Search Results for author: Kai Zhao

Found 56 papers, 19 papers with code

SRN-SZ: Deep Leaning-Based Scientific Error-bounded Lossy Compression with Super-resolution Neural Networks

no code implementations7 Sep 2023 Jinyang Liu, Sheng Di, Sian Jin, Kai Zhao, Xin Liang, Zizhong Chen, Franck Cappello

The fast growth of computational power and scales of modern super-computing systems have raised great challenges for the management of exascale scientific data.


RPG-Palm: Realistic Pseudo-data Generation for Palmprint Recognition

no code implementations26 Jul 2023 Lei Shen, Jianlong Jin, Ruixin Zhang, Huaen Li, Kai Zhao, Yingyi Zhang, Jingyun Zhang, Shouhong Ding, Yang Zhao, Wei Jia

Palmprint recently shows great potential in recognition applications as it is a privacy-friendly and stable biometric.

PartDiff: Image Super-resolution with Partial Diffusion Models

no code implementations21 Jul 2023 Kai Zhao, Alex Ling Yu Hung, Kaifeng Pang, Haoxin Zheng, Kyunghyun Sung

This observation inspired us to propose the Partial Diffusion Model (PartDiff), which diffuses the image to an intermediate latent state instead of pure random noise, where the intermediate latent state is approximated by the latent of diffusing the low-resolution image.

Denoising Image Generation +1

Improving Offline-to-Online Reinforcement Learning with Q-Ensembles

no code implementations12 Jun 2023 Kai Zhao, Yi Ma, Jianye Hao, Jinyi Liu, Yan Zheng, Zhaopeng Meng

Offline reinforcement learning (RL) is a learning paradigm where an agent learns from a fixed dataset of experience.

Offline RL reinforcement-learning +1

Node Embedding from Neural Hamiltonian Orbits in Graph Neural Networks

1 code implementation30 May 2023 Qiyu Kang, Kai Zhao, Yang song, Sijie Wang, Wee Peng Tay

In the graph node embedding problem, embedding spaces can vary significantly for different data types, leading to the need for different GNN model types.

Graph Embedding Link Prediction +1

Graph Neural Convection-Diffusion with Heterophily

1 code implementation26 May 2023 Kai Zhao, Qiyu Kang, Yang song, Rui She, Sijie Wang, Wee Peng Tay

Graph neural networks (GNNs) have shown promising results across various graph learning tasks, but they often assume homophily, which can result in poor performance on heterophilic graphs.

Graph Learning Node Classification

Leveraging Label Non-Uniformity for Node Classification in Graph Neural Networks

1 code implementation29 Apr 2023 Feng Ji, See Hian Lee, Hanyang Meng, Kai Zhao, Jielong Yang, Wee Peng Tay

We introduce the key notion of label non-uniformity, which is derived from the Wasserstein distance between the softmax distribution of the logits and the uniform distribution.

Node Classification

Zoom-VQA: Patches, Frames and Clips Integration for Video Quality Assessment

1 code implementation13 Apr 2023 Kai Zhao, Kun Yuan, Ming Sun, Xing Wen

Video quality assessment (VQA) aims to simulate the human perception of video quality, which is influenced by factors ranging from low-level color and texture details to high-level semantic content.

Video Quality Assessment Visual Question Answering (VQA)

Distributional Signals for Node Classification in Graph Neural Networks

no code implementations7 Apr 2023 Feng Ji, See Hian Lee, Kai Zhao, Wee Peng Tay, Jielong Yang

In graph neural networks (GNNs), both node features and labels are examples of graph signals, a key notion in graph signal processing (GSP).

Classification Node Classification

Node Embedding from Hamiltonian Information Propagation in Graph Neural Networks

no code implementations2 Mar 2023 Qiyu Kang, Kai Zhao, Yang song, Sijie Wang, Rui She, Wee Peng Tay

Graph neural networks (GNNs) have achieved success in various inference tasks on graph-structured data.

