Search Results for author: Kun Zhao

Found 40 papers, 10 papers with code

Constrained Multiview Representation for Self-supervised Contrastive Learning

no code implementations5 Feb 2024 Siyuan Dai, Kai Ye, Kun Zhao, Ge Cui, Haoteng Tang, Liang Zhan

In this work, we introduce a novel approach predicated on representation distance-based mutual information (MI) maximization for measuring the significance of different views, aiming at conducting more efficient contrastive learning and representation disentanglement.

Contrastive Learning Disentanglement +4

Effective Distillation of Table-based Reasoning Ability from LLMs

no code implementations22 Sep 2023 Bohao Yang, Chen Tang, Kun Zhao, Chenghao Xiao, Chenghua Lin

Large Language Models (LLMs) have demonstrated remarkable performance across a wide range of natural language processing tasks.

Table-to-Text Generation

CASPNet++: Joint Multi-Agent Motion Prediction

no code implementations15 Aug 2023 Maximilian Schäfer, Kun Zhao, Anton Kummert

In this work, we focus on further enhancing the interaction modeling and scene understanding to support the joint prediction of all road users in a scene using spatiotemporal grids to model future occupancy.

Autonomous Driving motion prediction +1

Evaluating Open-Domain Dialogues in Latent Space with Next Sentence Prediction and Mutual Information

1 code implementation26 May 2023 Kun Zhao, Bohao Yang, Chenghua Lin, Wenge Rong, Aline Villavicencio, Xiaohui Cui

The long-standing one-to-many issue of the open-domain dialogues poses significant challenges for automatic evaluation methods, i. e., there may be multiple suitable responses which differ in semantics for a given conversational context.

Semantic Similarity Semantic Textual Similarity +1

Credible Remote Sensing Scene Classification Using Evidential Fusion on Aerial-Ground Dual-view Images

1 code implementation2 Jan 2023 Kun Zhao, Qian Gao, Siyuan Hao, Jie Sun, Lijian Zhou

Based on this uncertainty, a novel decision-level fusion strategy is proposed to ensure that the view with lower risk obtains more weight, making the classification more credible.

Decision Making Scene Classification

Few-Shot Class-Incremental Learning from an Open-Set Perspective

1 code implementation30 Jul 2022 Can Peng, Kun Zhao, Tianren Wang, Meng Li, Brian C. Lovell

The continual appearance of new objects in the visual world poses considerable challenges for current deep learning methods in real-world deployments.

Data Augmentation Face Recognition +2

Unsupervised Quantized Prosody Representation for Controllable Speech Synthesis

no code implementations7 Apr 2022 Yutian Wang, Yuankun Xie, Kun Zhao, Hui Wang, Qin Zhang

In this paper, we propose a novel prosody disentangle method for prosodic Text-to-Speech (TTS) model, which introduces the vector quantization (VQ) method to the auxiliary prosody encoder to obtain the decomposed prosody representations in an unsupervised manner.

Quantization Speech Synthesis

Context-Aware Scene Prediction Network (CASPNet)

no code implementations18 Jan 2022 Maximilian Schäfer, Kun Zhao, Markus Bühren, Anton Kummert

Predicting the future motion of surrounding road users is a crucial and challenging task for autonomous driving (AD) and various advanced driver-assistance systems (ADAS).

Autonomous Driving

DIODE: Dilatable Incremental Object Detection

no code implementations12 Aug 2021 Can Peng, Kun Zhao, Sam Maksoud, Tianren Wang, Brian C. Lovell

In this paper, we aim to alleviate this performance decay on multi-step incremental detection tasks by proposing a dilatable incremental object detector (DIODE).

Incremental Learning Object +2

Cascaded Residual Density Network for Crowd Counting

no code implementations29 Jul 2021 Kun Zhao, Luchuan Song, Bin Liu, Qi Chu, Nenghai Yu

Crowd counting is a challenging task due to the issues such as scale variation and perspective variation in real crowd scenes.

Crowd Counting

Improving Conversational Recommendation System by Pretraining on Billions Scale of Knowledge Graph

no code implementations30 Apr 2021 Chi-Man Wong, Fan Feng, Wen Zhang, Chi-Man Vong, Hui Chen, Yichi Zhang, Peng He, Huan Chen, Kun Zhao, Huajun Chen

We first construct a billion-scale conversation knowledge graph (CKG) from information about users, items and conversations, and then pretrain CKG by introducing knowledge graph embedding method and graph convolution network to encode semantic and structural information respectively. To make the CTR prediction model sensible of current state of users and the relationship between dialogues and items, we introduce user-state and dialogue-interaction representations based on pre-trained CKG and propose K-DCN. In K-DCN, we fuse the user-state representation, dialogue-interaction representation and other normal feature representations via deep cross network, which will give the rank of candidate items to be recommended. We experimentally prove that our proposal significantly outperforms baselines and show it's real application in Alime.

