FNA++: Fast Network Adaptation via Parameter Remapping and Architecture Search
- 14 December 2020
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 43 (9) , 2990-3004
Abstract
Deep neural networks achieve remarkable performance in many computer vision tasks. Most state-of-the-art (SOTA) semantic segmentation and object detection approaches reuse neural network architectures designed for image classification as the backbone, commonly pre-trained on ImageNet. However, performance gains can be achieved by designing network architectures specifically for detection and segmentation, as shown by recent neural architecture search (NAS) research for detection and segmentation. One major challenge though is that ImageNet pre-training of the search space representation (a.k.a. super network) or the searched networks incurs huge computational cost. In this paper, we propose a Fast Network Adaptation (FNA++) method, which can adapt both the architecture and parameters of a seed network (e.g. an ImageNet pre-trained network) to become a network with different depths, widths, or kernel sizes via a parameter remapping technique, making it possible to use NAS for segmentation/detection tasks a lot more efficiently. In our experiments, we conduct FNA++ on MobileNetV2 to obtain new networks for semantic segmentation, object detection, and human pose estimation that clearly outperform existing networks designed both manually and by NAS. We also implement FNA++ on ResNets and NAS networks, which demonstrates a great generalization ability. FNA++ takes far less computation cost than other methods.Keywords
All Related Versions
Funding Information
- National Natural Science Foundation of China (61876212, 61733007)
- Zhejiang Lab (2019NB0AB02)
- HUST-Horizon Computer Vision Research Center
This publication has 22 references indexed in Scilit:
- BiSeNet: Bilateral Segmentation Network for Real-Time Semantic Segmentation2018
- Focal Loss for Dense Object Detection2017
- Densely Connected Convolutional Networks2017
- Deep Residual Learning for Image Recognition2016
- The Cityscapes Dataset for Semantic Urban Scene Understanding2016
- Rethinking the Inception Architecture for Computer Vision2016
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Fully convolutional networks for semantic segmentation2015
- 2D Human Pose Estimation: New Benchmark and State of the Art Analysis2014
- ImageNet: A large-scale hierarchical image database2009