Search Results for author: Jun Yu

Found 62 papers, 12 papers with code

Learning Disentangled Representations for Controllable Human Motion Prediction

no code implementations4 Jul 2022 Chunzhi Gu, Jun Yu, Chao Zhang

Specifically, the inductive bias imposed by the extra CVAE path encourages two latent variables in two paths to respectively govern separate representations for each partial-body motion.

Human motion prediction Inductive Bias +1

Understanding Robust Overfitting of Adversarial Training and Beyond

1 code implementation17 Jun 2022 Chaojian Yu, Bo Han, Li Shen, Jun Yu, Chen Gong, Mingming Gong, Tongliang Liu

Here, we explore the causes of robust overfitting by comparing the data distribution of \emph{non-overfit} (weak adversary) and \emph{overfitted} (strong adversary) adversarial training, and observe that the distribution of the adversarial data generated by weak adversary mainly contain small-loss data.

Adversarial Robustness Data Ablation

An optimal transport approach for selecting a representative subsample with application in efficient kernel density estimation

no code implementations31 May 2022 Jingyi Zhang, Cheng Meng, Jun Yu, Mengrui Zhang, Wenxuan Zhong, Ping Ma

Theoretically, we show the selected subsample can be used for efficient density estimation by deriving the convergence rate for the proposed subsample kernel density estimator.

Active Learning Density Estimation +1

Hilbert Curve Projection Distance for Distribution Comparison

no code implementations30 May 2022 Tao Li, Cheng Meng, Jun Yu, Hongteng Xu

Distribution comparison plays a central role in many machine learning tasks like data classification and generative modeling.

Efficient Approximation of Gromov-Wasserstein Distance using Importance Sparsification

no code implementations26 May 2022 Mengyu Li, Jun Yu, Hongteng Xu, Cheng Meng

As a valid metric of metric-measure spaces, Gromov-Wasserstein (GW) distance has shown the potential for the matching problems of structured data like point clouds and graphs.

Scene Clustering Based Pseudo-labeling Strategy for Multi-modal Aerial View Object Classification

no code implementations4 May 2022 Jun Yu, Hao Chang, Keda Lu, Liwen Zhang, Shenshen Du, Zhong Zhang

Multi-modal aerial view object classification (MAVOC) in Automatic target recognition (ATR), although an important and challenging problem, has been under studied.

Image Classification

Multi-model Ensemble Learning Method for Human Expression Recognition

no code implementations28 Mar 2022 Jun Yu, Zhongpeng Cai, Peng He, Guocheng Xie, Qiang Ling

Moreover, we introduce the multi-fold ensemble method to train and ensemble several models with the same architecture but different data distributions to enhance the performance of our solution.

Ensemble Learning

Hyper-relationship Learning Network for Scene Graph Generation

no code implementations15 Feb 2022 Yibing Zhan, Zhi Chen, Jun Yu, Baosheng Yu, DaCheng Tao, Yong Luo

As a result, HLN significantly improves the performance of scene graph generation by integrating and reasoning from object interactions, relationship interactions, and transitive inference of hyper-relationships.

Graph Attention Graph Generation +1

Wnet: Audio-Guided Video Object Segmentation via Wavelet-Based Cross-Modal Denoising Networks

1 code implementation CVPR 2022 Wenwen Pan, Haonan Shi, Zhou Zhao, Jieming Zhu, Xiuqiang He, Zhigeng Pan, Lianli Gao, Jun Yu, Fei Wu, Qi Tian

Audio-Guided video semantic segmentation is a challenging problem in visual analysis and editing, which automatically separates foreground objects from background in a video sequence according to the referring audio expressions.

Denoising Semantic Segmentation +2

Uncertainty Set Prediction of Aggregated Wind Power Generation based on Bayesian LSTM and Spatio-Temporal Analysis

no code implementations7 Oct 2021 Xiaopeng Li, Jiang Wu, Zhanbo Xu, Kun Liu, Jun Yu, Xiaohong Guan

This paper focuses on the uncertainty set prediction of the aggregated generation of geographically distributed wind farms.

