Search Results for author: Kun Zhao

Found 51 papers, 15 papers with code

GRAPHMOE: Amplifying Cognitive Depth of Mixture-of-Experts Network via Introducing Self-Rethinking Mechanism

no code implementations14 Jan 2025 Chen Tang, Bo Lv, Zifan Zheng, Bohao Yang, Kun Zhao, Ning Liao, Xiaoxing Wang, Feiyu Xiong, Zhiyu Li, Nayu Liu, Jingchi Jiang

Additionally, this study explores a novel recurrent routing strategy that may inspire further advancements in enhancing the reasoning capabilities of language models.

CASPFormer: Trajectory Prediction from BEV Images with Deformable Attention

no code implementations26 Sep 2024 Harsh Yadav, Maximilian Schaefer, Kun Zhao, Tobias Meisen

Motion prediction is an important aspect for Autonomous Driving (AD) and Advance Driver Assistance Systems (ADAS).

Autonomous Driving motion prediction +2

Predicting T-Cell Receptor Specificity

no code implementations27 Jul 2024 Tengyao Tu, Wei Zeng, Kun Zhao, Zhenyu Zhang

The result proves that adding a classifier to the model based on the random forest algorithm is very effective, and our model generally outperforms ordinary deep learning methods.

Deep Learning Specificity

Panoptic Segmentation of Mammograms with Text-To-Image Diffusion Model

no code implementations19 Jul 2024 Kun Zhao, Jakub Prokop, Javier Montalt Tordera, Sadegh Mohammadi

We aim to harness their capabilities for breast lesion segmentation in a panoptic setting, which encompasses both semantic and instance-level predictions.

Image Generation Instance Segmentation +3

BioMNER: A Dataset for Biomedical Method Entity Recognition

no code implementations28 Jun 2024 Chen Tang, Bohao Yang, Kun Zhao, Bo Lv, Chenghao Xiao, Frank Guerin, Chenghua Lin

Named entity recognition (NER) stands as a fundamental and pivotal task within the realm of Natural Language Processing.

Information Retrieval named-entity-recognition +2

X-ray Made Simple: Radiology Report Generation and Evaluation with Layman's Terms

1 code implementation25 Jun 2024 Kun Zhao, Chenghao Xiao, Chen Tang, Bohao Yang, Kai Ye, Noura Al Moubayed, Liang Zhan, Chenghua Lin

Last, we show that training on the layman's terms dataset encourages models to focus on the semantics of the reports, as opposed to overfitting to learning the report templates.

Crafting Customisable Characters with LLMs: Introducing SimsChat, a Persona-Driven Role-Playing Agent Framework

1 code implementation25 Jun 2024 Bohao Yang, Dong Liu, Chenghao Xiao, Kun Zhao, Chen Tang, Chao Li, Lin Yuan, Guang Yang, Lanxiao Huang, Chenghua Lin

Large Language Models (LLMs) demonstrate remarkable ability to comprehend instructions and generate human-like text, enabling sophisticated agent simulation beyond basic behavior replication.

SLIDE: A Framework Integrating Small and Large Language Models for Open-Domain Dialogues Evaluation

1 code implementation24 May 2024 Kun Zhao, Bohao Yang, Chen Tang, Chenghua Lin, Liang Zhan

Our approach introduces several techniques: (1) Contrastive learning to differentiate between robust and non-robust response embeddings; (2) A novel metric for semantic sensitivity that combines embedding cosine distances with similarity learned through neural networks, and (3) a strategy for incorporating the evaluation results from both the SLM and LLMs.

Contrastive Learning Dialogue Evaluation

Interpretable Spatio-Temporal Embedding for Brain Structural-Effective Network with Ordinary Differential Equation

no code implementations21 May 2024 Haoteng Tang, Guodong Liu, Siyuan Dai, Kai Ye, Kun Zhao, Wenlu Wang, Carl Yang, Lifang He, Alex Leow, Paul Thompson, Heng Huang, Liang Zhan

The MRI-derived brain network serves as a pivotal instrument in elucidating both the structural and functional aspects of the brain, encompassing the ramifications of diseases and developmental processes.

Graph Learning

Emphasising Structured Information: Integrating Abstract Meaning Representation into LLMs for Enhanced Open-Domain Dialogue Evaluation

1 code implementation1 Apr 2024 Bohao Yang, Kun Zhao, Chen Tang, Dong Liu, Liang Zhan, Chenghua Lin

Trainable evaluation metrics, typically trained with true positive and randomly selected negative responses, tend to assign higher scores to responses that share greater content similarity with a given context.

Abstract Meaning Representation Dialogue Evaluation +2

Spatially Selective Reconfigurable Intelligent Surfaces Through Element Permutation

no code implementations6 Mar 2024 Fredrik Rusek, Jose Flordelis, Kun Zhao, Erik Bengtsson, Olof Zander

The goal of this paper is to propose a RIS which \emph{only} reflects signals from the configured impinging direction.

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

1 code implementation22 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 +3

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.

class-incremental learning Data Augmentation +3

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 +1

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 Prediction +1

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 Conversational Recommendation +3

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.

Deep Learning

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.

regression

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 +5

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.

Optics

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").

Philosophy

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.

Attribute

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.

Clustering

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.

Prediction Time Series +1

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.