Search Results for author: Yi Xu

Found 115 papers, 30 papers with code

Monocular 3D Object Detection via Feature Domain Adaptation

no code implementations ECCV 2020 Lele Chen, Guofeng Cui, Celong Liu, Zhong Li, Ziyi Kou, Yi Xu, Chenliang Xu

Monocular 3D object detection is a challenging task due to unreliable depth, resulting in a distinct performance gap between monocular and LiDAR-based approaches.

Domain Adaptation Monocular 3D Object Detection +1

Asynchronous Convergence in Multi-Task Learning via Knowledge Distillation from Converged Tasks

no code implementations NAACL (ACL) 2022 Weiyi Lu, Sunny Rajagopalan, Priyanka Nigam, Jaspreet Singh, Xiaodi Sun, Yi Xu, Belinda Zeng, Trishul Chilimbi

However, one issue that often arises in MTL is the convergence speed between tasks varies due to differences in task difficulty, so it can be a challenge to simultaneously achieve the best performance on all tasks with a single model checkpoint.

Knowledge Distillation Multi-Task Learning

Making Reconstruction-based Method Great Again for Video Anomaly Detection

1 code implementation28 Jan 2023 Yizhou Wang, Can Qin, Yue Bai, Yi Xu, Xu Ma, Yun Fu

With the same perturbation magnitude, the testing reconstruction error of the normal frames lowers more than that of the abnormal frames, which contributes to mitigating the overfitting problem of reconstruction.

Anomaly Detection Optical Flow Estimation +1

ActiveRMAP: Radiance Field for Active Mapping And Planning

no code implementations23 Nov 2022 Huangying Zhan, Jiyang Zheng, Yi Xu, Ian Reid, Hamid Rezatofighi

We, for the first time, present an RGB-only active vision framework using radiance field representation for active 3D reconstruction and planning in an online manner.

3D Reconstruction

Temporal Knowledge Graph Reasoning with Historical Contrastive Learning

1 code implementation20 Nov 2022 Yi Xu, Junjie Ou, Hui Xu, Luoyi Fu

Simultaneously, it trains representations of queries to investigate whether the current moment depends more on historical or non-historical events by launching contrastive learning.

Contrastive Learning

Look More but Care Less in Video Recognition

1 code implementation18 Nov 2022 Yitian Zhang, Yue Bai, Huan Wang, Yi Xu, Yun Fu

To tackle this problem, we propose Ample and Focal Network (AFNet), which is composed of two branches to utilize more frames but with less computation.

Action Recognition Video Recognition

CLIP-FLow: Contrastive Learning by semi-supervised Iterative Pseudo labeling for Optical Flow Estimation

no code implementations25 Oct 2022 Zhiqi Zhang, Nitin Bansal, Changjiang Cai, Pan Ji, Qingan Yan, Xiangyu Xu, Yi Xu

To this end, we propose CLIP-FLow, a semi-supervised iterative pseudo-labeling framework to transfer the pretraining knowledge to the target real domain.

Contrastive Learning Optical Flow Estimation +1

Fairness via Adversarial Attribute Neighbourhood Robust Learning

no code implementations12 Oct 2022 Qi Qi, Shervin Ardeshir, Yi Xu, Tianbao Yang

Improving fairness between privileged and less-privileged sensitive attribute groups (e. g, {race, gender}) has attracted lots of attention.

Fairness

OmniNeRF: Hybriding Omnidirectional Distance and Radiance fields for Neural Surface Reconstruction

no code implementations27 Sep 2022 Jiaming Shen, Bolin Song, Zirui Wu, Yi Xu

3D reconstruction from images has wide applications in Virtual Reality and Automatic Driving, where the precision requirement is very high.

3D Reconstruction 3D Scene Reconstruction +2

INFINITY: A Simple Yet Effective Unsupervised Framework for Graph-Text Mutual Conversion

no code implementations22 Sep 2022 Yi Xu, Luoyi Fu, Zhouhan Lin, Jiexing Qi, Xinbing Wang

As a fully unsupervised framework, INFINITY is empirically verified to outperform state-of-the-art baselines for G2T and T2G tasks.

