Deep neural networks (DNNs) have become a key part of many modern software applications. After training and validating, the DNN is deployed as an irrevocable component and applied in real-world scenarios. Although most DNNs are built meticulously with huge volumes of training data, data in the real world still remain unknown to the DNN model, which leads to the crucial requirement of runtime out-of-distribution (OOD) detection. However, many existing approaches 1) need OOD data for classifier training or parameter tuning, or 2) simply combine the scores of each hidden layer as an ensemble of features for OOD detection. In this paper, we present a novel outlook on in-distribution data in a generative manner, which takes their latent features generated from each hidden layer as a joint distribution across representation spaces. Since only the in-distribution latent features are comprehensively understood in representation space, the internal difference between in-distribution and OOD data can be naturally revealed without the intervention of any OOD data. Specifically, We construct a generative model, called Latent Sequential Gaussian Mixture (LSGM), to depict how the in-distribution latent features are generated in terms of the trace of DNN inference across representation spaces. We first construct the Gaussian Mixture Model (GMM) based on in-distribution latent features for each hidden layer, and then connect GMMs via the transition probabilities of the inference traces. Experimental evaluations on popular benchmark OOD datasets and models validate the superiority of the proposed method over the state-of-the-art methods in OOD detection.
Spatio-Temporal Multi-Task Learning Transformer for Joint Moving Object Detection and Segmentation
Valeo R&D(法雷奥研发中心)
移动物体对于自动驾驶任务具有特殊的重要性。检测移动对象可以通过分割对象像素而被定位为移动对象分割,或者通过生成移动目标的限界框而被定位为移动目标检测。在本文中,我们提出了一个多任务学习架构,基于Transformers,通过一个网络来共同执行这两个任务。由于运动特征对任务的重要性,整个设置基于时空聚合。我们评估的性能与MTL设置,无论是早期共享的编码器,和后期共享的编码器-解码器Transformers器的单独任务架构。对于后者,我们提出了一种新的联合任务查询解码器Transformer,使我们能够有任务专用头的共享模型。为了评估我们的方法,我们使用KITTI MOD [29]数据集。结果显示,在单个任务网络上,移动目标检测的mAP提高了1.5%,移动对象分割的IoU提高了2%。
Joint Signal Detection and Automatic Modulation Classification via Deep Learning
Future Network of Intelligence Institute (FNii)(未来智能网络研究所(FNii));School of Science and Engineering (SSE)(科学与工程学院(SSE));The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳));School of Cyberspace Security, Beijing University of Posts and Telecommunications(北京邮电大学网络空间安全学院)