Dilated SpineNet for Semantic Segmentation

23 Mar 2021  ·  Abdullah Rashwan, Xianzhi Du, Xiaoqi Yin, Jing Li ·

Scale-permuted networks have shown promising results on object bounding box detection and instance segmentation. Scale permutation and cross-scale fusion of features enable the network to capture multi-scale semantics while preserving spatial resolution. In this work, we evaluate this meta-architecture design on semantic segmentation - another vision task that benefits from high spatial resolution and multi-scale feature fusion at different network stages. By further leveraging dilated convolution operations, we propose SpineNet-Seg, a network discovered by NAS that is searched from the DeepLabv3 system. SpineNet-Seg is designed with a better scale-permuted network topology with customized dilation ratios per block on a semantic segmentation task. SpineNet-Seg models outperform the DeepLabv3/v3+ baselines at all model scales on multiple popular benchmarks in speed and accuracy. In particular, our SpineNet-S143+ model achieves the new state-of-the-art on the popular Cityscapes benchmark at 83.04% mIoU and attained strong performance on the PASCAL VOC2012 benchmark at 85.56% mIoU. SpineNet-Seg models also show promising results on a challenging Street View segmentation dataset. Code and checkpoints will be open-sourced.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Semantic Segmentation Cityscapes val SpineNet-S143+ (single-scale test) mIoU 83.04% # 11
Semantic Segmentation PASCAL VOC 2012 val SpineNet-S143 (single-scale test) mIoU 85.64% # 4