Knowledge Graphs

MonoIndoor++:Towards Better Practice of Self-Supervised Monocular Depth Estimation for Indoor Environments

no code implementations18 Jul 2022 Runze Li, Pan Ji, Yi Xu, Bir Bhanu

As compared to outdoor environments, estimating depth of monocular videos for indoor environments, using self-supervised methods, results in two additional challenges: (i) the depth range of indoor video sequences varies a lot across different frames, making it difficult for the depth network to induce consistent depth cues for training; (ii) the indoor sequences recorded with handheld devices often contain much more rotational motions, which cause difficulties for the pose network to predict accurate relative camera poses.

Depth Prediction Monocular Depth Estimation +1

SepLUT: Separable Image-adaptive Lookup Tables for Real-time Image Enhancement

1 code implementation18 Jul 2022 Canqian Yang, Meiguang Jin, Yi Xu, Rui Zhang, Ying Chen, Huaida Liu

Image-adaptive lookup tables (LUTs) have achieved great success in real-time image enhancement tasks due to their high efficiency for modeling color transforms.

Image Enhancement Photo Retouching

Efficient and effective training of language and graph neural network models

no code implementations22 Jun 2022 Vassilis N. Ioannidis, Xiang Song, Da Zheng, Houyu Zhang, Jun Ma, Yi Xu, Belinda Zeng, Trishul Chilimbi, George Karypis

The effectiveness in our framework is achieved by applying stage-wise fine-tuning of the BERT model first with heterogenous graph information and then with a GNN model.

Edge Classification Language Modelling +1

Semantics-Depth-Symbiosis: Deeply Coupled Semi-Supervised Learning of Semantics and Depth

no code implementations21 Jun 2022 Nitin Bansal, Pan Ji, Junsong Yuan, Yi Xu

Multi-task learning (MTL) paradigm focuses on jointly learning two or more tasks, aiming for significant improvement w. r. t model's generalizability, performance, and training/inference memory footprint.

Data Augmentation Depth Estimation +2

DynaMaR: Dynamic Prompt with Mask Token Representation

no code implementations7 Jun 2022 Xiaodi Sun, Sunny Rajagopalan, Priyanka Nigam, Weiyi Lu, Yi Xu, Belinda Zeng, Trishul Chilimbi

In this paper, we propose an improvement to prompt-based fine-tuning that addresses these two issues.

Language Modelling

RIAV-MVS: Recurrent-Indexing an Asymmetric Volume for Multi-View Stereo

no code implementations28 May 2022 Changjiang Cai, Pan Ji, Qingan Yan, Yi Xu

In the pixel level, we propose to break the symmetry of the Siamese network (which is typically used in MVS to extract image features) by introducing a transformer block to the reference image (but not to the source images).

HIRL: A General Framework for Hierarchical Image Representation Learning

1 code implementation26 May 2022 Minghao Xu, Yuanfan Guo, Xuanyu Zhu, Jiawen Li, Zhenbang Sun, Jian Tang, Yi Xu, Bingbing Ni

This framework aims to learn multiple semantic representations for each image, and these representations are structured to encode image semantics from fine-grained to coarse-grained.

Image Clustering Representation Learning +3

An Empirical Study on Distribution Shift Robustness From the Perspective of Pre-Training and Data Augmentation

no code implementations25 May 2022 Ziquan Liu, Yi Xu, Yuanhong Xu, Qi Qian, Hao Li, Rong Jin, Xiangyang Ji, Antoni B. Chan

With our empirical result obtained from 1, 330 models, we provide the following main observations: 1) ERM combined with data augmentation can achieve state-of-the-art performance if we choose a proper pre-trained model respecting the data property; 2) specialized algorithms further improve the robustness on top of ERM when handling a specific type of distribution shift, e. g., GroupDRO for spurious correlation and CORAL for large-scale out-of-distribution data; 3) Comparing different pre-training modes, architectures and data sizes, we provide novel observations about pre-training on distribution shift, which sheds light on designing or selecting pre-training strategy for different kinds of distribution shifts.

Data Augmentation

CNN-Augmented Visual-Inertial SLAM with Planar Constraints

no code implementations5 May 2022 Pan Ji, Yuan Tian, Qingan Yan, Yuxin Ma, Yi Xu

The CNN depth effectively bootstraps the back-end optimization of SLAM and meanwhile the CNN uncertainty adaptively weighs the contribution of each feature point to the back-end optimization.