Co-variance: Tackling Noisy Labels with Sample Selection by Emphasizing High-variance Examples

no code implementations29 Sep 2021 Xiaobo Xia, Bo Han, Yibing Zhan, Jun Yu, Mingming Gong, Chen Gong, Tongliang Liu

The sample selection approach is popular in learning with noisy labels, which tends to select potentially clean data out of noisy data for robust training.

Learning with noisy labels

ROSITA: Enhancing Vision-and-Language Semantic Alignments via Cross- and Intra-modal Knowledge Integration

1 code implementation16 Aug 2021 Yuhao Cui, Zhou Yu, Chunqi Wang, Zhongzhou Zhao, Ji Zhang, Meng Wang, Jun Yu

Nevertheless, most existing VLP approaches have not fully utilized the intrinsic knowledge within the image-text pairs, which limits the effectiveness of the learned alignments and further restricts the performance of their models.

BiSTF: Bilateral-Branch Self-Training Framework for Semi-Supervised Large-scale Fine-Grained Recognition

no code implementations14 Jul 2021 Hao Chang, Guochen Xie, Jun Yu, Qiang Ling

Semi-supervised Fine-Grained Recognition is a challenge task due to the difficulty of data imbalance, high inter-class similarity and domain mismatch.

A Weakly-Supervised Depth Estimation Network Using Attention Mechanism

no code implementations10 Jul 2021 Fang Gao, Jiabao Wang, Jun Yu, Yaoxiong Wang, Feng Shuang

It consists of a dense residual network structure, an adaptive weight channel attention (AWCA) module, a patch second non-local (PSNL) module and a soft label generation method.

Monocular Depth Estimation Scene Understanding

The Story in Your Eyes: An Individual-difference-aware Model for Cross-person Gaze Estimation

1 code implementation27 Jun 2021 Jun Bao, Buyu Liu, Jun Yu

We propose a novel method on refining cross-person gaze prediction task with eye/face images only by explicitly modelling the person-specific differences.

Gaze Estimation Gaze Prediction

Improving White-box Robustness of Pre-processing Defenses via Joint Adversarial Training

no code implementations10 Jun 2021 Dawei Zhou, Nannan Wang, Xinbo Gao, Bo Han, Jun Yu, Xiaoyu Wang, Tongliang Liu

However, pre-processing methods may suffer from the robustness degradation effect, in which the defense reduces rather than improving the adversarial robustness of a target model in a white-box setting.

Adversarial Defense Adversarial Robustness

Sample Selection with Uncertainty of Losses for Learning with Noisy Labels

no code implementations NeurIPS 2021 Xiaobo Xia, Tongliang Liu, Bo Han, Mingming Gong, Jun Yu, Gang Niu, Masashi Sugiyama

In this way, we also give large-loss but less selected data a try; then, we can better distinguish between the cases (a) and (b) by seeing if the losses effectively decrease with the uncertainty after the try.

Learning with noisy labels

Instance Correction for Learning with Open-set Noisy Labels

no code implementations1 Jun 2021 Xiaobo Xia, Tongliang Liu, Bo Han, Mingming Gong, Jun Yu, Gang Niu, Masashi Sugiyama

Lots of approaches, e. g., loss correction and label correction, cannot handle such open-set noisy labels well, since they need training data and test data to share the same label space, which does not hold for learning with open-set noisy labels.

Removing Adversarial Noise in Class Activation Feature Space

no code implementations ICCV 2021 Dawei Zhou, Nannan Wang, Chunlei Peng, Xinbo Gao, Xiaoyu Wang, Jun Yu, Tongliang Liu

Then, we train a denoising model to minimize the distances between the adversarial examples and the natural examples in the class activation feature space.

Adversarial Robustness Denoising

Comprehensive Graph-conditional Similarity Preserving Network for Unsupervised Cross-modal Hashing

1 code implementation25 Dec 2020 Jun Yu, Hao Zhou, Yibing Zhan, DaCheng Tao

Essentially, DGCPN addresses the inaccurate similarity problem by exploring and exploiting the data's intrinsic relationships in a graph.


