Search Results for author: Xiang Gao

Found 69 papers, 26 papers with code

SRAGAN: Saliency Regularized and Attended Generative Adversarial Network for Chinese Ink-wash Painting Generation

no code implementations24 Apr 2024 Xiang Gao, Yuqi Zhang

The saliency map is utilized for content regularization from two aspects, both explicitly and implicitly: (\romannumeral1) we propose saliency IOU (SIOU) loss to explicitly regularize saliency consistency before and after stylization; (\romannumeral2) we propose saliency adaptive normalization (SANorm) which implicitly enhances content integrity of the generated paintings by injecting saliency information to the generator network to guide painting generation.

Generative Adversarial Network Image-to-Image Translation +3

SPUQ: Perturbation-Based Uncertainty Quantification for Large Language Models

no code implementations4 Mar 2024 Xiang Gao, Jiaxin Zhang, Lalla Mouatadid, Kamalika Das

Motivated by this gap, we introduce a novel UQ method, sampling with perturbation for UQ (SPUQ), designed to tackle both aleatoric and epistemic uncertainties.

Text Generation Uncertainty Quantification

Generative 3D Part Assembly via Part-Whole-Hierarchy Message Passing

1 code implementation27 Feb 2024 Bi'an Du, Xiang Gao, Wei Hu, Renjie Liao

Subsequently, we transform the point cloud using the latent poses, feeding it to the part encoder for aggregating super-part information and reasoning about part relationships to predict all part poses.

Investigating White-Box Attacks for On-Device Models

1 code implementation8 Feb 2024 Mingyi Zhou, Xiang Gao, Jing Wu, Kui Liu, Hailong Sun, Li Li

Our findings emphasize the need for developers to carefully consider their model deployment strategies, and use white-box methods to evaluate the vulnerability of on-device models.

Customizing Language Model Responses with Contrastive In-Context Learning

no code implementations30 Jan 2024 Xiang Gao, Kamalika Das

However, it can be challenging to align LLMs with our intent, particularly when we want to generate content that is preferable over others or when we want the LLM to respond in a certain style or tone that is hard to describe.

In-Context Learning Language Modelling

Machine Learning Driven Sensitivity Analysis of E3SM Land Model Parameters for Wetland Methane Emissions

no code implementations5 Dec 2023 Sandeep Chinta, Xiang Gao, Qing Zhu

One of the main sources of this uncertainty arises from the numerous uncertain model parameters within various physical, biological, and chemical processes that influence methane production, oxidation, and transport.

Bayesian Optimization

Cooperative Dispatch of Microgrids Community Using Risk-Sensitive Reinforcement Learning with Monotonously Improved Performance

no code implementations17 Oct 2023 Ziqing Zhu, Xiang Gao, Siqi Bu, Ka Wing Chan, Bin Zhou, Shiwei Xia

This online algorithm enables MGs to spontaneously search for the Pareto Frontier considering multiple objectives and risk mitigation.

Colmap-PCD: An Open-source Tool for Fine Image-to-point cloud Registration

1 code implementation9 Oct 2023 Chunge Bai, Ruijie Fu, Xiang Gao

In contrast, mapping methods based on LiDAR scans are popular in large-scale urban scene reconstruction due to their precise distance measurements, a capability fundamentally absent in visual-based approaches.

Image to Point Cloud Registration

Incremental Rotation Averaging Revisited and More: A New Rotation Averaging Benchmark

no code implementations29 Sep 2023 Xiang Gao, Hainan Cui, Shuhan Shen

In addition, to further address the limitations of the existing rotation averaging benchmark of relying on the slightly outdated Bundler camera calibration results as ground truths and focusing solely on rotation estimation accuracy, this paper presents a new COLMAP-based rotation averaging benchmark that incorporates a cross check between COLMAP and Bundler, and employ the accuracy of both rotation and downstream location estimation as evaluation metrics, which is desired to provide a more reliable and comprehensive evaluation tool for the rotation averaging research.

