Search Results for author: Han Zhang

Found 62 papers, 29 papers with code

Vector-quantized Image Modeling with Improved VQGAN

no code implementations9 Oct 2021 Jiahui Yu, Xin Li, Jing Yu Koh, Han Zhang, Ruoming Pang, James Qin, Alexander Ku, Yuanzhong Xu, Jason Baldridge, Yonghui Wu

Motivated by this success, we explore a Vector-quantized Image Modeling (VIM) approach that involves pretraining a Transformer to predict rasterized image tokens autoregressively.

Image Generation Transfer Learning +1

DeepAID: Interpreting and Improving Deep Learning-based Anomaly Detection in Security Applications

1 code implementation23 Sep 2021 Dongqi Han, Zhiliang Wang, Wenqi Chen, Ying Zhong, Su Wang, Han Zhang, Jiahai Yang, Xingang Shi, Xia Yin

Experimental results show that DeepAID can provide high-quality interpretations for unsupervised DL models while meeting the special requirements of security domains.

Anomaly Detection

Deep Image Synthesis from Intuitive User Input: A Review and Perspectives

no code implementations9 Jul 2021 Yuan Xue, Yuan-Chen Guo, Han Zhang, Tao Xu, Song-Hai Zhang, Xiaolei Huang

In many applications of computer graphics, art and design, it is desirable for a user to provide intuitive non-image input, such as text, sketch, stroke, graph or layout, and have a computer system automatically generate photo-realistic images that adhere to the input content.

Image Generation Image Retrieval

ViTGAN: Training GANs with Vision Transformers

1 code implementation9 Jul 2021 Kwonjoon Lee, Huiwen Chang, Lu Jiang, Han Zhang, Zhuowen Tu, Ce Liu

Recently, Vision Transformers (ViTs) have shown competitive performance on image recognition while requiring less vision-specific inductive biases.

Image Generation

SearchGCN: Powering Embedding Retrieval by Graph Convolution Networks for E-Commerce Search

no code implementations1 Jul 2021 Xinlin Xia, Shang Wang, Han Zhang, Songlin Wang, Sulong Xu, Yun Xiao, Bo Long, Wen-Yun Yang

Graph convolution networks (GCN), which recently becomes new state-of-the-art method for graph node classification, recommendation and other applications, has not been successfully applied to industrial-scale search engine yet.

Node Classification

Improved Transformer for High-Resolution GANs

no code implementations14 Jun 2021 Long Zhao, Zizhao Zhang, Ting Chen, Dimitris N. Metaxas, Han Zhang

Attention-based models, exemplified by the Transformer, can effectively model long range dependency, but suffer from the quadratic complexity of self-attention operation, making them difficult to be adopted for high-resolution image generation based on Generative Adversarial Networks (GANs).

Image Generation

Aggregating Nested Transformers

3 code implementations26 May 2021 Zizhao Zhang, Han Zhang, Long Zhao, Ting Chen, Tomas Pfister

In this work, we explore the idea of nesting basic local transformers on non-overlapping image blocks and aggregating them in a hierarchical manner.

Image Classification Image Generation

Joint Learning of Deep Retrieval Model and Product Quantization based Embedding Index

1 code implementation9 May 2021 Han Zhang, Hongwei Shen, Yiming Qiu, Yunjiang Jiang, Songlin Wang, Sulong Xu, Yun Xiao, Bo Long, Wen-Yun Yang

Embedding index that enables fast approximate nearest neighbor(ANN) search, serves as an indispensable component for state-of-the-art deep retrieval systems.


Learning Hamiltonian dynamics by reservoir computer

no code implementations24 Apr 2021 Han Zhang, Huawei Fan, Liang Wang, Xingang Wang

Reconstructing the KAM dynamics diagram of Hamiltonian system from the time series of a limited number of parameters is an outstanding question in nonlinear science, especially when the Hamiltonian governing the system dynamics are unknown.