Sufficient dimension reduction for classification using principal optimal transport direction

1 code implementation NeurIPS 2020 Cheng Meng, Jun Yu, Jingyi Zhang, Ping Ma, Wenxuan Zhong

The proposed method, named principal optimal transport direction (POTD), estimates the basis of the SDR subspace using the principal directions of the optimal transport coupling between the data respecting different response categories.

Classification Dimensionality Reduction +1

Learning Domain-invariant Graph for Adaptive Semi-supervised Domain Adaptation with Few Labeled Source Samples

no code implementations21 Aug 2020 Jinfeng Li, Weifeng Liu, Yicong Zhou, Jun Yu, Dapeng Tao

Traditional domain adaptation algorithms assume that enough labeled data, which are treated as the prior knowledge are available in the source domain.

Domain Adaptation Graph Learning

Retrieval of Family Members Using Siamese Neural Network

no code implementations30 May 2020 Jun Yu, Guochen Xie, Mengyan Li, Xinlong Hao

While in inference procedure, we try another similarity computing method by dropping the followed several fully connected layers and directly computing the cosine similarity of the two feature vectors.

Deep Fusion Siamese Network for Automatic Kinship Verification

no code implementations30 May 2020 Jun Yu, Mengyan Li, Xinlong Hao, Guochen Xie

Recognizing Families In the Wild (RFIW) is a challenging kinship recognition task with multiple tracks, which is based on Families in the Wild (FIW), a large-scale and comprehensive image database for automatic kinship recognition.

Optimal Distributed Subsampling for Maximum Quasi-Likelihood Estimators with Massive Data

no code implementations21 May 2020 Jun Yu, HaiYing Wang, Mingyao Ai, Huiming Zhang

We first derive optimal Poisson subsampling probabilities in the context of quasi-likelihood estimation under the A- and L-optimality criteria.

Deep Multimodal Neural Architecture Search

no code implementations25 Apr 2020 Zhou Yu, Yuhao Cui, Jun Yu, Meng Wang, DaCheng Tao, Qi Tian

Most existing works focus on a single task and design neural architectures manually, which are highly task-specific and hard to generalize to different tasks.

Neural Architecture Search Question Answering +3

Repulsive Mixture Models of Exponential Family PCA for Clustering

no code implementations7 Apr 2020 Maoying Qiao, Tongliang Liu, Jun Yu, Wei Bian, DaCheng Tao

To alleviate this problem, in this paper, a repulsiveness-encouraging prior is introduced among mixing components and a diversified EPCA mixture (DEPCAM) model is developed in the Bayesian framework.

Detecting Communities in Heterogeneous Multi-Relational Networks:A Message Passing based Approach

no code implementations6 Apr 2020 Maoying Qiao, Jun Yu, Wei Bian, DaCheng Tao

Specifically, an HMRNet is reorganized into a hierarchical structure with homogeneous networks as its layers and heterogeneous links connecting them.

Community Detection

Weakly-Supervised Multi-Level Attentional Reconstruction Network for Grounding Textual Queries in Videos

no code implementations16 Mar 2020 Yijun Song, Jingwen Wang, Lin Ma, Zhou Yu, Jun Yu

The task of temporally grounding textual queries in videos is to localize one video segment that semantically corresponds to the given query.

Multimodal Unified Attention Networks for Vision-and-Language Interactions

no code implementations12 Aug 2019 Zhou Yu, Yuhao Cui, Jun Yu, DaCheng Tao, Qi Tian

Learning an effective attention mechanism for multimodal data is important in many vision-and-language tasks that require a synergic understanding of both the visual and textual contents.

Question Answering Visual Grounding +2

Deep Modular Co-Attention Networks for Visual Question Answering

7 code implementations CVPR 2019 Zhou Yu, Jun Yu, Yuhao Cui, DaCheng Tao, Qi Tian

In this paper, we propose a deep Modular Co-Attention Network (MCAN) that consists of Modular Co-Attention (MCA) layers cascaded in depth.

Question Answering Visual Question Answering +1

Effective degrees of freedom for surface finish defect detection and classification

no code implementations20 Jun 2019 Natalya Pya Arnqvist, Blaise Ngendangenzwa, Eric Lindahl, Leif Nilsson, Jun Yu

One of the primary concerns of product quality control in the automotive industry is an automated detection of defects of small sizes on specular car body surfaces.