Camera Calibration

A Quick Guide for the Iterated Extended Kalman Filter on Manifolds

no code implementations18 Jul 2023 Jianzhu Huai, Xiang Gao

In contrast, the iterated EKF (IEKF) refines the state in the update step by iteratively solving a least squares problem.

Modularizing while Training: A New Paradigm for Modularizing DNN Models

1 code implementation15 Jun 2023 Binhang Qi, Hailong Sun, Hongyu Zhang, Ruobing Zhao, Xiang Gao

In this paper, we propose a novel approach that incorporates modularization into the model training process, i. e., modularizing-while-training (MwT).

Open Set Relation Extraction via Unknown-Aware Training

1 code implementation8 Jun 2023 Jun Zhao, Xin Zhao, WenYu Zhan, Qi Zhang, Tao Gui, Zhongyu Wei, Yunwen Chen, Xiang Gao, Xuanjing Huang

Inspired by text adversarial attacks, we adaptively apply small but critical perturbations to original training instances and thus synthesizing negative instances that are more likely to be mistaken by the model as known relations.

Relation Relation Extraction

Reusing Deep Neural Network Models through Model Re-engineering

1 code implementation1 Apr 2023 Binhang Qi, Hailong Sun, Xiang Gao, Hongyu Zhang, Zhaotian Li, Xudong Liu

Prior approaches to DNN model reuse have two main limitations: 1) reusing the entire model, while only a small part of the model's functionalities (labels) are required, would cause much overhead (e. g., computational and time costs for inference), and 2) model reuse would inherit the defects and weaknesses of the reused model, and hence put the new system under threats of security attack.

Learning Regularized Positional Encoding for Molecular Prediction

no code implementations23 Nov 2022 Xiang Gao, Weihao Gao, Wenzhi Xiao, Zhirui Wang, Chong Wang, Liang Xiang

To model the complex nonlinearity in predicting molecular properties in an more end-to-end approach, we propose to encode the positional quantities with a learnable embedding that is continuous and differentiable.

Supervised Pretraining for Molecular Force Fields and Properties Prediction

no code implementations23 Nov 2022 Xiang Gao, Weihao Gao, Wenzhi Xiao, Zhirui Wang, Chong Wang, Liang Xiang

Experiments show that, compared to training from scratch, fine-tuning the pretrained model can significantly improve the performance for seven molecular property prediction tasks and two force field tasks.

Molecular Property Prediction Property Prediction

Learning Latent Part-Whole Hierarchies for Point Clouds

no code implementations14 Nov 2022 Xiang Gao, Wei Hu, Renjie Liao

The decoder takes the latent variable and the feature from the encoder as an input and predicts the per-point part distribution at the top level.

Decoder Point Cloud Segmentation +1

Learning "O" Helps for Learning More: Handling the Concealed Entity Problem for Class-incremental NER

no code implementations10 Oct 2022 Ruotian Ma, Xuanting Chen, Lin Zhang, Xin Zhou, Junzhe Wang, Tao Gui, Qi Zhang, Xiang Gao, Yunwen Chen

In this work, we conduct an empirical study on the "Unlabeled Entity Problem" and find that it leads to severe confusion between "O" and entities, decreasing class discrimination of old classes and declining the model's ability to learn new classes.

Class Incremental Learning Contrastive Learning +3

Few-Shot Model Agnostic Federated Learning

2 code implementations Proceedings of the 30th ACM International Conference on Multimedia 2022 Wenke Huang, Mang Ye, Bo Du, Xiang Gao

To address these issues, this paper presents a novel framework with two main parts: 1) model agnostic federated learning, it performs public-private communication by unifying the model prediction outputs on the shared public datasets; 2) latent embedding adaptation, it addresses the domain gap with an adversarial learning scheme to discriminate the public and private domains.

