DCNAS: Densely Connected Neural Architecture Search for Semantic Image Segmentation
Authors:
- 1 June 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 13951-13962
Abstract
Existing NAS methods for dense image prediction tasks usually compromise on restricted search space or search on proxy task to meet the achievable computational demands. To allow as wide as possible network architectures and avoid the gap between realistic and proxy setting, we propose a novel Densely Connected NAS (DCNAS) framework, which directly searches the optimal network structures for the multi-scale representations of visual information, over a large-scale target dataset without proxy. Specifically, by connecting cells with each other using learnable weights, we introduce a densely connected search space to cover an abundance of mainstream network designs. Moreover, by combining both path-level and channel-level sampling strategies, we design a fusion module and mixture layer to reduce the memory consumption of ample search space, hence favoring the proxyless searching. Compared with contemporary works, experiments reveal that the proxyless searching scheme is capable of bridging the gap between searching and training environments. Further, DCNAS achieves new state-of-the-art performances on public semantic image segmentation benchmarks, including 84.3% on Cityscapes, and 86.9% on PASCAL VOC 2012. We also retain leading performances when evaluating the architecture on the more challenging ADE20K and PASCAL-Context dataset.Keywords
All Related Versions
This publication has 48 references indexed in Scilit:
- A genetic programming approach to designing convolutional neural network architectures2017
- Full-Resolution Residual Networks for Semantic Segmentation in Street Scenes2017
- Scene Parsing through ADE20K Dataset2017
- Pyramid Scene Parsing Network2017
- The Cityscapes Dataset for Semantic Urban Scene Understanding2016
- Efficient Piecewise Training of Deep Structured Models for Semantic Segmentation2016
- Attention to Scale: Scale-Aware Semantic Image Segmentation2016
- Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-scale Convolutional Architecture2015
- Fully convolutional networks for semantic segmentation2015
- The Role of Context for Object Detection and Semantic Segmentation in the Wild2014