Defect Detection General Classification

Multimodal Transformer with Multi-View Visual Representation for Image Captioning

no code implementations20 May 2019 Jun Yu, Jing Li, Zhou Yu, Qingming Huang

Despite the success of existing studies, current methods only model the co-attention that characterizes the inter-modal interactions while neglecting the self-attention that characterizes the intra-modal interactions.

Image Captioning Machine Translation

Grand Challenge of 106-Point Facial Landmark Localization

no code implementations9 May 2019 Yinglu Liu, Hao Shen, Yue Si, Xiaobo Wang, Xiangyu Zhu, Hailin Shi, Zhibin Hong, Hanqi Guo, Ziyuan Guo, Yanqin Chen, Bi Li, Teng Xi, Jun Yu, Haonian Xie, Guochen Xie, Mengyan Li, Qing Lu, Zengfu Wang, Shenqi Lai, Zhenhua Chai, Xiaoming Wei

However, previous competitions on facial landmark localization (i. e., the 300-W, 300-VW and Menpo challenges) aim to predict 68-point landmarks, which are incompetent to depict the structure of facial components.

Face Alignment Face Recognition +2

On Exploring Undetermined Relationships for Visual Relationship Detection

no code implementations CVPR 2019 Yibing Zhan, Jun Yu, Ting Yu, DaCheng Tao

In this paper, we explore the beneficial effect of undetermined relationships on visual relationship detection.

Visual Relationship Detection

Local Deep-Feature Alignment for Unsupervised Dimension Reduction

no code implementations22 Apr 2019 Jian Zhang, Jun Yu, DaCheng Tao

Next, we exploit an affine transformation to align the local deep features of each neighbourhood with the global features.

Data Visualization Dimensionality Reduction

Single Pixel Reconstruction for One-stage Instance Segmentation

no code implementations16 Apr 2019 Jun Yu, Jinghan Yao, Jian Zhang, Zhou Yu, DaCheng Tao

In this paper, we propose a one-stage framework, SPRNet, which performs efficient instance segmentation by introducing a single pixel reconstruction (SPR) branch to off-the-shelf one-stage detectors.

Instance Segmentation Region Proposal +1

Adapting Stochastic Block Models to Power-Law Degree Distributions

no code implementations5 Apr 2019 Maoying Qiao, Jun Yu, Wei Bian, Qiang Li, DaCheng Tao

Stochastic block models (SBMs) have been playing an important role in modeling clusters or community structures of network data.

Cross-modal Subspace Learning via Kernel Correlation Maximization and Discriminative Structure Preserving

no code implementations26 Mar 2019 Jun Yu, Xiao-Jun Wu

Our model not only considers the inter-modality correlation by maximizing the kernel correlation but also preserves the semantically structural information within each modality.

Semantic Similarity Semantic Textual Similarity

Unsupervised Multi-modal Hashing for Cross-modal retrieval

no code implementations26 Mar 2019 Jun Yu, Xiao-Jun Wu

With the advantage of low storage cost and high efficiency, hashing learning has received much attention in the domain of Big Data.

Content-Based Image Retrieval Cross-Modal Retrieval +1

Discriminative Supervised Hashing for Cross-Modal similarity Search

no code implementations6 Dec 2018 Jun Yu, Xiao-Jun Wu, Josef Kittler

With the advantage of low storage cost and high retrieval efficiency, hashing techniques have recently been an emerging topic in cross-modal similarity search.

Cross-Modal Retrieval

Textually Guided Ranking Network for Attentional Image Retweet Modeling

no code implementations24 Oct 2018 Zhou Zhao, Hanbing Zhan, Lingtao Meng, Jun Xiao, Jun Yu, Min Yang, Fei Wu, Deng Cai

In this paper, we study the problem of image retweet prediction in social media, which predicts the image sharing behavior that the user reposts the image tweets from their followees.

Semi-supervised Hashing for Semi-Paired Cross-View Retrieval

no code implementations19 Jun 2018 Jun Yu, Xiao-Jun Wu, Josef Kittler

Recently, hashing techniques have gained importance in large-scale retrieval tasks because of their retrieval speed.