Federated Learning

Patching Weak Convolutional Neural Network Models through Modularization and Composition

1 code implementation11 Sep 2022 Binhang Qi, Hailong Sun, Xiang Gao, Hongyu Zhang

To patch a weak CNN model that performs unsatisfactorily on a target class (TC), we compose the weak CNN model with the corresponding module obtained from a strong CNN model.

Learning to Incorporate Texture Saliency Adaptive Attention to Image Cartoonization

1 code implementation2 Aug 2022 Xiang Gao, Yuqi Zhang, Yingjie Tian

Image cartoonization is recently dominated by generative adversarial networks (GANs) from the perspective of unsupervised image-to-image translation, in which an inherent challenge is to precisely capture and sufficiently transfer characteristic cartoon styles (e. g., clear edges, smooth color shading, abstract fine structures, etc.).

Style Transfer Unsupervised Image-To-Image Translation

Multi-view Feature Augmentation with Adaptive Class Activation Mapping

no code implementations26 Jun 2022 Xiang Gao, Yingjie Tian, Zhiquan Qi

We propose an end-to-end-trainable feature augmentation module built for image classification that extracts and exploits multi-view local features to boost model performance.

Image Classification

Optimal annuitization post-retirement with labor income

no code implementations9 Feb 2022 Xiang Gao, Cody Hyndman, Traian A. Pirvu, Petar Jevtić

In this paper, we study the problem of post-retirement annuitization with extra labor income in the framework of stochastic control, optimal stopping, and expected utility maximization.

SGUIE-Net: Semantic Attention Guided Underwater Image Enhancement with Multi-Scale Perception

no code implementations8 Jan 2022 Qi Qi, Kunqian Li, Haiyong Zheng, Xiang Gao, Guojia Hou, Kun Sun

In this paper, we propose a novel underwater image enhancement network, called SGUIE-Net, in which we introduce semantic information as high-level guidance across different images that share common semantic regions.

Image Enhancement

A Computer-Aided Diagnosis System for Breast Pathology: A Deep Learning Approach with Model Interpretability from Pathological Perspective

no code implementations5 Aug 2021 Wei-Wen Hsu, Yongfang Wu, Chang Hao, Yu-Ling Hou, Xiang Gao, Yun Shao, Xueli Zhang, Tao He, Yanhong Tai

Objective: We develop a computer-aided diagnosis (CAD) system using deep learning approaches for lesion detection and classification on whole-slide images (WSIs) with breast cancer.

Classification Lesion Classification +3

Self-Supervised Graph Representation Learning via Topology Transformations

1 code implementation25 May 2021 Xiang Gao, Wei Hu, Guo-Jun Qi

We formalize the proposed model from an information-theoretic perspective, by maximizing the mutual information between topology transformations and node representations before and after the transformations.

Graph Classification Graph Representation Learning +3

RetGen: A Joint framework for Retrieval and Grounded Text Generation Modeling

1 code implementation14 May 2021 Yizhe Zhang, Siqi Sun, Xiang Gao, Yuwei Fang, Chris Brockett, Michel Galley, Jianfeng Gao, Bill Dolan

We propose a framework that alleviates this data constraint by jointly training a grounded generator and document retriever on the language model signal.

Dialogue Generation Language Modelling +1

An Adversarially-Learned Turing Test for Dialog Generation Models

1 code implementation16 Apr 2021 Xiang Gao, Yizhe Zhang, Michel Galley, Bill Dolan

To alleviate this risk, we propose an adversarial training approach to learn a robust model, ATT (Adversarial Turing Test), that discriminates machine-generated responses from human-written replies.

Dialogue Evaluation

Self-Supervised Multi-View Learning via Auto-Encoding 3D Transformations

no code implementations1 Mar 2021 Xiang Gao, Wei Hu, Guo-Jun Qi

Then, we self-train a representation to capture the intrinsic 3D object representation by decoding 3D transformation parameters from the fused feature representations of multiple views before and after the transformation.