Quality-aware Pre-trained Models for Blind Image Quality Assessment

no code implementations CVPR 2023 Kai Zhao, Kun Yuan, Ming Sun, Mading Li, Xing Wen

Blind image quality assessment (BIQA) aims to automatically evaluate the perceived quality of a single image, whose performance has been improved by deep learning-based methods in recent years.

Blind Image Quality Assessment Self-Supervised Learning

A Pattern Discovery Approach to Multivariate Time Series Forecasting

no code implementations20 Dec 2022 Yunyao Cheng, Chenjuan Guo, KaiXuan Chen, Kai Zhao, Bin Yang, Jiandong Xie, Christian S. Jensen, Feiteng Huang, Kai Zheng

To capture the temporal and multivariate correlations among subsequences, we design a pattern discovery model, that constructs correlations via diverse pattern functions.

Multivariate Time Series Forecasting Time Series

Adaptive Control with Global Exponential Stability for Parameter-Varying Nonlinear Systems under Unknown Control Gains

no code implementations23 Oct 2022 Hefu Ye, Haijia Wu, Kai Zhao, Yongduan Song

It is nontrivial to achieve exponential stability even for time-invariant nonlinear systems with matched uncertainties and persistent excitation (PE) condition.

Learning an Efficient Multimodal Depth Completion Model

1 code implementation23 Aug 2022 Dewang Hou, Yuanyuan Du, Kai Zhao, Yang Zhao

With the wide application of sparse ToF sensors in mobile devices, RGB image-guided sparse depth completion has attracted extensive attention recently, but still faces some problems.

Depth Completion Depth Estimation +1

Fractional Vegetation Cover Estimation using Hough Lines and Linear Iterative Clustering

1 code implementation30 Apr 2022 Venkat Margapuri, Trevor Rife, Chaney Courtney, Brandon Schlautman, Kai Zhao, Mitchell Neilsen

This paper presents a new image processing algorithm to determine the amount of vegetation cover present in a given area, called fractional vegetation cover.


ContrastMask: Contrastive Learning to Segment Every Thing

1 code implementation CVPR 2022 Xuehui Wang, Kai Zhao, Ruixin Zhang, Shouhong Ding, Yan Wang, Wei Shen

In this framework, annotated masks of seen categories and pseudo masks of unseen categories serve as a prior for contrastive learning, where features from the mask regions (foreground) are pulled together, and are contrasted against those from the background, and vice versa.

Instance Segmentation Semi-Supervised Instance Segmentation

Geometric Synthesis: A Free lunch for Large-scale Palmprint Recognition Model Pretraining

no code implementations11 Mar 2022 Kai Zhao, Lei Shen, Yingyi Zhang, Chuhan Zhou, Tao Wang, Ruixin Zhang, Shouhong Ding, Wei Jia, Wei Shen

In this paper, by observing that palmar creases are the key information to deep-learning-based palmprint recognition, we propose to synthesize training data by manipulating palmar creases.

Multi-domain Collaborative Feature Representation for Robust Visual Object Tracking

no code implementations10 Aug 2021 Jiqing Zhang, Kai Zhao, Bo Dong, Yingkai Fu, Yuxin Wang, Xin Yang, BaoCai Yin

Jointly exploiting multiple different yet complementary domain information has been proven to be an effective way to perform robust object tracking.

Visual Object Tracking

Adaptive Feature Alignment for Adversarial Training

no code implementations31 May 2021 Tao Wang, Ruixin Zhang, Xingyu Chen, Kai Zhao, Xiaolin Huang, Yuge Huang, Shaoxin Li, Jilin Li, Feiyue Huang

Based on this observation, we propose the adaptive feature alignment (AFA) to generate features of arbitrary attacking strengths.

