Learning to Steer by Mimicking Features from Heterogeneous Auxiliary Networks

by   Yuenan Hou, et al.

The training of many existing end-to-end steering angle prediction models heavily relies on steering angles as the supervisory signal. Without learning from much richer contexts, these methods are susceptible to the presence of sharp road curves, challenging traffic conditions, strong shadows, and severe lighting changes. In this paper, we considerably improve the accuracy and robustness of predictions through heterogeneous auxiliary networks feature mimicking, a new and effective training method that provides us with much richer contextual signals apart from steering direction. Specifically, we train our steering angle predictive model by distilling multi-layer knowledge from multiple heterogeneous auxiliary networks that perform related but different tasks, e.g., image segmentation or optical flow estimation. As opposed to multi-task learning, our method does not require expensive annotations of related tasks on the target set. This is made possible by applying contemporary off-the-shelf networks on the target set and mimicking their features in different layers after transformation. The auxiliary networks are discarded after training without affecting the runtime efficiency of our model. Our approach achieves a new state-of-the-art on Udacity and Comma.ai, outperforming the previous best by a large margin of 12.8 Encouraging results are also shown on Berkeley Deep Drive (BDD) dataset.


Composite Learning for Robust and Effective Dense Predictions

Multi-task learning promises better model generalization on a target tas...

Improving End-to-End Text Image Translation From the Auxiliary Text Translation Task

End-to-end text image translation (TIT), which aims at translating the s...

Learning On-Road Visual Control for Self-Driving Vehicles with Auxiliary Tasks

A safe and robust on-road navigation system is a crucial component of ac...

MultiDepth: Single-Image Depth Estimation via Multi-Task Regression and Classification

We introduce MultiDepth, a novel training strategy and convolutional neu...

Learning Twofold Heterogeneous Multi-Task by Sharing Similar Convolution Kernel Pairs

Heterogeneous multi-task learning (HMTL) is an important topic in multi-...

Histogram of Oriented Gradients Meet Deep Learning: A Novel Multi-task Deep Network for Medical Image Semantic Segmentation

We present our novel deep multi-task learning method for medical image s...

Universal Neural-Cracking-Machines: Self-Configurable Password Models from Auxiliary Data

We develop the first universal password model – a password model that, o...

Please sign up or login with your details

Forgot password? Click here to reset