3D Object Classification 3D Object Recognition +5

Pion form factor and charge radius from Lattice QCD at physical point

no code implementations11 Feb 2021 Xiang Gao, Nikhil Karthik, Swagato Mukherjee, Peter Petreczky, Sergey Syritsyn, Yong Zhao

We study the form factor at the physical point with a lattice spacing $a=0. 076$ fm.

High Energy Physics - Lattice High Energy Physics - Experiment High Energy Physics - Phenomenology Nuclear Theory

Towards studying the structural differences between the pion and its radial excitation

no code implementations27 Jan 2021 Xiang Gao, Nikhil Karthik, Swagato Mukherjee, Peter Petreczky, Sergey Syritsyn, Yong Zhao

We present an exploratory lattice QCD investigation of the differences between the valence quark structure of pion and its radial excitation $\pi(1300)$ in a fixed finite volume using the leading-twist factorization approach.

High Energy Physics - Lattice High Energy Physics - Experiment High Energy Physics - Phenomenology Nuclear Theory

TopoTER: Unsupervised Learning of Topology Transformation Equivariant Representations

no code implementations1 Jan 2021 Xiang Gao, Wei Hu, Guo-Jun Qi

We formalize the TopoTER from an information-theoretic perspective, by maximizing the mutual information between topology transformations and node representations before and after the transformations.

Graph Classification

Reinforcement Learning Control of Robotic Knee with Human in the Loop by Flexible Policy Iteration

no code implementations16 Jun 2020 Xiang Gao, Jennie Si, Yue Wen, Minhan Li, He, Huang

We are motivated by the real challenges presented in a human-robot system to develop new designs that are efficient at data level and with performance guarantees such as stability and optimality at systems level.

Reinforcement Learning (RL)

MixingBoard: a Knowledgeable Stylized Integrated Text Generation Platform

1 code implementation ACL 2020 Xiang Gao, Michel Galley, Bill Dolan

We present MixingBoard, a platform for quickly building demos with a focus on knowledge grounded stylized text generation.

Text Generation

A Controllable Model of Grounded Response Generation

1 code implementation1 May 2020 Zeqiu Wu, Michel Galley, Chris Brockett, Yizhe Zhang, Xiang Gao, Chris Quirk, Rik Koncel-Kedziorski, Jianfeng Gao, Hannaneh Hajishirzi, Mari Ostendorf, Bill Dolan

Current end-to-end neural conversation models inherently lack the flexibility to impose semantic control in the response generation process, often resulting in uninteresting responses.

Informativeness Response Generation

Optimus: Organizing Sentences via Pre-trained Modeling of a Latent Space

1 code implementation EMNLP 2020 Chunyuan Li, Xiang Gao, Yuan Li, Baolin Peng, Xiujun Li, Yizhe Zhang, Jianfeng Gao

We hope that our first pre-trained big VAE language model itself and results can help the NLP community renew the interests of deep generative models in the era of large-scale pre-training, and make these principled methods more practical.

Language Modelling Representation Learning +1

Dynamic Point Cloud Denoising via Manifold-to-Manifold Distance

no code implementations17 Mar 2020 Wei Hu, Qianjiang Hu, Zehua Wang, Xiang Gao

In particular, we define a manifold-to-manifold distance and its discrete counterpart on graphs to measure the variation-based intrinsic distance between surface patches in the temporal domain, provided that graph operators are discrete counterparts of functionals on Riemannian manifolds.

Autonomous Driving Denoising +1

GraphTER: Unsupervised Learning of Graph Transformation Equivariant Representations via Auto-Encoding Node-wise Transformations

1 code implementation CVPR 2020 Xiang Gao, Wei Hu, Guo-Jun Qi

Recent advances in Graph Convolutional Neural Networks (GCNNs) have shown their efficiency for non-Euclidean data on graphs, which often require a large amount of labeled data with high cost.

Point Cloud Segmentation

Joint Learning of Graph Representation and Node Features in Graph Convolutional Neural Networks

1 code implementation11 Sep 2019 Jiaxiang Tang, Wei Hu, Xiang Gao, Zongming Guo

In particular, we cast the graph optimization problem as distance metric learning to capture pairwise similarities of features in each layer.