Click-Through Rate Prediction Knowledge Graph Embedding +1

Scalable Bayesian Deep Learning with Kernel Seed Networks

no code implementations19 Apr 2021 Sam Maksoud, Kun Zhao, Can Peng, Brian C. Lovell

To address this problem we present a method for performing BDL, namely Kernel Seed Networks (KSN), which does not require a 2-fold increase in the number of parameters.

Genetic Algorithm based hyper-parameters optimization for transfer Convolutional Neural Network

no code implementations26 Feb 2021 Chen Li, JinZhe Jiang, YaQian Zhao, RenGang Li, EnDong Wang, Xin Zhang, Kun Zhao

Decision of transfer layers and trainable layers is a major task for design of the transfer convolutional neural networks (CNN).

Hyperparameter Optimization

Polynomial Trajectory Predictions for Improved Learning Performance

no code implementations29 Jan 2021 Ido Freeman, Kun Zhao, Anton Kummert

The rising demand for Active Safety systems in automotive applications stresses the need for a reliable short to mid-term trajectory prediction.

Trajectory Prediction

Eliminating the Barriers: Demystifying Wi-Fi Baseband Design and Introducing the PicoScenes Wi-Fi Sensing Platform

2 code implementations20 Oct 2020 Zhiping Jiang, Tom H. Luan, Han Hao, Jing Wang, Xincheng Ren, Kun Zhao, Wei Xi, Yueshen Xu, Rui Li

Three barriers always hamper the research: unknown baseband design and its influence, inadequate hardware, and the lack of versatile and flexible measurement software.

Hardware Architecture

Bounding Boxes Are All We Need: Street View Image Classification via Context Encoding of Detected Buildings

1 code implementation3 Oct 2020 Kun Zhao, Yongkun Liu, Siyuan Hao, Shaoxing Lu, Hongbin Liu, Lijian Zhou

Instead of using visual features of the whole image directly as common image-level models based on convolutional neural networks (CNNs) do, the proposed framework firstly obtains the bounding boxes of buildings in street view images from a detector.

General Classification Image Classification

SOS: Selective Objective Switch for Rapid Immunofluorescence Whole Slide Image Classification

1 code implementation CVPR 2020 Sam Maksoud, Kun Zhao, Peter Hobson, Anthony Jennings, Brian Lovell

The difficulty of processing gigapixel whole slide images (WSIs) in clinical microscopy has been a long-standing barrier to implementing computer aided diagnostic systems.

General Classification Image Classification +1

Faster ILOD: Incremental Learning for Object Detectors based on Faster RCNN

1 code implementation9 Mar 2020 Can Peng, Kun Zhao, Brian C. Lovell

To address this problem, incremental learning methods have been explored which preserve the old knowledge of deep learning models.

Incremental Learning Knowledge Distillation +2

To What Extent Does Downsampling, Compression, and Data Scarcity Impact Renal Image Analysis?

no code implementations22 Sep 2019 Can Peng, Kun Zhao, Arnold Wiliem, Teng Zhang, Peter Hobson, Anthony Jennings, Brian C. Lovell

Critical findings are observed: (1) The best balance between detection accuracy, detection speed and file size is achieved at 8 times downsampling captured with a $40\times$ objective; (2) compression which reduces the file size dramatically, does not necessarily have an adverse effect on overall accuracy; (3) reducing the amount of training data to some extents causes a drop in precision but has a negligible impact on the recall; (4) in most cases, Faster R-CNN achieves the best accuracy in the glomerulus detection task.

Image Compression

Visual analytics for team-based invasion sports with significant events and Markov reward process

no code implementations2 Jul 2019 Kun Zhao, Takayuki Osogami, Tetsuro Morimura

To solve this problem, we consider a whole match as a Markov chain of significant events, so that event values can be estimated with a continuous parameter space by solving the Markov chain with a machine learning model.

CORAL8: Concurrent Object Regression for Area Localization in Medical Image Panels

no code implementations24 Jun 2019 Sam Maksoud, Arnold Wiliem, Kun Zhao, Teng Zhang, Lin Wu, Brian C. Lovell

This is because the system can ignore the attention mechanism by assigning equal weights for all members.


