DCNAS: Densely Connected Neural Architecture Search for Semantic Image Segmentation

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 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.

arXiv commentaccepted by CVPR 2021

References in corpus (15)

• Rethinking Atrous Convolution for Semantic Image Segmentation
• Neural Architecture Search with Reinforcement Learning
• DARTS: Differentiable Architecture Search
• ParseNet: Looking Wider to See Better
• DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
• Learning Deconvolution Network for Semantic Segmentation
• Efficient Neural Architecture Search via Parameter Sharing
• Large-Scale Evolution of Image Classifiers
• Designing Neural Network Architectures using Reinforcement Learning
• Deep High-Resolution Representation Learning for Visual Recognition
• Searching for Efficient Multi-Scale Architectures for Dense Image Prediction
• Semantic Image Segmentation via Deep Parsing Network
• FasterSeg: Searching for Faster Real-time Semantic Segmentation
• Joint Semantic Segmentation and Boundary Detection using Iterative Pyramid Contexts
• Auto-Panoptic: Cooperative Multi-Component Architecture Search for Panoptic Segmentation

Cited by in corpus (6)

• A Survey on Deep Learning-based Architectures for Semantic Segmentation on 2D images
• A Comprehensive Review of Modern Object Segmentation Approaches
• Weight-Sharing Neural Architecture Search: A Battle to Shrink the Optimization Gap
• Learning Versatile Neural Architectures by Propagating Network Codes
• HR-NAS: Searching Efficient High-Resolution Neural Architectures with Lightweight Transformers
• Edge-Preserving Guided Semantic Segmentation for VIPriors Challenge