DeepAI AI Chat
Log In Sign Up

Design of Real-time Semantic Segmentation Decoder for Automated Driving

by   Arindam Das, et al.

Semantic segmentation remains a computationally intensive algorithm for embedded deployment even with the rapid growth of computation power. Thus efficient network design is a critical aspect especially for applications like automated driving which requires real-time performance. Recently, there has been a lot of research on designing efficient encoders that are mostly task agnostic. Unlike image classification and bounding box object detection tasks, decoders are computationally expensive as well for semantic segmentation task. In this work, we focus on efficient design of the segmentation decoder and assume that an efficient encoder is already designed to provide shared features for a multi-task learning system. We design a novel efficient non-bottleneck layer and a family of decoders which fit into a small run-time budget using VGG10 as efficient encoder. We demonstrate in our dataset that experimentation with various design choices led to an improvement of 10% from a baseline performance.


page 3

page 5


Real-time Joint Object Detection and Semantic Segmentation Network for Automated Driving

Convolutional Neural Networks (CNN) are successfully used for various vi...

FisheyeMultiNet: Real-time Multi-task Learning Architecture for Surround-view Automated Parking System

Automated Parking is a low speed manoeuvring scenario which is quite uns...

Efficient Semantic Segmentation using Gradual Grouping

Deep CNNs for semantic segmentation have high memory and run time requir...

FADE: Fusing the Assets of Decoder and Encoder for Task-Agnostic Upsampling

We consider the problem of task-agnostic feature upsampling in dense pre...

Multi-stream CNN based Video Semantic Segmentation for Automated Driving

Majority of semantic segmentation algorithms operate on a single frame e...

Multi-Task Network Pruning and Embedded Optimization for Real-time Deployment in ADAS

Camera-based Deep Learning algorithms are increasingly needed for percep...

TiledSoilingNet: Tile-level Soiling Detection on Automotive Surround-view Cameras Using Coverage Metric

Automotive cameras, particularly surround-view cameras, tend to get soil...