【学术报告】Fast Neural Architecture Search of Compact Semantic Segmentation Models

发布者:沈如达发布时间:2019-01-15浏览次数:229

报告题目:Fast Neural Architecture Search of Compact Semantic Segmentation Models 
报告人:沈春华教授 澳大利亚阿德莱德大学计算机科学学院
报告地点:无线谷A5楼5216会议室
报告时间:1月16日14:30-15:30

报告摘要:

Automated design of neural network architectures tailored for a specific task is an extremely promising, albeit inherently difficult, avenue to explore. While most results in this domain have been achieved on image classification and language modelling problems, here we concentrate on dense per-pixel tasks, in particular, semantic image segmentation using fully convolutional networks. In contrast to the aforementioned areas, the design choices of a fully convolutional network require several changes, ranging from the sort of operations that need to be used - e.g., dilated convolutions - to a solving of a more difficult optimisation problem. In this work, we are particularly interested in searching for high-performance compact segmentation architectures, able to run in real-time using limited resources. To achieve that, we intentionally over-parameterise the architecture during the training time via a set of auxiliary cells that provide an intermediate supervisory signal and can be omitted during the evaluation phase. The design of the auxiliary cell is emitted by a controller, a neural network with the fixed structure trained using reinforcement learning. More crucially, we demonstrate how to efficiently search for these architectures within limited time and computational budgets. In particular, we rely on a progressive strategy that terminates non-promising architectures from being further trained, and on Polyak averaging coupled with knowledge distillation to speed-up the convergence. Quantitatively, in 8 GPU-days our approach discovers a set of architectures performing on-par with state-of-the-art among compact models on the semantic segmentation, pose estimation and depth prediction tasks.


报告人简介:

沈春华博士现任澳大利亚阿德莱德大学计算机科学学院教授。 2011之前在澳大利亚国家信息通讯技术研究院堪培拉实验室的计算机视觉组工作近6年。 目前主要从事统计机器学习以及计算机视觉领域的研究工作。 主持多项科研课题,在重要国际学术期刊和会议发表论文220余篇。 担任或担任过副主编的期刊包括:Pattern Recognition, IEEE Transactions on Neural Networks and Learning Systems。多次担任重要国际学术会议(ICCV, CVPR, ECCV等)程序委员。 他曾在南京大学(本科及硕士),澳大利亚国立大学(硕士)学习,并在阿德莱德大学获得计算机视觉方向的博士学位。 沈春华教授曾获得AR C Future Fellowship,教育部长江****等荣誉。