FisheyeDistill: Self-Supervised Monocular Depth Estimation with Ordinal Distillation for Fisheye Cameras

no code implementations5 May 2022 Qingan Yan, Pan Ji, Nitin Bansal, Yuxin Ma, Yuan Tian, Yi Xu

In this paper, we deal with the problem of monocular depth estimation for fisheye cameras in a self-supervised manner.

Monocular Depth Estimation

GeoRefine: Self-Supervised Online Depth Refinement for Accurate Dense Mapping

no code implementations3 May 2022 Pan Ji, Qingan Yan, Yuxin Ma, Yi Xu

We present a robust and accurate depth refinement system, named GeoRefine, for geometrically-consistent dense mapping from monocular sequences.

Optical Flow Estimation

AdaInt: Learning Adaptive Intervals for 3D Lookup Tables on Real-time Image Enhancement

1 code implementation CVPR 2022 Canqian Yang, Meiguang Jin, Xu Jia, Yi Xu, Ying Chen

They adopt a sub-optimal uniform sampling point allocation, limiting the expressiveness of the learned LUTs since the (tri-)linear interpolation between uniform sampling points in the LUT transform might fail to model local non-linearities of the color transform.

Image Enhancement

EPiDA: An Easy Plug-in Data Augmentation Framework for High Performance Text Classification

1 code implementation NAACL 2022 Minyi Zhao, Lu Zhang, Yi Xu, Jiandong Ding, Jihong Guan, Shuigeng Zhou

However, to the best of our knowledge, most existing methods consider only either the diversity or the quality of augmented data, thus cannot fully mine the potential of DA for NLP.

Data Augmentation text-classification +1

Exploration strategies for articulatory synthesis of complex syllable onsets

1 code implementation20 Apr 2022 Daniel R. van Niekerk, Anqi Xu, Branislav Gerazov, Paul K. Krug, Peter Birkholz, Yi Xu

High-quality articulatory speech synthesis has many potential applications in speech science and technology.

Speech Synthesis

Interventional Multi-Instance Learning with Deconfounded Instance-Level Prediction

no code implementations20 Apr 2022 Tiancheng Lin, Hongteng Xu, Canqian Yang, Yi Xu

When applying multi-instance learning (MIL) to make predictions for bags of instances, the prediction accuracy of an instance often depends on not only the instance itself but also its context in the corresponding bag.

Causal Inference

Solving The Long-Tailed Problem via Intra- and Inter-Category Balance

no code implementations20 Apr 2022 Renhui Zhang, Tiancheng Lin, Rui Zhang, Yi Xu

Benchmark datasets for visual recognition assume that data is uniformly distributed, while real-world datasets obey long-tailed distribution.

Enhancing Non-mass Breast Ultrasound Cancer Classification With Knowledge Transfer

no code implementations18 Apr 2022 Yangrun Hu, Yuanfan Guo, Fan Zhang, Mingda Wang, Tiancheng Lin, Rong Wu, Yi Xu

Based on the insight that mass data is sufficient and shares the same knowledge structure with non-mass data of identifying the malignancy of a lesion based on the ultrasound image, we propose a novel transfer learning framework to enhance the generalizability of the DNN model for non-mass BUS with the help of mass BUS.

Classification Transfer Learning

Self Supervised Lesion Recognition For Breast Ultrasound Diagnosis

no code implementations18 Apr 2022 Yuanfan Guo, Canqian Yang, Tiancheng Lin, Chunxiao Li, Rui Zhang, Yi Xu

Since an ultrasound image only describes a partial 2D projection of a 3D lesion, such paradigm ignores the semantic relationship between different views of a lesion, which is inconsistent with the traditional diagnosis where sonographers analyze a lesion from at least two views.

Contrastive Learning

CHEX: CHannel EXploration for CNN Model Compression

1 code implementation CVPR 2022 Zejiang Hou, Minghai Qin, Fei Sun, Xiaolong Ma, Kun Yuan, Yi Xu, Yen-Kuang Chen, Rong Jin, Yuan Xie, Sun-Yuan Kung

However, conventional pruning methods have limitations in that: they are restricted to pruning process only, and they require a fully pre-trained large model.

