Search Results for author: Zhanyu Ma

Found 55 papers, 20 papers with code

Dual Graph Convolutional Networks for Aspect-based Sentiment Analysis

1 code implementation ACL 2021 Ruifan Li, Hao Chen, Fangxiang Feng, Zhanyu Ma, Xiaojie Wang, Eduard Hovy

To overcome these challenges, in this paper, we propose a dual graph convolutional networks (DualGCN) model that considers the complementarity of syntax structures and semantic correlations simultaneously.

Aspect-Based Sentiment Analysis Dependency Parsing

Cross-layer Navigation Convolutional Neural Network for Fine-grained Visual Classification

no code implementations21 Jun 2021 Chenyu Guo, Jiyang Xie, Kongming Liang, Xian Sun, Zhanyu Ma

Then, attention mechanisms are used after feature fusion to extract spatial and channel information while linking the high-level semantic information and the low-level texture features, which can better locate the discriminative regions for the FGVC.

Fine-Grained Image Classification

CMF: Cascaded Multi-model Fusion for Referring Image Segmentation

1 code implementation16 Jun 2021 Jianhua Yang, Yan Huang, Zhanyu Ma, Liang Wang

To solve this problem, we propose a simple yet effective Cascaded Multi-modal Fusion (CMF) module, which stacks multiple atrous convolutional layers in parallel and further introduces a cascaded branch to fuse visual and linguistic features.

Semantic Segmentation

Structured DropConnect for Uncertainty Inference in Image Classification

1 code implementation16 Jun 2021 Wenqing Zheng, Jiyang Xie, Weidong Liu, Zhanyu Ma

For image classification tasks, we propose a structured DropConnect (SDC) framework to model the output of a deep neural network by a Dirichlet distribution.

Classification Image Classification +1

Channel DropBlock: An Improved Regularization Method for Fine-Grained Visual Classification

no code implementations7 Jun 2021 Yifeng Ding, Shuwei Dong, Yujun Tong, Zhanyu Ma, Bo Xiao, Haibin Ling

Classifying the sub-categories of an object from the same super-category (e. g., bird) in a fine-grained visual classification (FGVC) task highly relies on mining multiple discriminative features.

Classification Fine-Grained Image Classification

Deep Metric Learning for Few-Shot Image Classification: A Selective Review

no code implementations17 May 2021 Xiaoxu Li, Xiaochen Yang, Zhanyu Ma, Jing-Hao Xue

Few-shot image classification is a challenging problem which aims to achieve the human level of recognition based only on a small number of images.

Classification Few-Shot Image Classification +3

Unsupervised Person Re-identification via Simultaneous Clustering and Consistency Learning

no code implementations1 Apr 2021 Junhui Yin, Jiayan Qiu, Siqing Zhang, Jiyang Xie, Zhanyu Ma, Jun Guo

Unsupervised person re-identification (re-ID) has become an important topic due to its potential to resolve the scalability problem of supervised re-ID models.

Unsupervised Person Re-Identification

DF^2AM: Dual-level Feature Fusion and Affinity Modeling for RGB-Infrared Cross-modality Person Re-identification

no code implementations1 Apr 2021 Junhui Yin, Zhanyu Ma, Jiyang Xie, Shibo Nie, Kongming Liang, Jun Guo

Meanwhile, to further mining the relationships between global features from person images, we propose an Affinities Modeling (AM) module to obtain the optimal intra- and inter-modality image matching.

Cross-Modality Person Re-identification Person Re-Identification

Duplex Contextual Relation Network for Polyp Segmentation

1 code implementation11 Mar 2021 Zijin Yin, Kongming Liang, Zhanyu Ma, Jun Guo

However, previous methods only focus on learning the dependencies between the position within an individual image and ignore the contextual relation across different images.

Fine-Grained Visual Classification via Simultaneously Learning of Multi-regional Multi-grained Features

2 code implementations31 Jan 2021 Dongliang Chang, Yixiao Zheng, Zhanyu Ma, Ruoyi Du, Kongming Liang

Finally, we can obtain multiple discriminative regions on high-level feature channels and obtain multiple more minute regions within these discriminative regions on middle-level feature channels.

Fine-Grained Image Classification General Classification

TLRM: Task-level Relation Module for GNN-based Few-Shot Learning

no code implementations25 Jan 2021 Yurong Guo, Zhanyu Ma, Xiaoxu Li, Yuan Dong

We consider this method of measuring relation of samples only models the sample-to-sample relation, while neglects the specificity of different tasks.