Deep Boosting of Diverse Experts

no code implementations ICLR 2018 Wei Zhang, Qiuyu Chen, Jun Yu, Jianping Fan

In this paper, a deep boosting algorithm is developed to learn more discriminative ensemble classifier by seamlessly combining a set of base deep CNNs (base experts) with diverse capabilities, e. g., these base deep CNNs are sequentially trained to recognize a set of object classes in an easy-to-hard way according to their learning complexities.

Object Recognition

Multi-modal Face Pose Estimation with Multi-task Manifold Deep Learning

no code implementations18 Dec 2017 Chaoqun Hong, Jun Yu

In the proposed deep learning based framework, Manifold Regularized Convolutional Layers (MRCL) improve traditional convolutional layers by learning the relationship among outputs of neurons.

Multi-Task Learning Pose Estimation +1

Towards Realistic Face Photo-Sketch Synthesis via Composition-Aided GANs

2 code implementations4 Dec 2017 Jun Yu, Xingxin Xu, Fei Gao, Shengjie Shi, Meng Wang, DaCheng Tao, Qingming Huang

Experimental results show that our method is capable of generating both visually comfortable and identity-preserving face sketches/photos over a wide range of challenging data.

 Ranked #1 on Face Sketch Synthesis on CUFS (FID metric)

Face Sketch Synthesis

Beyond Bilinear: Generalized Multimodal Factorized High-order Pooling for Visual Question Answering

2 code implementations10 Aug 2017 Zhou Yu, Jun Yu, Chenchao Xiang, Jianping Fan, DaCheng Tao

For fine-grained image and question representations, a `co-attention' mechanism is developed by using a deep neural network architecture to jointly learn the attentions for both the image and the question, which can allow us to reduce the irrelevant features effectively and obtain more discriminative features for image and question representations.

Question Answering Visual Question Answering +1

Multi-modal Factorized Bilinear Pooling with Co-Attention Learning for Visual Question Answering

6 code implementations ICCV 2017 Zhou Yu, Jun Yu, Jianping Fan, DaCheng Tao

For multi-modal feature fusion, here we develop a Multi-modal Factorized Bilinear (MFB) pooling approach to efficiently and effectively combine multi-modal features, which results in superior performance for VQA compared with other bilinear pooling approaches.

Question Answering Visual Question Answering +1

Embedding Visual Hierarchy with Deep Networks for Large-Scale Visual Recognition

no code implementations8 Jul 2017 Tianyi Zhao, Baopeng Zhang, Wei zhang, Ning Zhou, Jun Yu, Jianping Fan

Our LMM model can provide an end-to-end approach for jointly learning: (a) the deep networks to extract more discriminative deep features for image and object class representation; (b) the tree classifier for recognizing large numbers of object classes hierarchically; and (c) the visual hierarchy adaptation for achieving more accurate indexing of large numbers of object classes hierarchically.

Object Recognition

Deep Mixture of Diverse Experts for Large-Scale Visual Recognition

no code implementations24 Jun 2017 Tianyi Zhao, Jun Yu, Zhenzhong Kuang, Wei zhang, Jianping Fan

In this paper, a deep mixture of diverse experts algorithm is developed for seamlessly combining a set of base deep CNNs (convolutional neural networks) with diverse outputs (task spaces), e. g., such base deep CNNs are trained to recognize different subsets of tens of thousands of atomic object classes.

Multi-Task Learning Object Recognition

Constrained Low-Rank Learning Using Least Squares-Based Regularization

no code implementations15 Nov 2016 Ping Li, Jun Yu, Meng Wang, Luming Zhang, Deng Cai, Xuelong. Li

To achieve this goal, we cast the problem into a constrained rank minimization framework by adopting the least squares regularization.

General Classification Image Categorization +2

Bayesian and empirical Bayesian forests

no code implementations8 Feb 2015 Matt Taddy, Chun-Sheng Chen, Jun Yu, Mitch Wyle

We derive ensembles of decision trees through a nonparametric Bayesian model, allowing us to view random forests as samples from a posterior distribution.


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