AuxNet: Auxiliary tasks enhanced Semantic Segmentation for Automated Driving

Abstract

Decision making in automated driving is highly specific to the environment and thus semantic segmentation plays a key role in recognizing the objects in the environment around the car. Pixel level classification once considered a challenging task which is now becoming mature to be productized in a car. However, semantic annotation is time consuming and quite expensive. Synthetic datasets with domain adaptation techniques have been used to alleviate the lack of large annotated datasets. In this work, we explore an alternate approach of leveraging the annotations of other tasks to improve semantic segmentation. Recently, multi-task learning became a popular paradigm in automated driving which demonstrates joint learning of multiple tasks improves overall performance of each tasks. Motivated by this, we use auxiliary tasks like depth estimation to improve the performance of semantic segmentation task. We propose adaptive task loss weighting techniques to address scale issues in multi-task loss functions which become more crucial in auxiliary tasks. We experimented on automotive datasets including SYNTHIA and KITTI and obtained 3% and 5% improvement in accuracy respectively.

arXiv commentAccepted as a Short Paper for a poster presentation at VISAPP 2019

References in corpus (11)

• Adam: A Method for Stochastic Optimization
• Fully Convolutional Networks for Semantic Segmentation
• An Overview of Multi-Task Learning in Deep Neural Networks
• GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks
• Virtual Worlds as Proxy for Multi-Object Tracking Analysis
• Auxiliary Tasks in Multi-task Learning
• Synscapes: A Photorealistic Synthetic Dataset for Street Scene Parsing
• Analyzing Modular CNN Architectures for Joint Depth Prediction and Semantic Segmentation
• Driving Scene Perception Network: Real-time Joint Detection, Depth Estimation and Semantic Segmentation
• Fast Scene Understanding for Autonomous Driving
• End-to-End Multi-Task Learning with Attention

Cited by in corpus (4)

• MobTCast: Leveraging Auxiliary Trajectory Forecasting for Human Mobility Prediction
• FisheyeMultiNet: Real-time Multi-task Learning Architecture for Surround-view Automated Parking System
• Adaptive Distillation: Aggregating Knowledge from Multiple Paths for Efficient Distillation
• Fast Line Search for Multi-Task Learning