Image Classification Instance Segmentation +4

Efficient Few-Shot Object Detection via Knowledge Inheritance

1 code implementation23 Mar 2022 Ze Yang, Chi Zhang, Ruibo Li, Yi Xu, Guosheng Lin

Upon this baseline, we devise an initializer named knowledge inheritance (KI) to reliably initialize the novel weights for the box classifier, which effectively facilitates the knowledge transfer process and boosts the adaptation speed.

Few-Shot Object Detection object-detection +1

PlaneMVS: 3D Plane Reconstruction from Multi-View Stereo

no code implementations CVPR 2022 Jiachen Liu, Pan Ji, Nitin Bansal, Changjiang Cai, Qingan Yan, Xiaolei Huang, Yi Xu

The semantic plane detection branch is based on a single-view plane detection framework but with differences.

3D Reconstruction

Deformable VisTR: Spatio temporal deformable attention for video instance segmentation

no code implementations12 Mar 2022 Sudhir Yarram, Jialian Wu, Pan Ji, Yi Xu, Junsong Yuan

To improve the training efficiency, we propose Deformable VisTR, leveraging spatio-temporal deformable attention module that only attends to a small fixed set of key spatio-temporal sampling points around a reference point.

Instance Segmentation Semantic Segmentation +1

Adaptive Trajectory Prediction via Transferable GNN

no code implementations CVPR 2022 Yi Xu, Lichen Wang, Yizhou Wang, Yun Fu

To the best of our knowledge, our work is the pioneer which fills the gap in benchmarks and techniques for practical pedestrian trajectory prediction across different domains.

Autonomous Driving Pedestrian Trajectory Prediction +2

Multi-modal Alignment using Representation Codebook

no code implementations CVPR 2022 Jiali Duan, Liqun Chen, Son Tran, Jinyu Yang, Yi Xu, Belinda Zeng, Trishul Chilimbi

Aligning signals from different modalities is an important step in vision-language representation learning as it affects the performance of later stages such as cross-modality fusion.

Representation Learning Retrieval

HCSC: Hierarchical Contrastive Selective Coding

2 code implementations CVPR 2022 Yuanfan Guo, Minghao Xu, Jiawen Li, Bingbing Ni, Xuanyu Zhu, Zhenbang Sun, Yi Xu

In this framework, a set of hierarchical prototypes are constructed and also dynamically updated to represent the hierarchical semantic structures underlying the data in the latent space.

Contrastive Learning Representation Learning

A Novel Convergence Analysis for Algorithms of the Adam Family

no code implementations7 Dec 2021 Zhishuai Guo, Yi Xu, Wotao Yin, Rong Jin, Tianbao Yang

Although rigorous convergence analysis exists for Adam, they impose specific requirements on the update of the adaptive step size, which are not generic enough to cover many other variants of Adam.

Bilevel Optimization

Boosting Unsupervised Domain Adaptation with Soft Pseudo-label and Curriculum Learning

no code implementations3 Dec 2021 Shengjia Zhang, Tiancheng Lin, Yi Xu

To avoid overfitting on source domain, at the second stage, we propose a curriculum learning strategy to adaptively control the weighting between losses from the two domains so that the focus of the training stage is gradually shifted from source distribution to target distribution with prediction confidence boosted on the target domain.

Pseudo Label Unsupervised Domain Adaptation

SLA$^2$P: Self-supervised Anomaly Detection with Adversarial Perturbation

no code implementations25 Nov 2021 Yizhou Wang, Can Qin, Rongzhe Wei, Yi Xu, Yue Bai, Yun Fu

Next we add adversarial perturbation to the transformed features to decrease their softmax scores of the predicted labels and design anomaly scores based on the predictive uncertainties of the classifier on these perturbed features.

Pseudo Label Self-Supervised Anomaly Detection +3

Improved Fine-Tuning by Better Leveraging Pre-Training Data

no code implementations24 Nov 2021 Ziquan Liu, Yi Xu, Yuanhong Xu, Qi Qian, Hao Li, Xiangyang Ji, Antoni Chan, Rong Jin

The generalization result of using pre-training data shows that the excess risk bound on a target task can be improved when the appropriate pre-training data is included in fine-tuning.

