DCNAS: Densely Connected Neural Architecture Search for Semantic Image Segmentation
Authors:
Preprint
Abstract
Neural Architecture Search (NAS) has shown great potentials in automatically designing scalable network architectures for dense image predictions. However, existing NAS algorithms usually compromise on restricted search space and search on proxy task to meet the achievable computational demands. To allow as wide as possible network architectures and avoid the gap between target and proxy dataset, we propose a 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. 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 to reduce the memory consumption of ample search space. We demonstrate that the architecture obtained from our DCNAS algorithm achieves state-of-the-art performances on public semantic image segmentation benchmarks, including 83.6% on Cityscapes, and 86.9% on PASCAL VOC 2012 (track w/o additional data). 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 7 references indexed in Scilit:
- Densely Connected Search Space for More Flexible Neural Architecture Search2020
- Searching for MobileNetV32019
- Wider or Deeper: Revisiting the ResNet Model for Visual RecognitionPattern Recognition, 2019
- Stacked Deconvolutional Network for Semantic SegmentationIEEE Transactions on Image Processing, 2019
- Dense Relation Network: Learning Consistent and Context-Aware Representation for Semantic Image Segmentation2018
- DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2017
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009