Existing neural network architectures in computer vision -- whether designed by humans or by machines -- were typically found using both images and their associated labels. In this paper, we ask the question: can we find high-quality neural architectures using only images, but no human-annotated labels? To answer this question, we first define a new setup called Unsupervised Neural Architecture Search (UnNAS). We then conduct two sets of experiments. In sample-based experiments, we train a large number (500) of diverse architectures with either supervised or unsupervised objectives, and find that the architecture rankings produced with and without labels are highly correlated. In search-based experiments, we run a well-established NAS algorithm (DARTS) using various unsupervised objectives, and report that the architectures searched without labels can be competitive to their counterparts searched with labels. Together, these results reveal the potentially surprising finding that labels are not necessary, and the image statistics alone may be sufficient to identify good neural architectures.
Are Large-scale Soft Labels Necessary for Large-scale Dataset Distillation?
CFAR, Agency for Science, Technology and Research, Singapore（新加坡科技研究局CFAR）；National University of Singapore（新加坡国立大学）；IHPC, Agency for Science, Technology and Research, Singapore（新加坡科技研究局IHPC）
Data-Free Neural Architecture Search via Recursive Label Calibration
Hong Kong University of Science and Technology（香港科技大学）；Carnegie Mellon University（卡内基梅隆大学）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；Google Research（谷歌研究院）
UnrealNAS: Can We Search Neural Architectures with Unreal Data?
University of California, Berkeley（加州大学伯克利分校）；King Abdullah University of Science and Technology（阿卜杜拉国王科技大学）；Tsinghua University（清华大学）；Peking University（北京大学）
Is Complete Labeling Necessary? Understanding Active Learning in Longitudinal Medical Imaging
School of Computer Science, University College Dublin（都柏林大学计算机科学学院）；Insight Centre for Data Analytics（数据分析研究中心）；School of Medicine, University College Dublin（都柏林大学医学院）；Department of Radiology, St Vincent’s University Hospital（圣文森大学医院放射科）；Great Ormond Street Hospital for Children（儿童医院）
Pseudo Label-Guided Model Inversion Attack via Conditional Generative Adversarial Network
University of Science and Technology of China（中国科学技术大学）；University of Waterloo（滑铁卢大学）；CISPA Helmholtz Center for Information Security（CISPA赫尔姆霍茨信息安全中心）
Improving the Convergence Rate of Ray Search Optimization for Query-Efficient Hard-Label Attacks
Institute of Cyberspace Security, Zhejiang University of Technology（浙江工业大学网络空间安全研究院）；JQ Investments（JQ投资）；Binjiang Institute of Artificial Intelligence, ZJUT（浙江工业大学滨江人工智能研究院）
Fast One-Stage Unsupervised Domain Adaptive Person Search
The College of Information and Science Technology, Dalian Maritime University（大连海事大学信息科学技术学院）；The College School of Cyber Security and Computer, Hebei University（河北大学网络空间安全与计算机学院）；The College of Computer Science and Artificial Intelligence, Wenzhou University（温州大学计算机科学与人工智能学院）；Key Laboratory of Knowledge Engineering with Big Data, Hefei University of Technology（合肥工业大学大数据知识工程重点实验室）
Are Dense Labels Always Necessary for 3D Object Detection from Point Cloud?
School of Intelligent Systems Engineering, the Shenzhen Campus of Sun Yatsen University（南方科技大学深圳校区智能系统工程学院）；School of Computer Science, Wuhan University（武汉大学计算机学院）；School of Mathematics and Statistics and Ministry of Education Key Lab of Intelligent Networks and Network Security, Xi’an Jiaotong University（西安交通大学数学与统计学系和教育部智能网络与网络安全重点实验室）；School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications（重庆邮电大学通信与信息工程学院）；Meta；University of Maryland（美国马里兰大学）