Image Classification Learning Theory

Self-Supervised Pre-Training for Transformer-Based Person Re-Identification

1 code implementation23 Nov 2021 Hao Luo, Pichao Wang, Yi Xu, Feng Ding, Yanxin Zhou, Fan Wang, Hao Li, Rong Jin

We first investigate self-supervised learning (SSL) methods with Vision Transformer (ViT) pretrained on unlabelled person images (the LUPerson dataset), and empirically find it significantly surpasses ImageNet supervised pre-training models on ReID tasks.

 Ranked #1 on Unsupervised Person Re-Identification on Market-1501 (using extra training data)

Self-Supervised Learning Unsupervised Domain Adaptation +1

Magic Pyramid: Accelerating Inference with Early Exiting and Token Pruning

no code implementations30 Oct 2021 Xuanli He, Iman Keivanloo, Yi Xu, Xiang He, Belinda Zeng, Santosh Rajagopalan, Trishul Chilimbi

To achieve this, we propose a novel idea, Magic Pyramid (MP), to reduce both width-wise and depth-wise computation via token pruning and early exiting for Transformer-based models, particularly BERT.

text-classification Text Classification

DP-SSL: Towards Robust Semi-supervised Learning with A Few Labeled Samples

no code implementations NeurIPS 2021 Yi Xu, Jiandong Ding, Lu Zhang, Shuigeng Zhou

Extensive experiments on four standard SSL benchmarks show that DP-SSL can provide reliable labels for unlabeled data and achieve better classification performance on test sets than existing SSL methods, especially when only a small number of labeled samples are available.

Multiple-choice Semi-Supervised Image Classification

Weakly-supervised Text Classification Based on Keyword Graph

1 code implementation EMNLP 2021 Lu Zhang, Jiandong Ding, Yi Xu, Yingyao Liu, Shuigeng Zhou

Among them, keyword-driven methods are the mainstream where user-provided keywords are exploited to generate pseudo-labels for unlabeled texts.

Classification text-classification +1

MemREIN: Rein the Domain Shift for Cross-Domain Few-Shot Learning

no code implementations29 Sep 2021 Yi Xu, Lichen Wang, Yizhou Wang, Can Qin, Yulun Zhang, Yun Fu

In this paper, we propose a novel framework, MemREIN, which considers Memorized, Restitution, and Instance Normalization for cross-domain few-shot learning.

Contrastive Learning cross-domain few-shot learning

Causal Triple Attention Time Series Forecasting

no code implementations29 Sep 2021 Zhixuan Chu, Tan Yan, Yue Wu, Yi Xu, Cheng Zhang, Yulin kang

Time series forecasting has historically been a key area of academic research and industrial applications.

Causal Inference Time Series Forecasting

Distribution-sensitive Information Retention for Accurate Binary Neural Network

no code implementations25 Sep 2021 Haotong Qin, Xiangguo Zhang, Ruihao Gong, Yifu Ding, Yi Xu, Xianglong Liu

We present a novel Distribution-sensitive Information Retention Network (DIR-Net) that retains the information in the forward and backward propagation by improving internal propagation and introducing external representations.

Binarization Image Classification +1

Dash: Semi-Supervised Learning with Dynamic Thresholding

no code implementations1 Sep 2021 Yi Xu, Lei Shang, Jinxing Ye, Qi Qian, Yu-Feng Li, Baigui Sun, Hao Li, Rong Jin

In this work we develop a simple yet powerful framework, whose key idea is to select a subset of training examples from the unlabeled data when performing existing SSL methods so that only the unlabeled examples with pseudo labels related to the labeled data will be used to train models.

Semi-Supervised Image Classification

Recursive Fusion and Deformable Spatiotemporal Attention for Video Compression Artifact Reduction

no code implementations4 Aug 2021 Minyi Zhao, Yi Xu, Shuigeng Zhou

A number of deep learning based algorithms have been proposed to recover high-quality videos from low-quality compressed ones.

