing for NAS, the weights of each operation (at each layer) are supposed to be identical for all architectures (paths) in the supernet. However, this rules out the possibility of adjusting operation weights to cater…

Computer Vision and Pattern Recognition · Computer Science 2021-06-14 Xiu Su , Shan You , Mingkai Zheng , Fei Wang , Chen Qian , Changshui Zhang , Chang Xu

Knowledge distillation (KD) methods compress large models into smaller students with manually-designed student architectures given pre-specified computational cost. This requires several trials to find a viable student, and further…

Computation and Language · Computer Science 2022-02-22 Dongkuan Xu , Subhabrata Mukherjee , Xiaodong Liu , Debadeepta Dey , Wenhui Wang , Xiang Zhang , Ahmed Hassan Awadallah , Jianfeng Gao

Diffusion models have recently shown remarkable generation ability, achieving state-of-the-art performance in many tasks. However, the high computational cost is still a troubling problem for diffusion models. To tackle this problem, we…

Computer Vision and Pattern Recognition · Computer Science 2023-11-17 Siao Tang , Xin Wang , Hong Chen , Chaoyu Guan , Yansong Tang , Wenwu zhu