Adversarial Defense

Exploring Autoencoder-based Error-bounded Compression for Scientific Data

no code implementations25 May 2021 Jinyang Liu, Sheng Di, Kai Zhao, Sian Jin, Dingwen Tao, Xin Liang, Zizhong Chen, Franck Cappello

(1) We provide an in-depth investigation of the characteristics of various autoencoder models and develop an error-bounded autoencoder-based framework in terms of the SZ model.

Image Compression

FakeMix Augmentation Improves Transparent Object Detection

1 code implementation24 Mar 2021 Yang Cao, Zhengqiang Zhang, Enze Xie, Qibin Hou, Kai Zhao, Xiangui Luo, Jian Tuo

However, these methods usually encounter boundary-related imbalance problem, leading to limited generation capability.

Data Augmentation object-detection +2

cuSZ: An Efficient GPU-Based Error-Bounded Lossy Compression Framework for Scientific Data

2 code implementations19 Jul 2020 Jiannan Tian, Sheng Di, Kai Zhao, Cody Rivera, Megan Hickman Fulp, Robert Underwood, Sian Jin, Xin Liang, Jon Calhoun, Dingwen Tao, Franck Cappello

To the best of our knowledge, cuSZ is the first error-bounded lossy compressor on GPUs for scientific data.

Distributed, Parallel, and Cluster Computing

Dependency Aware Filter Pruning

no code implementations6 May 2020 Kai Zhao, Xin-Yu Zhang, Qi Han, Ming-Ming Cheng

Convolutional neural networks (CNNs) are typically over-parameterized, bringing considerable computational overhead and memory footprint in inference.

FT-CNN: Algorithm-Based Fault Tolerance for Convolutional Neural Networks

no code implementations27 Mar 2020 Kai Zhao, Sheng Di, Sihuan Li, Xin Liang, Yujia Zhai, Jieyang Chen, Kaiming Ouyang, Franck Cappello, Zizhong Chen

(1) We propose several systematic ABFT schemes based on checksum techniques and analyze their fault protection ability and runtime thoroughly. Unlike traditional ABFT based on matrix-matrix multiplication, our schemes support any convolution implementations.

Deep Hough Transform for Semantic Line Detection

2 code implementations ECCV 2020 Kai Zhao, Qi Han, Chang-Bin Zhang, Jun Xu, Ming-Ming Cheng

In addition to the proposed method, we design an evaluation metric to assess the quality of line detection and construct a large scale dataset for the line detection task.

Line Detection object-detection

Structured Sparsification with Joint Optimization of Group Convolution and Channel Shuffle

1 code implementation19 Feb 2020 Xin-Yu Zhang, Kai Zhao, Taihong Xiao, Ming-Ming Cheng, Ming-Hsuan Yang

Recent advances in convolutional neural networks(CNNs) usually come with the expense of excessive computational overhead and memory footprint.

Network Pruning

Deep Differentiable Random Forests for Age Estimation

no code implementations23 Jul 2019 Wei Shen, Yilu Guo, Yan Wang, Kai Zhao, Bo wang, Alan Yuille

Both of them connect split nodes to the top layer of convolutional neural networks (CNNs) and deal with inhomogeneous data by jointly learning input-dependent data partitions at the split nodes and age distributions at the leaf nodes.

Age Estimation regression

RegularFace: Deep Face Recognition via Exclusive Regularization

no code implementations CVPR 2019 Kai Zhao, Jingyi Xu, Ming-Ming Cheng

We consider the face recognition task where facial images of the same identity (person) is expected to be closer in the representation space, while different identities be far apart.

Face Recognition

Translate-to-Recognize Networks for RGB-D Scene Recognition

1 code implementation CVPR 2019 Dapeng Du, Li-Min Wang, Huiling Wang, Kai Zhao, Gangshan Wu

Empirically, we verify that this new semi-supervised setting is able to further enhance the performance of recognition network.

Scene Recognition Translation

Res2Net: A New Multi-scale Backbone Architecture

24 code implementations2 Apr 2019 Shang-Hua Gao, Ming-Ming Cheng, Kai Zhao, Xin-Yu Zhang, Ming-Hsuan Yang, Philip Torr

We evaluate the Res2Net block on all these models and demonstrate consistent performance gains over baseline models on widely-used datasets, e. g., CIFAR-100 and ImageNet.