Video Compression

MonoIndoor: Towards Good Practice of Self-Supervised Monocular Depth Estimation for Indoor Environments

no code implementations ICCV 2021 Pan Ji, Runze Li, Bir Bhanu, Yi Xu

The effectiveness of each module is shown through a carefully conducted ablation study and the demonstration of the state-of-the-art performance on three indoor datasets, \ie, EuRoC, NYUv2, and 7-scenes.

Monocular Depth Estimation Pose Estimation

Rethinking Adam: A Twofold Exponential Moving Average Approach

no code implementations22 Jun 2021 Yizhou Wang, Yue Kang, Can Qin, Huan Wang, Yi Xu, Yulun Zhang, Yun Fu

The intuition is that gradient with momentum contains more accurate directional information and therefore its second moment estimation is a more favorable option for learning rate scaling than that of the raw gradient.

Effective Model Sparsification by Scheduled Grow-and-Prune Methods

1 code implementation ICLR 2022 Xiaolong Ma, Minghai Qin, Fei Sun, Zejiang Hou, Kun Yuan, Yi Xu, Yanzhi Wang, Yen-Kuang Chen, Rong Jin, Yuan Xie

It addresses the shortcomings of the previous works by repeatedly growing a subset of layers to dense and then pruning them back to sparse after some training.

Image Classification

Dialogue-oriented Pre-training

1 code implementation Findings (ACL) 2021 Yi Xu, Hai Zhao

Pre-trained language models (PrLM) has been shown powerful in enhancing a broad range of downstream tasks including various dialogue related ones.

Language Modelling

Boosting the Performance of Video Compression Artifact Reduction with Reference Frame Proposals and Frequency Domain Information

no code implementations31 May 2021 Yi Xu, Minyi Zhao, Jing Liu, Xinjian Zhang, Longwen Gao, Shuigeng Zhou, Huyang Sun

Many deep learning based video compression artifact removal algorithms have been proposed to recover high-quality videos from low-quality compressed videos.

Video Compression

Dynamic Dual Sampling Module for Fine-Grained Semantic Segmentation

no code implementations25 May 2021 Chen Shi, Xiangtai Li, Yanran Wu, Yunhai Tong, Yi Xu

Representation of semantic context and local details is the essential issue for building modern semantic segmentation models.

Semantic Segmentation

NeuLF: Efficient Novel View Synthesis with Neural 4D Light Field

no code implementations15 May 2021 Zhong Li, Liangchen Song, Celong Liu, Junsong Yuan, Yi Xu

In this paper, we present an efficient and robust deep learning solution for novel view synthesis of complex scenes.

Novel View Synthesis

Why Does Multi-Epoch Training Help?

no code implementations13 May 2021 Yi Xu, Qi Qian, Hao Li, Rong Jin

Stochastic gradient descent (SGD) has become the most attractive optimization method in training large-scale deep neural networks due to its simplicity, low computational cost in each updating step, and good performance.

A Novel Convergence Analysis for Algorithms of the Adam Family and Beyond

no code implementations30 Apr 2021 Zhishuai Guo, Yi Xu, Wotao Yin, Rong Jin, Tianbao Yang

Our analysis exhibits that an increasing or large enough "momentum" parameter for the first-order moment used in practice is sufficient to ensure Adam and its many variants converge under a mild boundness condition on the adaptive scaling factor of the step size.

Bilevel Optimization

A Theoretical Analysis of Learning with Noisily Labeled Data

no code implementations8 Apr 2021 Yi Xu, Qi Qian, Hao Li, Rong Jin

Noisy labels are very common in deep supervised learning.

Federated Deep AUC Maximization for Heterogeneous Data with a Constant Communication Complexity

1 code implementation9 Feb 2021 Zhuoning Yuan, Zhishuai Guo, Yi Xu, Yiming Ying, Tianbao Yang

Deep AUC (area under the ROC curve) Maximization (DAM) has attracted much attention recently due to its great potential for imbalanced data classification.

Federated Learning

A Convergence Theory Towards Practical Over-parameterized Deep Neural Networks

no code implementations12 Jan 2021 Asaf Noy, Yi Xu, Yonathan Aflalo, Lihi Zelnik-Manor, Rong Jin

We show that convergence to a global minimum is guaranteed for networks with widths quadratic in the sample size and linear in their depth at a time logarithmic in both.