Time Series

Transfer training from smaller language model

no code implementations23 Apr 2021 Han Zhang

We initialize a larger target model from a smaller source model by copy weight values from source model and padding with zeros or small initialization values on it to make the source and target model have approximate outputs, which is valid due to block matrix multiplication and residual connection in transformer structure.

Language Modelling

Revisiting Hierarchical Approach for Persistent Long-Term Video Prediction

1 code implementation ICLR 2021 Wonkwang Lee, Whie Jung, Han Zhang, Ting Chen, Jing Yu Koh, Thomas Huang, Hyungsuk Yoon, Honglak Lee, Seunghoon Hong

Despite the recent advances in the literature, existing approaches are limited to moderately short-term prediction (less than a few seconds), while extrapolating it to a longer future quickly leads to destruction in structure and content.

Translation Video Prediction

A Multiscale Graph Convolutional Network for Change Detection in Homogeneous and Heterogeneous Remote Sensing Images

no code implementations16 Feb 2021 Junzheng Wu, Biao Li, Yao Qin, Weiping Ni, Han Zhang, Yuli Sun

In this paper, a novel CD method based on the graph convolutional network (GCN) and multiscale object-based technique is proposed for both homogeneous and heterogeneous images.

Modeling Heterogeneous Statistical Patterns in High-dimensional Data by Adversarial Distributions: An Unsupervised Generative Framework

1 code implementation15 Dec 2020 Han Zhang, Wenhao Zheng, Charley Chen, Kevin Gao, Yao Hu, Ling Huang, Wei Xu

Meanwhile, such applications usually require modeling the intrinsic clusters in high-dimensional data, which usually displays heterogeneous statistical patterns as the patterns of different clusters may appear in different dimensions.

Anomaly Detection Fraud Detection

Transfer learning of chaotic systems

no code implementations15 Nov 2020 Yali Guo, Han Zhang, Liang Wang, Huawei Fan, Xingang Wang

Here we investigate transfer learning of chaotic systems from the perspective of synchronization-based state inference, in which a reservoir computer trained by chaotic system A is used to infer the unmeasured variables of chaotic system B, while A is different from B in either parameter or dynamics.

Time Series Transfer Learning

Co-evolution of Functional Brain Network at Multiple Scales during Early Infancy

no code implementations15 Sep 2020 Xuyun Wen, Liming Hsu, Weili Lin, Han Zhang, Dinggang Shen

By applying our proposed methodological framework on the collected longitudinal infant dataset, we provided the first evidence that, in the first 2 years of life, the brain functional network is co-evolved at different scales, where each scale displays the unique reconfiguration pattern in terms of modular organization.

GloDyNE: Global Topology Preserving Dynamic Network Embedding

2 code implementations5 Aug 2020 Chengbin Hou, Han Zhang, Shan He, Ke Tang

The main and common objective of Dynamic Network Embedding (DNE) is to efficiently update node embeddings while preserving network topology at each time step.

Graph Reconstruction Incremental Learning +1

Improving NER's Performance with Massive financial corpus

1 code implementation31 Jul 2020 Han Zhang

Training large deep neural networks needs massive high quality annotation data, but the time and labor costs are too expensive for small business.

Language Modelling

From Spectrum Wavelet to Vertex Propagation: Graph Convolutional Networks Based on Taylor Approximation

no code implementations1 Jul 2020 Songyang Zhang, Han Zhang, Shuguang Cui, Zhi Ding

Graph convolutional networks (GCN) have been recently utilized to extract the underlying structures of datasets with some labeled data and high-dimensional features.

Node Classification

A Hybrid Evolutionary Algorithm for Reliable Facility Location Problem

no code implementations27 Jun 2020 Han Zhang, Jialin Liu, Xin Yao

The reliable facility location problem (RFLP) is an important research topic of operational research and plays a vital role in the decision-making and management of modern supply chain and logistics.