Image Classification Instance Segmentation +4

When to Finish? Optimal Beam Search for Neural Text Generation (modulo beam size)

no code implementations EMNLP 2017 Liang Huang, Kai Zhao, Mingbo Ma

In neural text generation such as neural machine translation, summarization, and image captioning, beam search is widely used to improve the output text quality.

Image Captioning Machine Translation +2

Hifi: Hierarchical feature integration for skeleton detection

no code implementations1 Jul 2018 Kai Zhao, Wei Shen, ShangHua Gao, Dandan Li, Ming-Ming Cheng

In natural images, the scales (thickness) of object skeletons may dramatically vary among objects and object parts.

Object Skeleton Detection

Optimizing the F-measure for Threshold-free Salient Object Detection

no code implementations ICCV 2019 Kai Zhao, Shang-Hua Gao, Wenguan Wang, Ming-Ming Cheng

By reformulating the standard F-measure we propose the relaxed F-measure which is differentiable w. r. t the posterior and can be easily appended to the back of CNNs as the loss function.

object-detection RGB Salient Object Detection +1

Hi-Fi: Hierarchical Feature Integration for Skeleton Detection

no code implementations5 Jan 2018 Kai Zhao, Wei Shen, Shang-Hua Gao, Dandan Li, Ming-Ming Cheng

In natural images, the scales (thickness) of object skeletons may dramatically vary among objects and object parts, making object skeleton detection a challenging problem.

Object Skeleton Detection

OSU Multimodal Machine Translation System Report

no code implementations WS 2017 Mingbo Ma, Dapeng Li, Kai Zhao, Liang Huang

This paper describes Oregon State University's submissions to the shared WMT'17 task "multimodal translation task I".

Image Captioning Multimodal Machine Translation +1

Jointly Trained Sequential Labeling and Classification by Sparse Attention Neural Networks

no code implementations28 Sep 2017 Mingbo Ma, Kai Zhao, Liang Huang, Bing Xiang, Bo-Wen Zhou

In order to utilize the potential benefits from their correlations, we propose a jointly trained model for learning the two tasks simultaneously via Long Short-Term Memory (LSTM) networks.

Classification General Classification +9

Joint Syntacto-Discourse Parsing and the Syntacto-Discourse Treebank

1 code implementation EMNLP 2017 Kai Zhao, Liang Huang

Discourse parsing has long been treated as a stand-alone problem independent from constituency or dependency parsing.

Dependency Parsing Discourse Parsing

Label Distribution Learning Forests

no code implementations NeurIPS 2017 Wei Shen, Kai Zhao, Yilu Guo, Alan Yuille

This paper presents label distribution learning forests (LDLFs) - a novel label distribution learning algorithm based on differentiable decision trees, which have several advantages: 1) Decision trees have the potential to model any general form of label distributions by a mixture of leaf node predictions.

Representation Learning

Textual Entailment with Structured Attentions and Composition

1 code implementation COLING 2016 Kai Zhao, Liang Huang, Mingbo Ma

We show that it is beneficial to extend the attention model to tree nodes between premise and hypothesis.

Natural Language Inference

DeepSkeleton: Learning Multi-task Scale-associated Deep Side Outputs for Object Skeleton Extraction in Natural Images

1 code implementation13 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.

Multi-Task Learning object-detection +2

Object Skeleton Extraction in Natural Images by Fusing Scale-associated Deep Side Outputs

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.

object-detection Object Detection

Type-Driven Incremental Semantic Parsing with Polymorphism

no code implementations HLT 2015 Kai Zhao, Liang Huang

Semantic parsing has made significant progress, but most current semantic parsers are extremely slow (CKY-based) and rather primitive in representation.

Semantic Parsing Vocal Bursts Type Prediction

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