no code implementations • ICML 2020 • Zhen-Yu Zhang, Peng Zhao, Yuan Jiang, Zhi-Hua Zhou
Besides the feature space evolving, it is noteworthy that the data distribution often changes in streaming data.
no code implementations • ICML 2020 • Lan-Zhe Guo, Zhen-Yu Zhang, Yuan Jiang, Yufeng Li, Zhi-Hua Zhou
Deep semi-supervised learning (SSL) has been shown very effectively.
1 code implementation • 21 Aug 2023 • Lue Tao, Yu-Xuan Huang, Wang-Zhou Dai, Yuan Jiang
Neuro-symbolic hybrid systems are promising for integrating machine learning and symbolic reasoning, where perception models are facilitated with information inferred from a symbolic knowledge base through logical reasoning.
no code implementations • 1 May 2023 • Yi-Xiao He, Shen-Huan Lyu, Yuan Jiang
Deep forest is a non-differentiable deep model which has achieved impressive empirical success across a wide variety of applications, especially on categorical/symbolic or mixed modeling tasks.
1 code implementation • 15 Feb 2022 • Yuan Jiang, Yaoxin Wu, Zhiguang Cao, Jie Zhang
Recent deep models for solving routing problems always assume a single distribution of nodes for training, which severely impairs their cross-distribution generalization ability.
1 code implementation • 26 Jan 2022 • Lu Dong, Zhi-Qiang Guo, Chao-Hong Tan, Ya-Jun Hu, Yuan Jiang, Zhen-Hua Ling
Neural network models have achieved state-of-the-art performance on grapheme-to-phoneme (G2P) conversion.
1 code implementation • NeurIPS 2021 • Yu-Xuan Huang, Wang-Zhou Dai, Le-Wen Cai, Stephen Muggleton, Yuan Jiang
To utilize the raw inputs and symbolic knowledge simultaneously, some recent neuro-symbolic learning methods use abduction, i. e., abductive reasoning, to integrate sub-symbolic perception and logical inference.
no code implementations • 11 Nov 2021 • Jin-Hui Wu, Shao-Qun Zhang, Yuan Jiang, Zhi-Hua Zhou
Neural network models generally involve two important components, i. e., network architecture and neuron model.
no code implementations • 30 Sep 2021 • Zhao-Yu Zhang, Shao-Qun Zhang, Yuan Jiang, Zhi-Hua Zhou
Multivariate time series (MTS) prediction is ubiquitous in real-world fields, but MTS data often contains missing values.
no code implementations • 17 Jun 2021 • Xin-Qiang Cai, Yao-Xiang Ding, Zi-Xuan Chen, Yuan Jiang, Masashi Sugiyama, Zhi-Hua Zhou
In many real-world imitation learning tasks, the demonstrator and the learner have to act under different observation spaces.
no code implementations • 17 Apr 2021 • Yang Yang, Zhao-Yang Fu, De-Chuan Zhan, Zhi-Bin Liu, Yuan Jiang
Moreover, we introduce the extrinsic unlabeled multi-modal multi-instance data, and propose the M3DNS, which considers the instance-level auto-encoder for single modality and modified bag-level optimal transport to strengthen the consistency among modalities.
no code implementations • 3 Sep 2020 • Jing-Xuan Zhang, Li-Juan Liu, Yan-Nian Chen, Ya-Jun Hu, Yuan Jiang, Zhen-Hua Ling, Li-Rong Dai
In this paper, we present a ASR-TTS method for voice conversion, which used iFLYTEK ASR engine to transcribe the source speech into text and a Transformer TTS model with WaveNet vocoder to synthesize the converted speech from the decoded text.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +4
2 code implementations • NeurIPS 2020 • Lu Wang, Xuanqing Liu, Jin-Feng Yi, Yuan Jiang, Cho-Jui Hsieh
Metric learning is an important family of algorithms for classification and similarity search, but the robustness of learned metrics against small adversarial perturbations is less studied.
no code implementations • 7 Jun 2020 • Ji Feng, Yi-Xuan Xu, Yuan Jiang, Zhi-Hua Zhou
Gradient Boosting Machine has proven to be one successful function approximator and has been widely used in a variety of areas.
