RI:Small: Neural Architecture Search with Deep Compositional Grammatical Structures

RI:Small：具有深层组合语法结构的神经架构搜索

• 批准号: 1909644
• 负责人: Tianfu Wu
• 金额: $ 44.86万
• 依托单位: North Carolina State University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2019
• 资助国家: 美国
• 起止时间: 2019-08-01 至 2024-07-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1909644&HistoricalAwards=false
• 关键词: RI; Small; Neural; Architecture; Search

Artificial Intelligence (AI) technologies have recently shown great values in a wide range of applications such as self-driving cars, smart speaker, machine translation, robot autonomy and medical diagnosis. Computer vision (automatic analysis of images and videos) and natural language processing (automatic analysis of text) are two key pillars of AI. Deep learning artificial neural networks are the "brain" of many state-of-the-art AI systems in these two domains. However, much of the neural architectures are still hand-crafted to tailor to individual tasks in each domain, whereas learning in the human brains seems to be more task- and domain-agnostic. This project presents a principled framework to automatically learn neural architectures that are smaller, faster and better for both computer vision and natural language processing tasks. More specifically, the project explores methods of searching for neural architecture based on structural rules that compose smaller units to make bigger units, similar to how grammars in natural languages guides the way sentences are formed. This approach eliminates the efforts of manually engineering neural architectures. The success of this project will significantly advance AI systems in computer vision and natural language processing, thus moving forward other practical applications of AI technologies as well. This project will also integrate educational components by making significant connections with an interdisciplinary set of students and researchers in the Digital Humanities, and preparing demos to engage the K-12 and undergraduate communities.The project proposes three main tasks. The first is to unfold the space of neural architectures with deep compositional grammatical architectures; this allows for learning rich features of deep neural networks in a principled way. The second is to develop grammar-guided neural architecture search. The goal is to search smaller, faster and better deep compositional grammatical architectures by integrating differentiable search and reinforcement learning search in the unfolded space. The third task is to evaluate the proposed work applications. The searched architectures will be used as new feature backbones for existing state-of-the-art deep learning based systems commonly used in computer vision and NLP. The key innovations of this project include: a novel method of grammar-guided network architecture design and search for deep learning, and a unified feature backbone enabling effective and efficient feature exploration and exploitation in computer vision and NLP.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

人工智能（AI）技术最近在广泛的应用中显示了巨大的价值，例如自动驾驶汽车，智能扬声器，机器翻译，机器人自主权和医学诊断。计算机视觉（图像和视频的自动分析）和自然语言处理（文本自动分析）是AI的两个关键支柱。深度学习的人工神经网络是这两个领域中许多最先进的AI系统的“大脑”。但是，许多神经体系结构仍然是手工制作的，可以根据每个领域的单个任务来量身定制，而在人类大脑中学习似乎是任务和领域 - 无知的。该项目提出了一个原则性的框架，可以自动学习对计算机视觉和自然语言处理任务的较小，更快，更好的神经体系结构。更具体地说，该项目探讨了基于结构规则搜索神经体系结构的方法，该结构规则构成了较小的单元以制造较大的单元，类似于自然语言的语法如何指导句子的形成方式。这种方法消除了手动工程神经体系结构的努力。该项目的成功将在计算机视觉和自然语言处理中大大提高AI系统，从而推动AI技术的其他实际应用。该项目还将通过与数字人文学科中的学生和研究人员建立巨大的联系，并准备演示与K-12和本科社区的互动。该项目提出三个主要任务。首先是用深层的构图语法结构展开神经体系结构的空间。这可以以原则性的方式学习深神网络的丰富特征。第二个是开发语法引导的神经体系结构搜索。目的是通过在未折叠的空间中整合可区分的搜索和强化学习搜索来搜索较小，更快，更好的深层构图语法体系结构。第三个任务是评估拟议的工作应用程序。搜索的体系结构将用作现有的基于计算机视觉和NLP中常用的基于最新深度学习的系统的新功能骨干。该项目的关键创新包括：一种新颖的语法引导网络架构设计和寻找深度学习的方法，以及一个统一的功能骨干，在计算机视觉和NLP中实现有效，有效的功能探索和剥削。该奖项反映了NSF的法规任务，并被认为是通过基金会的知识优点和广泛的critia crietia criter criter scriter criter critia criter critia criter criteria criter criteria criter criteria criteria criter criteria criteria crietia crietia crietia crietia crietia crietia criteria均值得一提。

项目成果

Holistically-Attracted Wireframe Parsing

• DOI: 10.1109/cvpr42600.2020.00286
• 发表时间: 2020-03
• 期刊: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
• 作者: Nan Xue;Tianfu Wu;S. Bai;Fudong Wang;Guisong Xia;Liangpei Zhang;Philip H. S. Torr

Attentive Normalization

• DOI: 10.1007/978-3-030-58520-4_5
• 发表时间: 2019-08
• 作者: Xilai Li;Wei Sun-;Tianfu Wu

NOPE-SAC: Neural One-Plane RANSAC for Sparse-View Planar 3D Reconstruction

• DOI: 10.1109/tpami.2023.3314745
• 发表时间: 2022-11
• 期刊: IEEE Transactions on Pattern Analysis and Machine Intelligence
• 影响因子: 23.6
• 作者: Bin Tan;Nan Xue;Tianfu Wu;Guisong Xia

Learning Ordered Top-k Attacks via Adversarial Distillation

通过对抗性蒸馏学习有序 Top-k 攻击

• 发表时间: 2020
• 期刊: CVPR 2020 Workshop on Adversarial Machine Learning in Computer Vision
• 作者: Zhang, Zekun;Wu, Tianfu
• 通讯作者: Wu, Tianfu

Learning Local-Global Contextual Adaptation for Multi-Person Pose Estimation

• DOI: 10.1109/cvpr52688.2022.01272
• 发表时间: 2021-09
• 期刊: 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
• 作者: Nan Xue;Tianfu Wu;Gui-Song Xia;L. Zhang