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

Abstract

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.

arXiv commentAccepted to BMVC 2019

References in corpus (6)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• Rethinking Atrous Convolution for Semantic Image Segmentation
• Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
• ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation
• ContextNet: Exploring Context and Detail for Semantic Segmentation in Real-time

Cited by in corpus (21)

• ABCNet: Attentive Bilateral Contextual Network for Efficient Semantic Segmentation of Fine-Resolution Remote Sensing Images
• nnFormer: Interleaved Transformer for Volumetric Segmentation
• BiSeNet V2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentation
• Stage-Aware Feature Alignment Network for Real-Time Semantic Segmentation of Street Scenes
• Rethinking BiSeNet For Real-time Semantic Segmentation
• HAFormer: Unleashing the Power of Hierarchy-Aware Features for Lightweight Semantic Segmentation
• Segmenting Transparent Object in the Wild with Transformer
• AdaSpring: Context-adaptive and Runtime-evolutionary Deep Model Compression for Mobile Applications
• SegBlocks: Block-Based Dynamic Resolution Networks for Real-Time Segmentation
• CFPNet-M: A Light-Weight Encoder-Decoder Based Network for Multimodal Biomedical Image Real-Time Segmentation
• Highly Efficient Salient Object Detection with 100K Parameters
• Segmenting Transparent Objects in the Wild
• MSCFNet: A Lightweight Network With Multi-Scale Context Fusion for Real-Time Semantic Segmentation
• CFPNet: Channel-wise Feature Pyramid for Real-Time Semantic Segmentation
• FDDWNet: A Lightweight Convolutional Neural Network for Real-time Sementic Segmentation
• Predicting Terrain Mechanical Properties in Sight for Planetary Rovers with Semantic Clues
• RoadNet-RT: High Throughput CNN Architecture and SoC Design for Real-Time Road Segmentation
• Real-Time Semantic Segmentation via Auto Depth, Downsampling Joint Decision and Feature Aggregation
• Distilled Semantics for Comprehensive Scene Understanding from Videos
• AASeg: Attention Aware Network for Real Time Semantic Segmentation
• Dense Dual-Path Network for Real-time Semantic Segmentation