Decision Making

Image Augmentations for GAN Training

no code implementations4 Jun 2020 Zhengli Zhao, Zizhao Zhang, Ting Chen, Sameer Singh, Han Zhang

We provide new state-of-the-art results for conditional generation on CIFAR-10 with both consistency loss and contrastive loss as additional regularizations.

Image Augmentation Image Generation

Towards Personalized and Semantic Retrieval: An End-to-End Solution for E-commerce Search via Embedding Learning

no code implementations3 Jun 2020 Han Zhang, Songlin Wang, Kang Zhang, Zhiling Tang, Yunjiang Jiang, Yun Xiao, Weipeng Yan, Wen-Yun Yang

Two critical challenges stay in today's e-commerce search: how to retrieve items that are semantically relevant but not exact matching to query terms, and how to retrieve items that are more personalized to different users for the same search query.

Semantic Retrieval

A Simple Semi-Supervised Learning Framework for Object Detection

2 code implementations10 May 2020 Kihyuk Sohn, Zizhao Zhang, Chun-Liang Li, Han Zhang, Chen-Yu Lee, Tomas Pfister

Semi-supervised learning (SSL) has a potential to improve the predictive performance of machine learning models using unlabeled data.

Data Augmentation Image Classification +2

ReMixMatch: Semi-Supervised Learning with Distribution Matching and Augmentation Anchoring

1 code implementation ICLR 2020 David Berthelot, Nicholas Carlini, Ekin D. Cubuk, Alex Kurakin, Kihyuk Sohn, Han Zhang, Colin Raffel

We improve the recently-proposed ``MixMatch semi-supervised learning algorithm by introducing two new techniques: distribution alignment and augmentation anchoring.

Solving Missing-Annotation Object Detection with Background Recalibration Loss

2 code implementations12 Feb 2020 Han Zhang, Fangyi Chen, Zhiqiang Shen, Qiqi Hao, Chenchen Zhu, Marios Savvides

In this paper, we introduce a superior solution called Background Recalibration Loss (BRL) that can automatically re-calibrate the loss signals according to the pre-defined IoU threshold and input image.

Object Detection

Improved Consistency Regularization for GANs

no code implementations11 Feb 2020 Zhengli Zhao, Sameer Singh, Honglak Lee, Zizhao Zhang, Augustus Odena, Han Zhang

Recent work has increased the performance of Generative Adversarial Networks (GANs) by enforcing a consistency cost on the discriminator.

Image Generation

ERNIE-GEN: An Enhanced Multi-Flow Pre-training and Fine-tuning Framework for Natural Language Generation

3 code implementations26 Jan 2020 Dongling Xiao, Han Zhang, Yukun Li, Yu Sun, Hao Tian, Hua Wu, Haifeng Wang

Current pre-training works in natural language generation pay little attention to the problem of exposure bias on downstream tasks.

 Ranked #1 on Generative Question Answering on CoQA (using extra training data)

Abstractive Text Summarization Dialogue Generation +2

MANELA: A Multi-Agent Algorithm for Learning Network Embeddings

no code implementations1 Dec 2019 Han Zhang, Hong Xu

On the other hand, learning network embeddings on distributively stored networks still remained understudied: To the best of our knowledge, all existing algorithms for learning network embeddings have hitherto been exclusively centralized and thus cannot be applied to these networks.

Network Embedding

Multimodal, Multilingual Grapheme-to-Phoneme Conversion for Low-Resource Languages

no code implementations WS 2019 James Route, Steven Hillis, Isak Czeresnia Etinger, Han Zhang, Alan W. black

Grapheme-to-phoneme conversion (g2p) is the task of predicting the pronunciation of words from their orthographic representation.

Small-GAN: Speeding Up GAN Training Using Core-sets

no code implementations ICML 2020 Samarth Sinha, Han Zhang, Anirudh Goyal, Yoshua Bengio, Hugo Larochelle, Augustus Odena

Recent work by Brock et al. (2018) suggests that Generative Adversarial Networks (GANs) benefit disproportionately from large mini-batch sizes.

