The text generated by neural language models is not as good as the real text. This means that their distributions are different. Generative Adversarial Nets (GAN) are used to alleviate it. However, some researchers argue that GAN variants do not work at all. When both sample quality (such as Bleu) and sample diversity (such as self-Bleu) are taken into account, the GAN variants even are worse than a well-adjusted language model. But, Bleu and self-Bleu can not precisely measure this distributional discrepancy. In fact, how to measure the distributional discrepancy between real text and generated text is still an open problem. In this paper, we theoretically propose two metric functions to measure the distributional difference between real text and generated text. Besides that, a method is put forward to estimate them. First, we evaluate language model with these two functions and find the difference is huge. Then, we try several methods to use the detected discrepancy signal to improve the generator. However the difference becomes even bigger than before. Experimenting on two existing language GANs, the distributional discrepancy between real text and generated text increases with more adversarial learning rounds. It demonstrates both of these language GANs fail.
Multimodal Semantic Transfer from Text to Image. Fine-Grained Image Classification by Distributional Semantics
University Passau(帕绍大学);University of St.Gallen(圣加仑大学)
在过去的几年里,图像分类过程,如艺术史和遗产信息学领域的神经网络,经历了广泛的分布(Lang和Ommer 2018)。这些方法面临着一些挑战,包括处理相对少量的数据以及数字人文中的高维数据。这里,使用卷积神经网络(CNN),其输出不是像往常一样的一系列平面文本标签,而是一系列语义加载的向量。这些向量的结果从一个分布式语义模型(DSM),这是从域内的文本语料库生成。- In den letzten Jahren hat die Verwendung von Bildklassifierungsverfahren wie neuronalen Netzwerken auch im Bereich der historischen Bildwissenschaften und der Heritage Informatics weite Verbreitung gefunden(Lang und Ommer 2018).这种方法可以通过一个简单的方法来实现,因为它可以在数字地理科学中获得更高维度的数据。这一分类方法在一个非常小的空间内进行。Zugang在Bemühen的本体论研究中发现了一个与本体论相关的概念,包括分类学、部分学和关联的概念,这些概念并不是形式化的本体论。大北是一个卷积神经网络(CNN)的生成器,用于训练过程中,也可以用于训练,但不是在一个意甲联赛中,而是在一个意甲联赛中…
Bridging the RGB-IR Gap: Consensus and Discrepancy Modeling for Text-Guided Multispectral Detection
Department of Automation, Tsinghua University(清华大学自动化系);State Key Laboratory of Blockchain and Data Security, Zhejiang University(浙江大学区块链与数据安全全国重点实验室);Tsinghua University(清华大学)
Beyond Perceptual Distance: Discrepancy Assessment on Deep Representation for Out-of-Distribution Detection with Diffusion Model
Department of Automation, Shanghai Jiao Tong University(上海交通大学自动化系);Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University(香港理工大学电子与电气工程系);The Intsig Information Co., Ltd., Shanghai, China(上海Intsig信息有限公司);School of Automation, Beijing Institute of Technology(北京理工大学自动化学院)
Dataset Distillation with Neural Characteristic Function: A Minmax Perspective
School of Artificial Intelligence, Shanghai Jiao Tong University(上海交通大学人工智能学院);EPIC Lab, Shanghai Jiao Tong University(上海交通大学EPIC实验室);Hong Kong University of Science and Technology, Guangzhou(香港科技大学(广州));Shanghai Artificial Intelligence Laboratory(上海人工智能实验室)
GDCNet: Generative Discrepancy Comparison Network for Multimodal Sarcasm Detection
State Key Laboratory of AI Safety, Institute of Computing Technology (ICT), Chinese Academy of Sciences (CAS)(人工智能安全国家重点实验室,计算技术研究所(ICT),中国科学院(CAS));University of Chinese Academy of Sciences, CAS(中国科学院大学);Pengcheng Laboratory(鹏城实验室);Shenzhen Stock Exchange(深圳证券交易所)