paper-with-me

Papers

Prioritized Subnet Sampling for Resource-Adaptive Supernet Training

2021-09-12 · Bohong Chen, Mingbao Lin, Rongrong Ji, Liujuan Cao

A resource-adaptive supernet adjusts its subnets for inference to fit the dynamically available resources. In this paper, we propose prioritized subnet sampling to train a resource-adaptive supernet, termed PSS-Net. We maintain multiple subnet pools, each of which stores the information of substantial subnets with similar resource consumption. Considering a resource constraint, subnets conditioned on this resource constraint are sampled from a pre-defined subnet structure space and high-quality ones will be inserted into the corresponding subnet pool. Then, the sampling will gradually be prone to sampling subnets from the subnet pools. Moreover, the one with a better performance metric is assigned with higher priority to train our PSS-Net, if sampling is from a subnet pool. At the end of training, our PSS-Net retains the best subnet in each pool to entitle a fast switch of high-quality subnets for inference when the available resources vary. Experiments on ImageNet using MobileNet-V1/V2 and ResNet-50 show that our PSS-Net can well outperform state-of-the-art resource-adaptive supernets. Our project is publicly available at https://github.com/chenbong/PSS-Net.

📄 PDF Abstract BibTeX arXiv:2109.05432

Code (1)

chenbong/PSS-Net 공식 구현 pytorch

Similar Papers 제목 키워드 기반

PSE-Net: Channel Pruning for Convolutional Neural Networks with Parallel-subnets Estimator

2024-08-29 · Shiguang Wang, Tao Xie, Haijun Liu, Xingcheng Zhang 외

Channel Pruning is one of the most widespread techniques used to compress deep neural networks while maintaining their performances. Currently, a typical pruning algorithm leverages neural architecture search to directly…

Neural Architecture Search

Subnet-Aware Dynamic Supernet Training for Neural Architecture Search

2025-03-13 · CVPR 2025 1 · Jeimin Jeon, Youngmin Oh, Junghyup Lee, Donghyeon Baek 외

N-shot neural architecture search (NAS) exploits a supernet containing all candidate subnets for a given search space. The subnets are typically trained with a static training strategy (e.g., using the same learning rate…

Neural Architecture Search

ElasticViT: Conflict-aware Supernet Training for Deploying Fast Vision Transformer on Diverse Mobile Devices

2023-03-17 · ICCV 2023 1 · Chen Tang, Li Lyna Zhang, Huiqiang Jiang, Jiahang Xu 외

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 devic…

Neural Architecture Search

Efficient Few-Shot Neural Architecture Search by Counting the Number of Nonlinear Functions

2024-12-19 · Youngmin Oh, Hyunju Lee, Bumsub Ham

Neural architecture search (NAS) enables finding the best-performing architecture from a search space automatically. Most NAS methods exploit an over-parameterized network (i.e., a supernet) containing all possible archi…

Neural Architecture Search

ADDS: Adaptive Differentiable Sampling for Robust Multi-Party Learning

2021-10-29 · Maoguo Gong, Yuan Gao, Yue Wu, A. K. Qin

Distributed multi-party learning provides an effective approach for training a joint model with scattered data under legal and practical constraints. However, due to the quagmire of a skewed distribution of data labels a…