paper-with-me

Papers

FMAS: Fast Multi-Objective SuperNet Architecture Search for Semantic Segmentation

2023-03-28 · Zhuoran Xiong, Marihan Amein, Olivier Therrien, Warren J. Gross, Brett H. Meyer

We present FMAS, a fast multi-objective neural architecture search framework for semantic segmentation. FMAS subsamples the structure and pre-trained parameters of DeepLabV3+, without fine-tuning, dramatically reducing training time during search. To further reduce candidate evaluation time, we use a subset of the validation dataset during the search. Only the final, Pareto non-dominated, candidates are ultimately fine-tuned using the complete training set. We evaluate FMAS by searching for models that effectively trade accuracy and computational cost on the PASCAL VOC 2012 dataset. FMAS finds competitive designs quickly, e.g., taking just 0.5 GPU days to discover a DeepLabV3+ variant that reduces FLOPs and parameters by 10$\%$ and 20$\%$ respectively, for less than 3$\%$ increased error. We also search on an edge device called GAP8 and use its latency as the metric. FMAS is capable of finding 2.2$\times$ faster network with 7.61$\%$ MIoU loss.

📄 PDF Abstract BibTeX arXiv:2303.16322

Code (0)

등록된 구현이 없습니다.

Tasks

GPUNeural Architecture SearchSemantic Segmentation

Similar Papers 제목 키워드 기반

TRACE: Tensorizing and Generalizing Supernets from Neural Architecture Search

2021-01-01 · Hansi Yang, Quanming Yao

Recently, a special kind of graph, i.e., supernet, which allows two nodes connected by multi-choice edges, has exhibited its power in neural architecture search (NAS) by searching better architectures for computer vision…

Knowledge GraphsNeural Architecture Search

Efficient Differentiable Neural Architecture Search with Model Parallelism

2021-01-01 · Yi-Wei Chen, Qingquan Song, Xia Hu

Neural architecture search (NAS) automatically designs effective network architectures. Differentiable NAS with supernets that encompass all potential architectures in a large graph cuts down search overhead to few GPU d…

GPUmodelNeural Architecture Search

Mixture-of-Supernets: Improving Weight-Sharing Supernet Training with Architecture-Routed Mixture-of-Experts

2023-06-08 · Ganesh Jawahar, Haichuan Yang, Yunyang Xiong, Zechun Liu 외

Weight-sharing supernets are crucial for performance estimation in cutting-edge neural architecture search (NAS) frameworks. Despite their ability to generate diverse subnetworks without retraining, the quality of these …

Language ModelingLanguage ModellingMachine TranslationMixture-of-Experts+2

GreedyNAS: Towards Fast One-Shot NAS with Greedy Supernet

2020-03-25 · CVPR 2020 6 · Shan You, Tao Huang, Mingmin Yang, Fei Wang 외

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 su…

AllImage ClassificationNeural Architecture Search

Novelty Driven Evolutionary Neural Architecture Search

2022-04-01 · Nilotpal Sinha, Kuan-Wen Chen

Evolutionary algorithms (EA) based neural architecture search (NAS) involves evaluating each architecture by training it from scratch, which is extremely time-consuming. This can be reduced by using a supernet for estima…

Evolutionary AlgorithmsNeural Architecture Search