Deep Instance-Level Hard Negative Mining Model for Histopathology Images

1 code implementation24 Jun 2019 Meng Li, Lin Wu, Arnold Wiliem, Kun Zhao, Teng Zhang, Brian C. Lovell

Histopathology image analysis can be considered as a Multiple instance learning (MIL) problem, where the whole slide histopathology image (WSI) is regarded as a bag of instances (i. e, patches) and the task is to predict a single class label to the WSI.

General Classification Multiple Instance Learning

AliGraph: A Comprehensive Graph Neural Network Platform

no code implementations23 Feb 2019 Rong Zhu, Kun Zhao, Hongxia Yang, Wei. Lin, Chang Zhou, Baole Ai, Yong Li, Jingren Zhou

An increasing number of machine learning tasks require dealing with large graph datasets, which capture rich and complex relationship among potentially billions of elements.

Distributed, Parallel, and Cluster Computing

Convex Class Model on Symmetric Positive Definite Manifolds

no code implementations14 Jun 2018 Kun Zhao, Arnold Wiliem, Shaokang Chen, Brian C. Lovell

Our proposed framework, named Manifold Convex Class Model, represents each class on SPD manifolds using a convex model, and classification can be performed by computing distances to the convex models.

Classification General Classification +4

SlideNet: Fast and Accurate Slide Quality Assessment Based on Deep Neural Networks

no code implementations20 Mar 2018 Teng Zhang, Johanna Carvajal, Daniel F. Smith, Kun Zhao, Arnold Wiliem, Peter Hobson, Anthony Jennings, Brian C. Lovell

In order to address the quality assessment problem, we propose a deep neural network based framework to automatically assess the slide quality in a semantic way.


Structured Illumination in Spatial-Orientational Hyperspace

1 code implementation14 Dec 2017 Karl Zhanghao, Xingye Chen, Wenhui Liu, Meiqi Li, Chunyan Shan, Xiao Wang, Kun Zhao, Amit Lai, Hao Xie, Qionghai Dai, Peng Xi

The dipole nature of chromophore is important for both super-resolution microscopy and imaging molecular structure, which is nevertheless neglected in most microscopies, even including structured illumination microscopy (SIM) with polarized excitations.


Topic Modeling the Hàn diăn Ancient Classics

no code implementations2 Feb 2017 Colin Allen, Hongliang Luo, Jaimie Murdock, Jianghuai Pu, XiaoHong Wang, Yanjie Zhai, Kun Zhao

In this paper we describe a collaborative effort between Indiana University and Xi'an Jiaotong University to support exploration and interpretation of a digital corpus of over 18, 000 ancient Chinese documents, which we refer to as the "Handian" ancient classics corpus (H\`an di\u{a}n g\u{u} j\'i, i. e, the "Han canon" or "Chinese classics").


Determining the best attributes for surveillance video keywords generation

no code implementations21 Feb 2016 Liangchen Liu, Arnold Wiliem, Shaokang Chen, Kun Zhao, Brian C. Lovell

In this paper, we propose a novel approach, based on the shared structure exhibited amongst meaningful attributes, that enables us to compare between different automatic attribute discovery approaches. We then validate our approach by comparing various attribute discovery methods such as PiCoDeS on two attribute datasets.


Efficient Clustering on Riemannian Manifolds: A Kernelised Random Projection Approach

no code implementations18 Sep 2015 Kun Zhao, Azadeh Alavi, Arnold Wiliem, Brian C. Lovell

We then validate our framework on several computer vision applications by comparing against popular clustering methods on Riemannian manifolds.


Temporal Embedding in Convolutional Neural Networks for Robust Learning of Abstract Snippets

no code implementations18 Feb 2015 Jiajun Liu, Kun Zhao, Brano Kusy, Ji-Rong Wen, Raja Jurdak

The prediction of periodical time-series remains challenging due to various types of data distortions and misalignments.

Time Series Time Series Analysis

Random Projections on Manifolds of Symmetric Positive Definite Matrices for Image Classification

no code implementations4 Mar 2014 Azadeh Alavi, Arnold Wiliem, Kun Zhao, Brian C. Lovell, Conrad Sanderson

Recent advances suggest that encoding images through Symmetric Positive Definite (SPD) matrices and then interpreting such matrices as points on Riemannian manifolds can lead to increased classification performance.

Face Recognition General Classification +3

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