Active Learning Anomaly Detection +1

Differentiable Combinatorial Losses through Generalized Gradients of Linear Programs

no code implementations18 Oct 2019 Xi Gao, Han Zhang, Aliakbar Panahi, Tom Arodz

When samples have internal structure, we often see a mismatch between the objective optimized during training and the model's goal during inference.

Combinatorial Optimization Graph Matching +1

Distilling Effective Supervision from Severe Label Noise

2 code implementations CVPR 2020 Zizhao Zhang, Han Zhang, Sercan O. Arik, Honglak Lee, Tomas Pfister

For instance, on CIFAR100 with a $40\%$ uniform noise ratio and only 10 trusted labeled data per class, our method achieves $80. 2{\pm}0. 3\%$ classification accuracy, where the error rate is only $1. 4\%$ higher than a neural network trained without label noise.

Image Classification

Distributed Equivalent Substitution Training for Large-Scale Recommender Systems

no code implementations10 Sep 2019 Haidong Rong, Yangzihao Wang, Feihu Zhou, Junjie Zhai, Haiyang Wu, Rui Lan, Fan Li, Han Zhang, Yuekui Yang, Zhenyu Guo, Di Wang

We present Distributed Equivalent Substitution (DES) training, a novel distributed training framework for large-scale recommender systems with dynamic sparse features.

Recommendation Systems

Multiple instance dense connected convolution neural network for aerial image scene classification

no code implementations22 Aug 2019 Qi Bi, Kun Qin, Zhili Li, Han Zhang, Kai Xu

While the current convolution neural network tends to extract global features and global semantic information in a scene, the geo-spatial objects can be located at anywhere in an aerial image scene and their spatial arrangement tends to be more complicated.

General Classification Scene Classification

Building change detection based on multi-scale filtering and grid partition

no code implementations22 Aug 2019 Qi Bi, Kun Qin, Han Zhang, Wenjun Han, Zhili Li, Kai Xu

Exhaustive experiments indicate that the proposed method can detect building change types directly and outperform the current multi-index learning method.

Approximation Capabilities of Neural ODEs and Invertible Residual Networks

no code implementations ICML 2020 Han Zhang, Xi Gao, Jacob Unterman, Tom Arodz

Neural ODEs and i-ResNet are recently proposed methods for enforcing invertibility of residual neural models.

DynWalks: Global Topology and Recent Changes Awareness Dynamic Network Embedding

2 code implementations arXiv 2019 Chengbin Hou, Han Zhang, Ke Tang, Shan He

Dynamic network embedding aims to learn low dimensional embeddings for unseen and seen nodes by using any currently available snapshots of a dynamic network.

Graph Reconstruction Link Prediction +1

Brain Network Construction and Classification Toolbox (BrainNetClass)

1 code implementation17 Jun 2019 Zhen Zhou, Xiaobo Chen, Yu Zhang, Lishan Qiao, Renping Yu, Gang Pan, Han Zhang, Dinggang Shen

The goal of this work is to introduce a toolbox namely "Brain Network Construction and Classification" (BrainNetClass) to the field to promote more advanced brain network construction methods.

Classification General Classification

Deep Learning for Signal Demodulation in Physical Layer Wireless Communications: Prototype Platform, Open Dataset, and Analytics

no code implementations8 Mar 2019 Hongmei Wang, Zhenzhen Wu, Shuai Ma, Songtao Lu, Han Zhang, Guoru Ding, Shiyin Li

In this paper, we investigate deep learning (DL)-enabled signal demodulation methods and establish the first open dataset of real modulated signals for wireless communication systems.

Multi-Antenna Channel Interpolation via Tucker Decomposed Extreme Learning Machine

no code implementations26 Dec 2018 Han Zhang, Bo Ai, Wenjun Xu, Li Xu, Shuguang Cui

Channel interpolation is an essential technique for providing high-accuracy estimation of the channel state information (CSI) for wireless systems design where the frequency-space structural correlations of multi-antenna channel are typically hidden in matrix or tensor forms.