Few-Shot Learning

Knowledge Transfer Based Fine-grained Visual Classification

1 code implementation21 Dec 2020 Siqing Zhang, Ruoyi Du, Dongliang Chang, Zhanyu Ma, Jun Guo

Convolution neural networks (CNNs), which employ the cross entropy loss (CE-loss) as the loss function, show poor performance since the model can only learn the most discriminative part and ignore other meaningful regions.

Classification Fine-Grained Image Classification +2

Dilated-Scale-Aware Attention ConvNet For Multi-Class Object Counting

no code implementations15 Dec 2020 Wei Xu, Dingkang Liang, Yixiao Zheng, Zhanyu Ma

In this paper, we propose a simple yet efficient counting network based on point-level annotations.

Object Counting

BSNet: Bi-Similarity Network for Few-shot Fine-grained Image Classification

1 code implementation29 Nov 2020 Xiaoxu Li, Jijie Wu, Zhuo Sun, Zhanyu Ma, Jie Cao, Jing-Hao Xue

Motivated by this, we propose a so-called \textit{Bi-Similarity Network} (\textit{BSNet}) that consists of a single embedding module and a bi-similarity module of two similarity measures.

Classification Few-Shot Learning +2

Your "Flamingo" is My "Bird": Fine-Grained, or Not

1 code implementation CVPR 2021 Dongliang Chang, Kaiyue Pang, Yixiao Zheng, Zhanyu Ma, Yi-Zhe Song, Jun Guo

For that, we re-envisage the traditional setting of FGVC, from single-label classification, to that of top-down traversal of a pre-defined coarse-to-fine label hierarchy -- so that our answer becomes "bird"-->"Phoenicopteriformes"-->"Phoenicopteridae"-->"flamingo".

Fine-Grained Image Classification General Classification

DS-UI: Dual-Supervised Mixture of Gaussian Mixture Models for Uncertainty Inference

no code implementations17 Nov 2020 Jiyang Xie, Zhanyu Ma, Jing-Hao Xue, Guoqiang Zhang, Jun Guo

In the DS-UI, we combine the classifier of a DNN, i. e., the last fully-connected (FC) layer, with a mixture of Gaussian mixture models (MoGMM) to obtain an MoGMM-FC layer.

Actor and Action Modular Network for Text-based Video Segmentation

no code implementations2 Nov 2020 Jianhua Yang, Yan Huang, Kai Niu, Zhanyu Ma, Liang Wang

We first learn the actor-/action-related content for the video and textual query, and then match them in a symmetrical manner to localize the target region.

Action Segmentation Action Understanding +4

GINet: Graph Interaction Network for Scene Parsing

1 code implementation ECCV 2020 Tianyi Wu, Yu Lu, Yu Zhu, Chuang Zhang, Ming Wu, Zhanyu Ma, Guodong Guo

GI unit is further improved by the SC-loss to enhance the semantic representations over the exemplar-based semantic graph.

Scene Parsing

SSKD: Self-Supervised Knowledge Distillation for Cross Domain Adaptive Person Re-Identification

no code implementations13 Sep 2020 Junhui Yin, Jiayan Qiu, Siqing Zhang, Zhanyu Ma, Jun Guo

To this end, we propose a Self-Supervised Knowledge Distillation (SSKD) technique containing two modules, the identity learning and the soft label learning.

Domain Adaptive Person Re-Identification Knowledge Distillation +1

ReMarNet: Conjoint Relation and Margin Learning for Small-Sample Image Classification

1 code implementation27 Jun 2020 Xiaoxu Li, Liyun Yu, Xiaochen Yang, Zhanyu Ma, Jing-Hao Xue, Jie Cao, Jun Guo

Despite achieving state-of-the-art performance, deep learning methods generally require a large amount of labeled data during training and may suffer from overfitting when the sample size is small.

Classification General Classification +1

A Concise Review of Recent Few-shot Meta-learning Methods

no code implementations22 May 2020 Xiaoxu Li, Zhuo Sun, Jing-Hao Xue, Zhanyu Ma

Few-shot meta-learning has been recently reviving with expectations to mimic humanity's fast adaption to new concepts based on prior knowledge.

Meta-Learning

OSLNet: Deep Small-Sample Classification with an Orthogonal Softmax Layer

1 code implementation20 Apr 2020 Xiaoxu Li, Dongliang Chang, Zhanyu Ma, Zheng-Hua Tan, Jing-Hao Xue, Jie Cao, Jingyi Yu, Jun Guo

A deep neural network of multiple nonlinear layers forms a large function space, which can easily lead to overfitting when it encounters small-sample data.

Classification General Classification

GPCA: A Probabilistic Framework for Gaussian Process Embedded Channel Attention

1 code implementation10 Mar 2020 Jiyang Xie, Dongliang Chang, Zhanyu Ma, Guo-Qiang Zhang, Jun Guo

In this paper, we propose Gaussian process embedded channel attention (GPCA) module and further interpret the channel attention schemes in a probabilistic way.