Graph Learning Metric Learning

Structuring Latent Spaces for Stylized Response Generation

1 code implementation IJCNLP 2019 Xiang Gao, Yizhe Zhang, Sungjin Lee, Michel Galley, Chris Brockett, Jianfeng Gao, Bill Dolan

This structure allows the system to generate stylized relevant responses by sampling in the neighborhood of the conversation model prediction, and continuously control the style level.

Response Generation Style Transfer

Feature Graph Learning for 3D Point Cloud Denoising

no code implementations22 Jul 2019 Wei Hu, Xiang Gao, Gene Cheung, Zongming Guo

In this work, we assume instead the availability of a relevant feature vector $\mathbf{f}_i$ per node $i$, from which we compute an optimal feature graph via optimization of a feature metric.

Graph Learning Image Denoising

Conversing by Reading: Contentful Neural Conversation with On-demand Machine Reading

1 code implementation ACL 2019 Lianhui Qin, Michel Galley, Chris Brockett, Xiaodong Liu, Xiang Gao, Bill Dolan, Yejin Choi, Jianfeng Gao

Although neural conversation models are effective in learning how to produce fluent responses, their primary challenge lies in knowing what to say to make the conversation contentful and non-vacuous.

Informativeness Reading Comprehension +1

3D Dynamic Point Cloud Denoising via Spatial-Temporal Graph Learning

no code implementations28 Apr 2019 Wei Hu, Qianjiang Hu, Zehua Wang, Xiang Gao

Finally, based on the spatial-temporal graph learning, we formulate dynamic point cloud denoising as the joint optimization of the desired point cloud and underlying spatio-temporal graph, which leverages both intra-frame affinities and inter-frame consistency and is solved via alternating minimization.

Denoising graph construction +1

Exploring Structure-Adaptive Graph Learning for Robust Semi-Supervised Classification

no code implementations23 Apr 2019 Xiang Gao, Wei Hu, Zongming Guo

In this paper, we propose Graph Learning Neural Networks (GLNNs), which exploit the optimization of graphs (the adjacency matrix in particular) from both data and tasks.

General Classification Graph Learning +2

Complete Scene Reconstruction by Merging Images and Laser Scans

no code implementations21 Apr 2019 Xiang Gao, Shuhan Shen, Lingjie Zhu, Tianxin Shi, Zhiheng Wang, Zhanyi Hu

Experimental evaluations on two ancient Chinese architecture datasets demonstrate the effectiveness of our proposed complete scene reconstruction pipeline.

A Multi-Task Learning Framework for Overcoming the Catastrophic Forgetting in Automatic Speech Recognition

no code implementations17 Apr 2019 Jiabin Xue, Jiqing Han, Tieran Zheng, Xiang Gao, Jiaxing Guo

On the one hand, we constrain the new parameters not to deviate too far from the original parameters and punish the new system when forgetting original knowledge.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

Visual Localization Using Sparse Semantic 3D Map

no code implementations8 Apr 2019 Tianxin Shi, Shuhan Shen, Xiang Gao, Lingjie Zhu

Accurate and robust visual localization under a wide range of viewing condition variations including season and illumination changes, as well as weather and day-night variations, is the key component for many computer vision and robotics applications.

Visual Localization

Consistent Dialogue Generation with Self-supervised Feature Learning

1 code implementation13 Mar 2019 Yizhe Zhang, Xiang Gao, Sungjin Lee, Chris Brockett, Michel Galley, Jianfeng Gao, Bill Dolan

Generating responses that are consistent with the dialogue context is one of the central challenges in building engaging conversational agents.

Dialogue Generation Response Generation

Understanding the Mechanism of Deep Learning Framework for Lesion Detection in Pathological Images with Breast Cancer

no code implementations4 Mar 2019 Wei-Wen Hsu, Chung-Hao Chen, Chang Hoa, Yu-Ling Hou, Xiang Gao, Yun Shao, Xueli Zhang, Jingjing Wang, Tao He, Yanghong Tai

Most of the characteristics learned by the deep learning models have summarized the detection rules that can be recognized by the experienced pathologists, whereas there are still some features may not be intuitive to domain experts but discriminative in classification for machines.