1 code implementation • 11 May 2020 • Lu Wang, huan zhang, Jin-Feng Yi, Cho-Jui Hsieh, Yuan Jiang
By constraining adversarial perturbations in a low-dimensional subspace via spanning an auxiliary unlabeled dataset, the spanning attack significantly improves the query efficiency of a wide variety of existing black-box attacks.
no code implementations • 15 Nov 2019 • Liang Yang, Xi-Zhu Wu, Yuan Jiang, Zhi-Hua Zhou
In multi-label learning, each instance is associated with multiple labels and the crucial task is how to leverage label correlations in building models.
no code implementations • 5 Nov 2019 • Xin Wang, Junichi Yamagishi, Massimiliano Todisco, Hector Delgado, Andreas Nautsch, Nicholas Evans, Md Sahidullah, Ville Vestman, Tomi Kinnunen, Kong Aik Lee, Lauri Juvela, Paavo Alku, Yu-Huai Peng, Hsin-Te Hwang, Yu Tsao, Hsin-Min Wang, Sebastien Le Maguer, Markus Becker, Fergus Henderson, Rob Clark, Yu Zhang, Quan Wang, Ye Jia, Kai Onuma, Koji Mushika, Takashi Kaneda, Yuan Jiang, Li-Juan Liu, Yi-Chiao Wu, Wen-Chin Huang, Tomoki Toda, Kou Tanaka, Hirokazu Kameoka, Ingmar Steiner, Driss Matrouf, Jean-Francois Bonastre, Avashna Govender, Srikanth Ronanki, Jing-Xuan Zhang, Zhen-Hua Ling
Spoofing attacks within a logical access (LA) scenario are generated with the latest speech synthesis and voice conversion technologies, including state-of-the-art neural acoustic and waveform model techniques.
no code implementations • 9 Sep 2019 • Xin-Qiang Cai, Yao-Xiang Ding, Yuan Jiang, Zhi-Hua Zhou
One of the key issues for imitation learning lies in making policy learned from limited samples to generalize well in the whole state-action space.
no code implementations • ICML 2018 • Han-Jia Ye, De-Chuan Zhan, Yuan Jiang, Zhi-Hua Zhou
On the way to the robust learner for real-world applications, there are still great challenges, including considering unknown environments with limited data.
no code implementations • ICCV 2017 • Wei Shen, Bin Wang, Yuan Jiang, Yan Wang, Alan Yuille
This design is biologically-plausible, as it likes a human visual system to compare different possible segmentation solutions to address the ambiguous boundary issue.
no code implementations • NeurIPS 2016 • Han-Jia Ye, De-Chuan Zhan, Xue-Min Si, Yuan Jiang, Zhi-Hua Zhou
In UM2L, a type of combination operator is introduced for distance characterization from multiple perspectives, and thus can introduce flexibilities for representing and utilizing both spatial and semantic linkages.
1 code implementation • 13 Sep 2016 • Wei Shen, Kai Zhao, Yuan Jiang, Yan Wang, Xiang Bai, Alan Yuille
By observing the relationship between the receptive field sizes of the different layers in the network and the skeleton scales they can capture, we introduce two scale-associated side outputs to each stage of the network.
no code implementations • 20 May 2016 • Wei Shen, Yuan Jiang, Wenjing Gao, Dan Zeng, Xinggang Wang
Contour and skeleton are two complementary representations for shape recognition.
no code implementations • CVPR 2016 • Wei Shen, Kai Zhao, Yuan Jiang, Yan Wang, Zhijiang Zhang, Xiang Bai
Object skeleton is a useful cue for object detection, complementary to the object contour, as it provides a structural representation to describe the relationship among object parts.
no code implementations • 4 Aug 2015 • Shao-Yuan Li, Yuan Jiang, Zhi-Hua Zhou
Multi-label active learning is a hot topic in reducing the label cost by optimally choosing the most valuable instance to query its label from an oracle.