Image Classification

Dual-attention Guided Dropblock Module for Weakly Supervised Object Localization

1 code implementation9 Mar 2020 Junhui Yin, Siqing Zhang, Dongliang Chang, Zhanyu Ma, Jun Guo

This module contains two key components, the channel attention guided dropout (CAGD) and the spatial attention guided dropblock (SAGD).

Weakly-Supervised Object Localization

Mind the Gap: Enlarging the Domain Gap in Open Set Domain Adaptation

2 code implementations8 Mar 2020 Dongliang Chang, Aneeshan Sain, Zhanyu Ma, Yi-Zhe Song, Jun Guo

The key insight lies with how we exploit the mutually beneficial information between two networks; (a) to separate samples of known and unknown classes, (b) to maximize the domain confusion between source and target domain without the influence of unknown samples.

Unsupervised Domain Adaptation

OVC-Net: Object-Oriented Video Captioning with Temporal Graph and Detail Enhancement

no code implementations8 Mar 2020 Fangyi Zhu, Jenq-Neng Hwang, Zhanyu Ma, Guang Chen, Jun Guo

Thereafter, we construct a new dataset, providing consistent object-sentence pairs, to facilitate effective cross-modal learning.

Video Captioning

Weakly Supervised Attention Pyramid Convolutional Neural Network for Fine-Grained Visual Classification

no code implementations9 Feb 2020 Yifeng Ding, Shaoguo Wen, Jiyang Xie, Dongliang Chang, Zhanyu Ma, Zhongwei Si, Haibin Ling

Classifying the sub-categories of an object from the same super-category (e. g. bird species, car and aircraft models) in fine-grained visual classification (FGVC) highly relies on discriminative feature representation and accurate region localization.

Fine-Grained Image Classification General Classification

Competing Ratio Loss for Discriminative Multi-class Image Classification

1 code implementation25 Dec 2019 Ke Zhang, Yurong Guo, Xinsheng Wang, Dongliang Chang, Zhenbing Zhao, Zhanyu Ma, Tony X. Han

However, during the training of the deep convolutional neural network, the value of NLLR is not always positive or negative, which severely affects the convergence of NLLR.

Age Estimation Classification +3

Semi-Heterogeneous Three-Way Joint Embedding Network for Sketch-Based Image Retrieval

no code implementations10 Nov 2019 Jianjun Lei, Yuxin Song, Bo Peng, Zhanyu Ma, Ling Shao, Yi-Zhe Song

How to align abstract sketches and natural images into a common high-level semantic space remains a key problem in SBIR.

Sketch-Based Image Retrieval

Competing Ratio Loss for Discriminative Multi-class Image Classification

no code implementations31 Jul 2019 Ke Zhang, Xinsheng Wang, Yurong Guo, Zhenbing Zhao, Zhanyu Ma, Tony X. Han

A lot of studies of image classification based on deep convolutional neural network focus on the network structure to improve the image classification performance.

Age Estimation Classification +3

Deep Zero-Shot Learning for Scene Sketch

no code implementations11 May 2019 Yao Xie, Peng Xu, Zhanyu Ma

We introduce a novel problem of scene sketch zero-shot learning (SSZSL), which is a challenging task, since (i) different from photo, the gap between common semantic domain (e. g., word vector) and sketch is too huge to exploit common semantic knowledge as the bridge for knowledge transfer, and (ii) compared with single-object sketch, more expressive feature representation for scene sketch is required to accommodate its high-level of abstraction and complexity.

Transfer Learning Zero-Shot Learning

Channel Max Pooling Layer for Fine-Grained Vehicle Classification

no code implementations14 Feb 2019 Zhanyu Ma, Dongliang Chang, Xiaoxu Li

Experimental results on two fine-grained vehicle datasets, the Stanford Cars-196 dataset and the Comp Cars dataset, demonstrate that the proposed layer could improve classification accuracies of deep neural networks on fine-grained vehicle classification in the situation that a massive of parameters are reduced.

Classification Fine-Grained Vehicle Classification +1

On the Convergence of Extended Variational Inference for Non-Gaussian Statistical Models

no code implementations13 Feb 2019 Zhanyu Ma, Jalil Taghia, Jun Guo

Recently, an improved framework, namely the extended variational inference (EVI), has been introduced and applied to derive analytically tractable solution by employing lower-bound approximation to the variational objective function.

