Two-stage architectural fine-tuning with neural architecture search using early-stopping in image classification
Not on the map. Why?
Abstract (arXiv)
In many deep neural network (DNN) applications, the difficulty of gathering high-quality data in the industry field hinders the practical use of DNN. Thus, the concept of transfer learning has emerged, which leverages the pretrained knowledge of DNNs trained on large-scale datasets. Therefore, this paper suggests two-stage architectural fine-tuning, inspired by neural architecture search (NAS). One of main ideas is mutation, which reduces the search cost using given architectural information. Moreover, early-stopping is considered which cuts NAS costs by terminating the search process in advance. Experimental results verify our proposed method reduces 32.4% computational and 22.3% searching costs.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 19 of its 23 references that are in the map. First posted on arXiv 17 Feb 2022.
Builds on
19 of 23 references.
References · 19
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2013Playing Atari with Deep Reinforcement Learningcited by 3,211
- 2016Neural Architecture Search with Reinforcement Learningcited by 1,489
- 2015Learning Transferable Features with Deep Adaptation Networkscited by 1,323
- 2014How transferable are features in deep neural networks?cited by 1,216
- 2019A Comprehensive Survey on Transfer Learningcited by 1,154
- 2017Learning Transferable Architectures for Scalable Image Recognitioncited by 1,097
- 2018Efficient Neural Architecture Search via Parameter Sharingcited by 831
- 2018Do Better ImageNet Models Transfer Better?cited by 560
- 2017Understanding the Effective Receptive Field in Deep Convolutional Neural Networkscited by 549
- 2018Object Detection with Deep Learning: A Reviewcited by 524
- 2019Random Search and Reproducibility for Neural Architecture Searchcited by 253
7 more
- 2020Communication-Efficient and Distributed Learning Over Wireless Networks: Principles and Applicationscited by 62
- 2020Neural Architecture Transfercited by 59
- 2021Joint Superposition Coding and Training for Federated Learning over Multi-Width Neural Networkscited by 14
- 2021Boosting Deep Transfer Learning for COVID-19 Classificationcited by 4
- 2021Trends in Neural Architecture Search: Towards the Acceleration of Searchcited by 3
- 2021Efficient Transfer Learning via Joint Adaptation of Network Architecture and Weightcited by 1
- 2021Delay-Sensitive and Power-Efficient Quality Control of Dynamic Video Streaming using Adaptive Super-Resolutioncited by 1
Built on by
Citing papers per year: 2022: 1; 2023: 1.
2 papers.