NeurAll: 自動運転のための統合視覚認識モデルに向けて
NeurAll: Towards a Unified Visual Perception Model for Automated Driving
自動運転の複数の視覚認識タスクを、初期畳み込み層を共有するマルチタスクCNNで統合的に学習し、計算効率と精度向上を目指した研究。
著者: Ganesh Sistu, Isabelle Leang, Sumanth Chennupati, Senthil Yogamani, Ciaran Hughes, Stefan Milz, Samir Rawashdeh
分類: cs.CV, cs.LG, cs.RO, stat.ML
原文アブストラクト
Convolutional Neural Networks (CNNs) are successfully used for the important automotive visual perception tasks including object recognition, motion and depth estimation, visual SLAM, etc. However, these tasks are typically independently explored and modeled. In this paper, we propose a joint multi-task network design for learning several tasks simultaneously. Our main motivation is the computational efficiency achieved by sharing the expensive initial convolutional layers between all tasks. Indeed, the main bottleneck in automated driving systems is the limited processing power available on deployment hardware. There is also some evidence for other benefits in improving accuracy for some tasks and easing development effort. It also offers scalability to add more tasks leveraging existing features and achieving better generalization. We survey various CNN based solutions for visual perception tasks in automated driving. Then we propose a unified CNN model for the important tasks and discuss several advanced optimization and architecture design techniques to improve the baseline model. The paper is partly review and partly positional with demonstration of several preliminary results promising for future research. We first demonstrate results of multi-stream learning and auxiliary learning which are important ingredients to scale to a large multi-task model. Finally, we implement a two-stream three-task network which performs better in many cases compared to their corresponding single-task models, while maintaining network size.