Variational Inference

Language Identification with Deep Bottleneck Features

no code implementations18 Sep 2018 Zhanyu Ma, Hong Yu

In order to improve the SLD accuracy of short utterances a phase vocoder based time-scale modification(TSM) method is used to reduce and increase speech rated of the test utterance.

Language Identification Transfer Learning

Deep Neural Network for Analysis of DNA Methylation Data

no code implementations2 Aug 2018 Hong Yu, Zhanyu Ma

Many researches demonstrated that the DNA methylation, which occurs in the context of a CpG, has strong correlation with diseases, including cancer.

Histogram Transform-based Speaker Identification

no code implementations2 Aug 2018 Zhanyu Ma, Hong Yu

A novel text-independent speaker identification (SI) method is proposed.

Speaker Identification

Impacts of Weather Conditions on District Heat System

no code implementations2 Aug 2018 Jiyang Xie, Zhanyu Ma, Jun Guo

Using artificial neural network for the prediction of heat demand has attracted more and more attention.

Mobile big data analysis with machine learning

no code implementations2 Aug 2018 Jiyang Xie, Zeyu Song, Yupeng Li, Zhanyu Ma

Finally, we summarize the main challenges and future development directions of mobile big data analysis.

Speech Recognition

Classification of EEG Signal based on non-Gaussian Neutral Vector

no code implementations2 Aug 2018 Zhanyu Ma

In the design of brain-computer interface systems, classification of Electroencephalogram (EEG) signals is the essential part and a challenging task.

Classification EEG +2

Dirichlet Mixture Model based VQ Performance Prediction for Line Spectral Frequency

no code implementations2 Aug 2018 Zhanyu Ma

In this paper, we continue our previous work on the Dirichlet mixture model (DMM)-based VQ to derive the performance bound of the LSF VQ.

Quantization

SEA: A Combined Model for Heat Demand Prediction

no code implementations28 Jul 2018 Jiyang Xie, Jiaxin Guo, Zhanyu Ma, Jing-Hao Xue, Qie Sun, Hailong Li, Jun Guo

ENN and ARIMA are used to predict seasonal and trend components, respectively.

Infinite Mixture of Inverted Dirichlet Distributions

no code implementations27 Jul 2018 Zhanyu Ma, Yuping Lai

In this work, we develop a novel Bayesian estimation method for the Dirichlet process (DP) mixture of the inverted Dirichlet distributions, which has been shown to be very flexible for modeling vectors with positive elements.

Variational Inference

BALSON: Bayesian Least Squares Optimization with Nonnegative L1-Norm Constraint

no code implementations8 Jul 2018 Jiyang Xie, Zhanyu Ma, Guo-Qiang Zhang, Jing-Hao Xue, Jen-Tzung Chien, Zhiqing Lin, Jun Guo

In order to explicitly characterize the nonnegative L1-norm constraint of the parameters, we further approximate the true posterior distribution by a Dirichlet distribution.

Fine-Grained Age Estimation in the wild with Attention LSTM Networks

no code implementations26 May 2018 Ke Zhang, Na Liu, Xingfang Yuan, Xinyao Guo, Ce Gao, Zhenbing Zhao, Zhanyu Ma

Then, we fine-tune the ResNets or the RoR on the target age datasets to extract the global features of face images.

 Ranked #1 on Age And Gender Classification on Adience Age (using extra training data)

Age And Gender Classification Age Estimation

SketchMate: Deep Hashing for Million-Scale Human Sketch Retrieval

1 code implementation CVPR 2018 Peng Xu, Yongye Huang, Tongtong Yuan, Kaiyue Pang, Yi-Zhe Song, Tao Xiang, Timothy M. Hospedales, Zhanyu Ma, Jun Guo

Key to our network design is the embedding of unique characteristics of human sketch, where (i) a two-branch CNN-RNN architecture is adapted to explore the temporal ordering of strokes, and (ii) a novel hashing loss is specifically designed to accommodate both the temporal and abstract traits of sketches.

Sketch Recognition

Decorrelation of Neutral Vector Variables: Theory and Applications

no code implementations30 May 2017 Zhanyu Ma, Jing-Hao Xue, Arne Leijon, Zheng-Hua Tan, Zhen Yang, Jun Guo

In this paper, we propose novel strategies for neutral vector variable decorrelation.

DNN Filter Bank Cepstral Coefficients for Spoofing Detection

no code implementations13 Feb 2017 Hong Yu, Zheng-Hua Tan, Zhanyu Ma, Jun Guo

In order to improve the reliability of speaker verification systems, we develop a new filter bank based cepstral feature, deep neural network filter bank cepstral coefficients (DNN-FBCC), to distinguish between natural and spoofed speech.

Speaker Verification Speech Synthesis

Cannot find the paper you are looking for? You can Submit a new open access paper.