Attentional-Biased Stochastic Gradient Descent

no code implementations13 Dec 2020 Qi Qi, Yi Xu, Rong Jin, Wotao Yin, Tianbao Yang

In this paper, we present a simple yet effective method (ABSGD) for addressing the data imbalance issue in deep learning.

Classification General Classification +2

PoP-Net: Pose over Parts Network for Multi-Person 3D Pose Estimation from a Depth Image

1 code implementation12 Dec 2020 Yuliang Guo, Zhong Li, Zekun Li, Xiangyu Du, Shuxue Quan, Yi Xu

In this paper, a real-time method called PoP-Net is proposed to predict multi-person 3D poses from a depth image.

3D Pose Estimation Data Augmentation

WeMix: How to Better Utilize Data Augmentation

no code implementations3 Oct 2020 Yi Xu, Asaf Noy, Ming Lin, Qi Qian, Hao Li, Rong Jin

To this end, we develop two novel algorithms, termed "AugDrop" and "MixLoss", to correct the data bias in the data augmentation.

Data Augmentation

Topic-Aware Multi-turn Dialogue Modeling

1 code implementation26 Sep 2020 Yi Xu, Hai Zhao, Zhuosheng Zhang

In the retrieval-based multi-turn dialogue modeling, it remains a challenge to select the most appropriate response according to extracting salient features in context utterances.

Retrieval

Object Detection in the Context of Mobile Augmented Reality

no code implementations15 Aug 2020 Xiang Li, Yuan Tian, Fuyao Zhang, Shuxue Quan, Yi Xu

Ordinary object detection approaches process information from the images only, and they are oblivious to the camera pose with regard to the environment and the scale of the environment.

object-detection Real-Time Object Detection

Talking-head Generation with Rhythmic Head Motion

1 code implementation16 Jul 2020 Lele Chen, Guofeng Cui, Celong Liu, Zhong Li, Ziyi Kou, Yi Xu, Chenliang Xu

When people deliver a speech, they naturally move heads, and this rhythmic head motion conveys prosodic information.

Talking Head Generation

Towards Understanding Label Smoothing

no code implementations20 Jun 2020 Yi Xu, Yuanhong Xu, Qi Qian, Hao Li, Rong Jin

Label smoothing regularization (LSR) has a great success in training deep neural networks by stochastic algorithms such as stochastic gradient descent and its variants.

An Online Method for A Class of Distributionally Robust Optimization with Non-Convex Objectives

1 code implementation NeurIPS 2021 Qi Qi, Zhishuai Guo, Yi Xu, Rong Jin, Tianbao Yang

In this paper, we propose a practical online method for solving a class of distributionally robust optimization (DRO) with non-convex objectives, which has important applications in machine learning for improving the robustness of neural networks.

Evaluating Features and Metrics for High-Quality Simulation of Early Vocal Learning of Vowels

no code implementations20 May 2020 Branislav Gerazov, Daniel van Niekerk, Anqi Xu, Paul Konstantin Krug, Peter Birkholz, Yi Xu

One of the crucial parameters in these simulations is the choice of features and a metric to evaluate the acoustic error between the synthesised sound and the reference target.

Speech Synthesis

Relational Learning between Multiple Pulmonary Nodules via Deep Set Attention Transformers

no code implementations12 Apr 2020 Jiancheng Yang, Haoran Deng, Xiaoyang Huang, Bingbing Ni, Yi Xu

In this study, we propose a multiple instance learning (MIL) approach and empirically prove the benefit to learn the relations between multiple nodules.

Multiple Instance Learning Relational Reasoning

Adaptive Fractional Dilated Convolution Network for Image Aesthetics Assessment

no code implementations CVPR 2020 Qiuyu Chen, Wei zhang, Ning Zhou, Peng Lei, Yi Xu, Yu Zheng, Jianping Fan

Specifically, the fractional dilated kernel is adaptively constructed according to the image aspect ratios, where the interpolation of nearest two integers dilated kernels is used to cope with the misalignment of fractional sampling.

