Unknown examples that are unseen during training often appear in real-world computer vision tasks, and an intelligent self-learning system should be able to differentiate between known and unknown examples. Open set recognition, which addresses this problem, has been studied for approximately a decade. However, conventional open set recognition methods based on deep neural networks (DNNs) lack a foundation for post recognition score analysis. In this paper, we propose a DNN structure in which multiple one-vs-rest sigmoid networks follow a convolutional neural network feature extractor. A one-vs-rest network, which is composed of rectified linear unit activation functions for the hidden layers and a single sigmoid target class output node, can maximize the ability to learn information from nonmatch examples. Furthermore, the network yields a sophisticated nonlinear features-to-output mapping that is explainable in the feature space. By introducing extreme value theory-based calibration techniques, the nonlinear and explainable mapping provides a well-grounded class membership probability models. Our experiments show that one-vs-rest networks can provide more informative hidden representations for unknown examples than the commonly used SoftMax layer. In addition, the proposed probability model outperformed the state-of-the art methods in open set classification scenarios.
Permutation-invariant Feature Restructuring for Correlation-aware Image Set-based Recognition
Carnegie Mellon University（卡内基梅隆大学）；Harvard University（哈佛大学）；CIOMP, Chinese Academy of Sciences（中国科学院长春光学精密机械与物理研究所）；Graduate School at Shenzhen, Tsinghua University（清华大学深圳研究生院）；The Hong Kong Polytechnic University（香港理工大学）
Asymmetric Invertible Threat: Learning Reversible Privacy Defense for Face Recognition
School of Cyber Science and Engineering, Sichuan University（四川大学计算机科学与工程学院）；Lee Kong Chian School of Medicine, Nanyang Technological University（南洋理工大学李科钦医学院）；School of Electrical and Electronic Engineering, Yonsei University（延世大学电子与电气工程学院）
ResLPR: A LiDAR Data Restoration Network and Benchmark for Robust Place Recognition Against Weather Corruptions
College of Intelligence Science and Technology（智能科学与技术学院）；National University of Defense Technology（国防科技大学）；Harbin Institute of Technology（哈尔滨工业大学）；New York University Abu Dhabi（纽约大学阿布扎比分校）；University of Science and Technology of China（中国科学技术大学）
Noise-Tolerant Paradigm for Training Face Recognition CNNs
Beijing University of Chemical Technology（北京化工大学）；Yunshitu Corporation（云视途公司）
得益于大规模训练数据集，深度卷积神经网络（CNN）在人脸识别（FR）方面取得了令人印象深刻的结果。然而，巨大规模的数据集不可避免地导致噪声数据，这明显降低了训练的CNN模型的性能。从大规模FR数据集中踢出错误的标签仍然非常昂贵，尽管提出了一些清理方法。通过对基于角间隔损失（angular margin based loss，AM-Loss）函数监督下的CNN模型训练全过程的分析，发现训练样本的$θ$分布隐含地反映了其干净的概率。因此，我们提出了一种新的训练范式，采用基于上述概率的加权样本的想法。在没有任何噪声先验知识的情况下，我们可以用大规模FR数据集训练高性能的CNN模型。实验证明了我们的训练范式的有效性。这些代码可在https://github.com/huangyangyu/NoiseFace上获得。
Driving with Context: Online Map Matching for Complex Roads Using Lane Markings and Scenario Recognition
School of Automotive Studies, Tongji University（同济大学汽车学院）；Department of Automation and Perception, Shanghai Jiao Tong University（上海交通大学自动化与感知系）；Zenseact
DropSample: A New Training Method to Enhance Deep Convolutional Neural Networks for Large-Scale Unconstrained Handwritten Chinese Character Recognition
South China University of Technology（华南理工大学）；University of Technology, Sydney（悉尼科技大学）