General Classification Lesion Detection

Jointly Optimizing Diversity and Relevance in Neural Response Generation

no code implementations NAACL 2019 Xiang Gao, Sungjin Lee, Yizhe Zhang, Chris Brockett, Michel Galley, Jianfeng Gao, Bill Dolan

In this paper, we propose a SpaceFusion model to jointly optimize diversity and relevance that essentially fuses the latent space of a sequence-to-sequence model and that of an autoencoder model by leveraging novel regularization terms.

Dialogue Generation Response Generation

Optimized Skeleton-based Action Recognition via Sparsified Graph Regression

no code implementations29 Nov 2018 Xiang Gao, Wei Hu, Jiaxiang Tang, Jiaying Liu, Zongming Guo

In this paper, we represent skeletons naturally on graphs, and propose a graph regression based GCN (GR-GCN) for skeleton-based action recognition, aiming to capture the spatio-temporal variation in the data.

Action Recognition graph construction +4

Large Scale Urban Scene Modeling from MVS Meshes

no code implementations ECCV 2018 Lingjie Zhu, Shuhan Shen, Xiang Gao, Zhanyi Hu

There are two major steps in our framework: segmentation and building modeling.

LDSO: Direct Sparse Odometry with Loop Closure

no code implementations3 Aug 2018 Xiang Gao, Rui Wang, Nikolaus Demmel, Daniel Cremers

In this paper we present an extension of Direct Sparse Odometry (DSO) to a monocular visual SLAM system with loop closure detection and pose-graph optimization (LDSO).

Loop Closure Detection Translation

Global Norm-Aware Pooling for Pose-Robust Face Recognition at Low False Positive Rate

no code implementations1 Aug 2018 Sheng Chen, Jia Guo, Yang Liu, Xiang Gao, Zhen Han

In this paper, we propose a novel Global Norm-Aware Pooling (GNAP) block, which reweights local features in a convolutional neural network (CNN) adaptively according to their L2 norms and outputs a global feature vector with a global average pooling layer.

Face Recognition Robust Face Recognition

CSfM: Community-based Structure from Motion

no code implementations23 Mar 2018 Hainan Cui, Shuhan Shen, Xiang Gao, Zhanyi Hu

The global manner has the advantage of simultaneously estimating all camera poses, but it is usually sensitive to epipolar geometry outliers.

Computational Efficiency

Deep reinforcement learning for time series: playing idealized trading games

2 code implementations11 Mar 2018 Xiang Gao

Deep Q-learning is investigated as an end-to-end solution to estimate the optimal strategies for acting on time series input.

Q-Learning reinforcement-learning +3

HSfM: Hybrid Structure-from-Motion

no code implementations CVPR 2017 Hainan Cui, Xiang Gao, Shuhan Shen, Zhanyi Hu

In this work, we propose a new hybrid SfM method to tackle the issues of efficiency, accuracy and robustness in a unified framework.

Computational Efficiency

Challenges in Monocular Visual Odometry: Photometric Calibration, Motion Bias and Rolling Shutter Effect

no code implementations11 May 2017 Nan Yang, Rui Wang, Xiang Gao, Daniel Cremers

Monocular visual odometry (VO) and simultaneous localization and mapping (SLAM) have seen tremendous improvements in accuracy, robustness and efficiency, and have gained increasing popularity over recent years.

Monocular Visual Odometry Simultaneous Localization and Mapping

Randomized Primal-Dual Proximal Block Coordinate Updates

no code implementations19 May 2016 Xiang Gao, Yangyang Xu, Shuzhong Zhang

Assuming mere convexity, we establish its $O(1/t)$ convergence rate in terms of the objective value and feasibility measure.

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