A Teacher-Student Framework for Maintainable Dialog Manager

no code implementations EMNLP 2018 Weikang Wang, Jiajun Zhang, Han Zhang, Mei-Yuh Hwang, Cheng-qing Zong, Zhifei Li

Specifically, the {``}student{''} is an extended dialog manager based on a new ontology, and the {``}teacher{''} is existing resources used for guiding the learning process of the {``}student{''}.

A Unified Mammogram Analysis Method via Hybrid Deep Supervision

1 code implementation31 Aug 2018 Rongzhao Zhang, Han Zhang, Albert C. S. Chung

In this work, we present a unified mammogram analysis framework for both whole-mammogram classification and segmentation.

Classification General Classification +2

Deep Chronnectome Learning via Full Bidirectional Long Short-Term Memory Networks for MCI Diagnosis

no code implementations30 Aug 2018 Weizheng Yan, Han Zhang, Jing Sui, Dinggang Shen

Dynamic functional connectivity (dFC), consisting of time-varying spatiotemporal dynamics, may characterize "chronnectome" diagnostic information for improving MCI classification.

General Classification Time Series

Self-Attention Generative Adversarial Networks

43 code implementations arXiv 2018 Han Zhang, Ian Goodfellow, Dimitris Metaxas, Augustus Odena

In this paper, we propose the Self-Attention Generative Adversarial Network (SAGAN) which allows attention-driven, long-range dependency modeling for image generation tasks.

Conditional Image Generation

Improving GANs Using Optimal Transport

2 code implementations ICLR 2018 Tim Salimans, Han Zhang, Alec Radford, Dimitris Metaxas

We present Optimal Transport GAN (OT-GAN), a variant of generative adversarial nets minimizing a new metric measuring the distance between the generator distribution and the data distribution.

Image Generation

AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks

17 code implementations CVPR 2018 Tao Xu, Pengchuan Zhang, Qiuyuan Huang, Han Zhang, Zhe Gan, Xiaolei Huang, Xiaodong He

In this paper, we propose an Attentional Generative Adversarial Network (AttnGAN) that allows attention-driven, multi-stage refinement for fine-grained text-to-image generation.

Ranked #3 on Text-to-Image Generation on COCO (SOA-C metric)

Text Matching Text-to-Image Generation

StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks

16 code implementations19 Oct 2017 Han Zhang, Tao Xu, Hongsheng Li, Shaoting Zhang, Xiaogang Wang, Xiaolei Huang, Dimitris Metaxas

In this paper, we propose Stacked Generative Adversarial Networks (StackGAN) aiming at generating high-resolution photo-realistic images.

Text-to-Image Generation

Link the head to the "beak": Zero Shot Learning from Noisy Text Description at Part Precision

no code implementations CVPR 2017 Mohamed Elhoseiny, Yizhe Zhu, Han Zhang, Ahmed Elgammal

We propose a learning framework that is able to connect text terms to its relevant parts and suppress connections to non-visual text terms without any part-text annotations.

Zero-Shot Learning

SegAN: Adversarial Network with Multi-scale $L_1$ Loss for Medical Image Segmentation

2 code implementations6 Jun 2017 Yuan Xue, Tao Xu, Han Zhang, Rodney Long, Xiaolei Huang

Extensive experimental results demonstrate the effectiveness of the proposed SegAN with multi-scale loss: on BRATS 2013 SegAN gives performance comparable to the state-of-the-art for whole tumor and tumor core segmentation while achieves better precision and sensitivity for Gd-enhance tumor core segmentation; on BRATS 2015 SegAN achieves better performance than the state-of-the-art in both dice score and precision.

Brain Tumor Segmentation Tumor Segmentation

Multi-lingual Geoparsing based on Machine Translation

no code implementations6 Nov 2015 Xu Chen, Han Zhang, Judith Gelernter

Our results for geoparsing Chinese and Arabic text using our multi-lingual geoparsing method are comparable to our results for geoparsing English text with our English tools.

Machine Translation Translation

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