DCNAS: Densely Connected Neural Architecture Search for Semantic Image Segmentation

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.

PDF Abstract CVPR 2021 PDF CVPR 2021 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Semantic Segmentation ADE20K val DCNAS mIoU 47.12 # 44
Semantic Segmentation Cityscapes test DCNAS Mean IoU (class) 83.6% # 7
Semantic Segmentation PASCAL Context DCNAS mIoU 55.6 # 18
Semantic Segmentation PASCAL VOC 2012 test DCNAS Mean IoU 86.9% # 10


No methods listed for this paper. Add relevant methods here