Bilateral Network with Residual U-blocks and Dual-Guided Attention for Real-time Semantic Segmentation
This work addresses real-time segmentation needs for applications like autonomous driving, but it is incremental as it builds on existing two-branch architectures.
The authors tackled the performance bottleneck in two-branch real-time semantic segmentation models by designing a new fusion mechanism using Dual-Guided Attention (DGA) modules, achieving competitive performance with near-linear complexity on Cityscapes and CamVid datasets.
When some application scenarios need to use semantic segmentation technology, like automatic driving, the primary concern comes to real-time performance rather than extremely high segmentation accuracy. To achieve a good trade-off between speed and accuracy, two-branch architecture has been proposed in recent years. It treats spatial information and semantics information separately which allows the model to be composed of two networks both not heavy. However, the process of fusing features with two different scales becomes a performance bottleneck for many nowaday two-branch models. In this research, we design a new fusion mechanism for two-branch architecture which is guided by attention computation. To be precise, we use the Dual-Guided Attention (DGA) module we proposed to replace some multi-scale transformations with the calculation of attention which means we only use several attention layers of near linear complexity to achieve performance comparable to frequently-used multi-layer fusion. To ensure that our module can be effective, we use Residual U-blocks (RSU) to build one of the two branches in our networks which aims to obtain better multi-scale features. Extensive experiments on Cityscapes and CamVid dataset show the effectiveness of our method.