CVJul 26, 2019

DABNet: Depth-wise Asymmetric Bottleneck for Real-time Semantic Segmentation

arXiv:1907.11357v2270 citations
Originality Incremental advance
AI Analysis

This addresses the need for efficient real-time segmentation in autonomous systems and robots, offering an incremental improvement in balancing performance and speed.

The paper tackles the trade-off between accuracy and speed in semantic segmentation by proposing DABNet, which achieves 70.1% Mean IoU on Cityscapes with 0.76 million parameters and 104 FPS on a GTX 1080Ti.

As a pixel-level prediction task, semantic segmentation needs large computational cost with enormous parameters to obtain high performance. Recently, due to the increasing demand for autonomous systems and robots, it is significant to make a tradeoff between accuracy and inference speed. In this paper, we propose a novel Depthwise Asymmetric Bottleneck (DAB) module to address this dilemma, which efficiently adopts depth-wise asymmetric convolution and dilated convolution to build a bottleneck structure. Based on the DAB module, we design a Depth-wise Asymmetric Bottleneck Network (DABNet) especially for real-time semantic segmentation, which creates sufficient receptive field and densely utilizes the contextual information. Experiments on Cityscapes and CamVid datasets demonstrate that the proposed DABNet achieves a balance between speed and precision. Specifically, without any pretrained model and postprocessing, it achieves 70.1% Mean IoU on the Cityscapes test dataset with only 0.76 million parameters and a speed of 104 FPS on a single GTX 1080Ti card.

Code Implementations3 repos
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes