Search Results for author: Tian Xia

Found 35 papers, 13 papers with code

AlignTTS: Efficient Feed-Forward Text-to-Speech System without Explicit Alignment

2 code implementations4 Mar 2020 Zhen Zeng, Jianzong Wang, Ning Cheng, Tian Xia, Jing Xiao

Targeting at both high efficiency and performance, we propose AlignTTS to predict the mel-spectrum in parallel.

UniCtrl: Improving the Spatiotemporal Consistency of Text-to-Video Diffusion Models via Training-Free Unified Attention Control

1 code implementation4 Mar 2024 Xuweiyi Chen, Tian Xia, Sihan Xu

Video Diffusion Models have been developed for video generation, usually integrating text and image conditioning to enhance control over the generated content.

Video Generation

High Fidelity Image Counterfactuals with Probabilistic Causal Models

1 code implementation27 Jun 2023 Fabio De Sousa Ribeiro, Tian Xia, Miguel Monteiro, Nick Pawlowski, Ben Glocker

We present a general causal generative modelling framework for accurate estimation of high fidelity image counterfactuals with deep structural causal models.

counterfactual

R-Judge: Benchmarking Safety Risk Awareness for LLM Agents

1 code implementation18 Jan 2024 Tongxin Yuan, Zhiwei He, Lingzhong Dong, Yiming Wang, Ruijie Zhao, Tian Xia, Lizhen Xu, Binglin Zhou, Fangqi Li, Zhuosheng Zhang, Rui Wang, Gongshen Liu

We introduce R-Judge, a benchmark crafted to evaluate the proficiency of LLMs in judging and identifying safety risks given agent interaction records.

Benchmarking

DeepPicker: a Deep Learning Approach for Fully Automated Particle Picking in Cryo-EM

1 code implementation6 May 2016 Feng Wang, Huichao Gong, Gaochao liu, Meijing Li, Chuangye Yan, Tian Xia, Xueming Li, Jianyang Zeng

Particle picking is a time-consuming step in single-particle analysis and often requires significant interventions from users, which has become a bottleneck for future automated electron cryo-microscopy (cryo-EM).

Single Particle Analysis

Learning to synthesise the ageing brain without longitudinal data

1 code implementation4 Dec 2019 Tian Xia, Agisilaos Chartsias, Chengjia Wang, Sotirios A. Tsaftaris

Our method synthesises images conditioned on two factors: age (a continuous variable), and status of Alzheimer's Disease (AD, an ordinal variable).

Anatomy

Pseudo-healthy synthesis with pathology disentanglement and adversarial learning

1 code implementation20 Apr 2020 Tian Xia, Agisilaos Chartsias, Sotirios A. Tsaftaris

In this paper, we present a model that is encouraged to disentangle the information of pathology from what seems to be healthy.

Anomaly Detection Disentanglement

Penalty Gradient Normalization for Generative Adversarial Networks

1 code implementation23 Jun 2023 Tian Xia

In this paper, we propose a novel normalization method called penalty gradient normalization (PGN) to tackle the training instability of Generative Adversarial Networks (GANs) caused by the sharp gradient space.

Counterfactual contrastive learning: robust representations via causal image synthesis

1 code implementation14 Mar 2024 Melanie Roschewitz, Fabio De Sousa Ribeiro, Tian Xia, Galvin Khara, Ben Glocker

Contrastive pretraining is well-known to improve downstream task performance and model generalisation, especially in limited label settings.

Contrastive Learning counterfactual +2

Fully Convolutional Attention Networks for Fine-Grained Recognition

no code implementations22 Mar 2016 Xiao Liu, Tian Xia, Jiang Wang, Yi Yang, Feng Zhou, Yuanqing Lin

Fine-grained recognition is challenging due to its subtle local inter-class differences versus large intra-class variations such as poses.

reinforcement-learning Reinforcement Learning (RL)

Vehicle Detection from 3D Lidar Using Fully Convolutional Network

no code implementations29 Aug 2016 Bo Li, Tianlei Zhang, Tian Xia

Convolutional network techniques have recently achieved great success in vision based detection tasks.

Object Detection

Direct 0-1 Loss Minimization and Margin Maximization with Boosting

no code implementations NeurIPS 2013 Shaodan Zhai, Tian Xia, Ming Tan, Shaojun Wang

We propose a boosting method, DirectBoost, a greedy coordinate descent algorithm that builds an ensemble classifier of weak classifiers through directly minimizing empirical classification error over labeled training examples; once the training classification error is reduced to a local coordinatewise minimum, DirectBoost runs a greedy coordinate ascent algorithm that continuously adds weak classifiers to maximize any targeted arbitrarily defined margins until reaching a local coordinatewise maximum of the margins in a certain sense.

Classification General Classification

Adversarial Pseudo Healthy Synthesis Needs Pathology Factorization

no code implementations10 Jan 2019 Tian Xia, Agisilaos Chartsias, Sotirios A. Tsaftaris

Pseudo healthy synthesis, i. e. the creation of a subject-specific `healthy' image from a pathological one, could be helpful in tasks such as anomaly detection, understanding changes induced by pathology and disease or even as data augmentation.

Anomaly Detection Data Augmentation +2

Learning From Massive Noisy Labeled Data for Image Classification

no code implementations CVPR 2015 Tong Xiao, Tian Xia, Yi Yang, Chang Huang, Xiaogang Wang

To demonstrate the effectiveness of our approach, we collect a large-scale real-world clothing classification dataset with both noisy and clean labels.

Classification General Classification +1

Analysis of Regression Tree Fitting Algorithms in Learning to Rank

no code implementations12 Sep 2019 Tian Xia, Shaodan Zhai, Shaojun Wang

In learning to rank area, industry-level applications have been dominated by gradient boosting framework, which fits a tree using least square error principle.

Learning-To-Rank regression

Plackett-Luce model for learning-to-rank task

no code implementations15 Sep 2019 Tian Xia, Shaodan Zhai, Shaojun Wang

List-wise based learning to rank methods are generally supposed to have better performance than point- and pair-wise based.

Learning-To-Rank

Learning Multi-Robot Decentralized Macro-Action-Based Policies via a Centralized Q-Net

no code implementations19 Sep 2019 Yuchen Xiao, Joshua Hoffman, Tian Xia, Christopher Amato

In many real-world multi-robot tasks, high-quality solutions often require a team of robots to perform asynchronous actions under decentralized control.

Multi-agent Reinforcement Learning

A simple discriminative training method for machine translation with large-scale features

no code implementations15 Sep 2019 Tian Xia, Shaodan Zhai, Shaojun Wang

Margin infused relaxed algorithms (MIRAs) dominate model tuning in statistical machine translation in the case of large scale features, but also they are famous for the complexity in implementation.

Machine Translation Translation

Une m\'ethode discriminant formation simple pour la traduction automatique avec Grands Caract\'eristiques

no code implementations JEPTALNRECITAL 2015 Tian Xia, Shaodan Zhai, Zhongliang Li, Shaojun Wang

Marge infus{\'e} algorithmes d{\'e}tendus (MIRAS) dominent mod{\`e}le de tuning dans la traduction automatique statistique dans le cas des grandes caract{\'e}ristiques de l{'}{\'e}chelle, mais ils sont {\'e}galement c{\'e}l{\`e}bres pour la complexit{\'e} de mise en {\oe}uvre.

Deep Multi-attribute Graph Representation Learning on Protein Structures

no code implementations22 Dec 2020 Tian Xia, Wei-Shinn Ku

To address the above challenges, we propose a new graph neural network architecture to represent the proteins as 3D graphs and predict both distance geometric graph representation and dihedral geometric graph representation together.

Attribute Graph Representation Learning

PAII-NLP at SMM4H 2021: Joint Extraction and Normalization of Adverse Drug Effect Mentions in Tweets

no code implementations NAACL (SMM4H) 2021 Zongcheng Ji, Tian Xia, Mei Han

This paper describes our system developed for the subtask 1c of the sixth Social Media Mining for Health Applications (SMM4H) shared task in 2021.

Hybrid Policies Using Inverse Rewards for Reinforcement Learning

no code implementations27 Sep 2018 Yao Shi, Tian Xia, Guanjun Zhao, Xin Gao

This paper puts forward a broad-spectrum improvement for reinforcement learning algorithms, which combines the policies using original rewards and inverse (negative) rewards.

OpenAI Gym Q-Learning +2

Adversarial Counterfactual Augmentation: Application in Alzheimer's Disease Classification

no code implementations15 Mar 2022 Tian Xia, Pedro Sanchez, Chen Qin, Sotirios A. Tsaftaris

To demonstrate the effectiveness of the proposed approach, we validate the method with the classification of Alzheimer's Disease (AD) as a downstream task.

Classification counterfactual +1

Cooperative IoT Data Sharing with Heterogeneity of Participants Based on Electricity Retail

no code implementations31 May 2023 Bohong Wang, Qinglai Guo, Tian Xia, Qiang Li, Di Liu, Feng Zhao

With the development of Internet of Things (IoT) and big data technology, the data value is increasingly explored in multiple practical scenarios, including electricity transactions.

Data Valuation Fairness

Mitigating attribute amplification in counterfactual image generation

no code implementations14 Mar 2024 Tian Xia, Mélanie Roschewitz, Fabio De Sousa Ribeiro, Charles Jones, Ben Glocker

Causal generative modelling is gaining interest in medical imaging due to its ability to answer interventional and counterfactual queries.

Attribute counterfactual +1

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