Sort by: Year Popularity Relevance
Masato Uchida, Yasuhiro Katsura - 2020
Unlike ordinary supervised pattern recognition, in a newly proposed framework namely complementary-label learning, each label specifies one class that the pattern does not belong to. In this paper, we propose the natural generalization of learning from an ordinary label and a complementary label, specifically focused on one-versus-all and pairwis...
Dawei Yin, Xiaofang Zhao, Yonghao Song, Cheng Zhang, Hongshen Chen, Hengyi Cai - 2020
Neural conversation systems generate responses based on the sequence-to-sequence (SEQ2SEQ) paradigm. Typically, the model is equipped with a single set of learned parameters to generate responses for given input contexts. When confronting diverse conversations, its adaptability is rather limited and the model is hence prone to generate generic re...
Nils M. Kriege, Jonathan Masci, Christopher Morris, Jan E. Lenssen, Matthias Fey - 2020
This work presents a two-stage neural architecture for learning and refining structural correspondences between graphs. First, we use localized node embeddings computed by a graph neural network to obtain an initial ranking of soft correspondences between nodes. Secondly, we employ synchronous message passing networks to iteratively re-rank the s...
Johan A. K. Suykens, Michaël Fanuel, Henri De Plaen - 2020
In the context of kernel methods, the similarity between data points is encoded by the kernel function which is often defined thanks to the Euclidean distance, a common example being the squared exponential kernel. Recently, other distances relying on optimal transport theory - such as the Wasserstein distance between probability distributions - ...
Ming Li, Shiliang Zhao, Suofei Zhang, Xiaofu Wu, Ben Xie - 2020
Learning diverse features is key to the success of person re-identification. Various part-based methods have been extensively proposed for learning local representations, which, however, are still inferior to the best-performing methods for person re-identification. This paper proposes to construct a strong lightweight network architecture, terme...
Jan Peters, Hany Abdulsamad, Joao Carvalho, Samuele Tosatto - 2020
Reinforcement learning (RL) algorithms still suffer from high sample complexity despite outstanding recent successes. The need for intensive interactions with the environment is especially observed in many widely popular policy gradient algorithms that perform updates using on-policy samples. The price of such inefficiency becomes evident in real...
Wei An, Xinpu Deng, Zaiping Lin, Li Liu, Yulan Guo, Longguang Wang - 2020
Video super-resolution (SR) aims at generating a sequence of high-resolution (HR) frames with plausible and temporally consistent details from their low-resolution (LR) counterparts. The key challenge for video SR lies in the effective exploitation of temporal dependency between consecutive frames. Existing deep learning based methods commonly es...
Yuan Tang, Mingjie Tang, Wei Yan, Xiang Chen, Wenjing Zhu, Ziyao Gao, Liang Xie, Yu Wang, Yongfeng Liu, Xu Yan, Yi Wu, Weiguo Zhu, Yang Yang, Yi Wang - 2020
Industrial AI systems are mostly end-to-end machine learning (ML) workflows. A typical recommendation or business intelligence system includes many online micro-services and offline jobs. We describe SQLFlow for developing such workflows efficiently in SQL. SQL enables developers to write short programs focusing on the purpose (what) and ignoring...
Frederic Gibou, Luis Ángel Larios Cárdenas - 2020
We propose a deep learning strategy to compute the mean curvature of an implicit level-set representation of an interface. Our approach is based on fitting neural networks to synthetic datasets of pairs of nodal $\phi$ values and curvatures obtained from circular interfaces immersed in different uniform resolutions. These neural networks are mult...
Zhiguo Cao, Chunhua Shen, Liang Liu, Chengxin Liu, Hao Lu, Haipeng Xiong - 2020
Visual counting, a task that aims to estimate the number of objects from an image/video, is an open-set problem by nature, i.e., the number of population can vary in [0, inf) in theory. However, collected data and labeled instances are limited in reality, which means that only a small closed set is observed. Existing methods typically model this ...