Optimal Epoch Stochastic Gradient Descent Ascent Methods for Min-Max Optimization

no code implementations NeurIPS 2020 Yan Yan, Yi Xu, Qihang Lin, Wei Liu, Tianbao Yang

In this paper, we bridge this gap by providing a sharp analysis of epoch-wise stochastic gradient descent ascent method (referred to as Epoch-GDA) for solving strongly convex strongly concave (SCSC) min-max problems, without imposing any additional assumption about smoothness or the function's structure.

Occlum: Secure and Efficient Multitasking Inside a Single Enclave of Intel SGX

7 code implementations21 Jan 2020 Youren Shen, Hongliang Tian, Yu Chen, Kang Chen, Runji Wang, Yi Xu, Yubin Xia

SFI is a software instrumentation technique for sandboxing untrusted modules (called domains).

Operating Systems Hardware Architecture Cryptography and Security

Quaternion Product Units for Deep Learning on 3D Rotation Groups

1 code implementation CVPR 2020 Xuan Zhang, Shaofei Qin, Yi Xu, Hongteng Xu

We propose a novel quaternion product unit (QPU) to represent data on 3D rotation groups.

Non-Local ConvLSTM for Video Compression Artifact Reduction

no code implementations ICCV 2019 Yi Xu, Longwen Gao, Kai Tian, Shuigeng Zhou, Huyang Sun

Video compression artifact reduction aims to recover high-quality videos from low-quality compressed videos.

Video Compression

Probabilistic Radiomics: Ambiguous Diagnosis with Controllable Shape Analysis

no code implementations20 Oct 2019 Jiancheng Yang, Rongyao Fang, Bingbing Ni, Yamin Li, Yi Xu, Linguo Li

The final diagnosis is obtained by combining the ambiguity prior sample and lesion representation, and the whole network named $DenseSharp^{+}$ is end-to-end trainable.

Probabilistic Deep Learning

On Leveraging the Visual Modality for Neural Machine Translation

no code implementations WS 2019 Vikas Raunak, Sang Keun Choe, Quanyang Lu, Yi Xu, Florian Metze

Leveraging the visual modality effectively for Neural Machine Translation (NMT) remains an open problem in computational linguistics.

Multimodal Machine Translation NMT +1

Evaluating and Boosting Uncertainty Quantification in Classification

no code implementations13 Sep 2019 Xiaoyang Huang, Jiancheng Yang, Linguo Li, Haoran Deng, Bingbing Ni, Yi Xu

Emergence of artificial intelligence techniques in biomedical applications urges the researchers to pay more attention on the uncertainty quantification (UQ) in machine-assisted medical decision making.

Classification Decision Making +1

Stochastic Optimization for Non-convex Inf-Projection Problems

no code implementations ICML 2020 Yan Yan, Yi Xu, Lijun Zhang, Xiaoyu Wang, Tianbao Yang

In this paper, we study a family of non-convex and possibly non-smooth inf-projection minimization problems, where the target objective function is equal to minimization of a joint function over another variable.

Stochastic Optimization

3D Virtual Garment Modeling from RGB Images

no code implementations31 Jul 2019 Yi Xu, Shanglin Yang, Wei Sun, Li Tan, Kefeng Li, Hui Zhou

The predicted landmarks are used for estimating sizing information of the garment.

Mixed Reality Multi-Task Learning

Optimizing Interim Analysis Timing for Bayesian Adaptive Commensurate Designs

1 code implementation17 May 2019 Xiao Wu, Yi Xu, Bradley P. Carlin

In developing products for rare diseases, statistical challenges arise due to the limited number of patients available for participation in drug trials and other clinical research.

Applications Computation Methodology

Stochastic Primal-Dual Algorithms with Faster Convergence than $O(1/\sqrt{T})$ for Problems without Bilinear Structure

no code implementations23 Apr 2019 Yan Yan, Yi Xu, Qihang Lin, Lijun Zhang, Tianbao Yang

The main contribution of this paper is the design and analysis of new stochastic primal-dual algorithms that use a mixture of stochastic gradient updates and a logarithmic number of deterministic dual updates for solving a family of convex-concave problems with no bilinear structure assumed.

Quaternion Convolutional Neural Networks

1 code implementation ECCV 2018 Xuanyu Zhu, Yi Xu, Hongteng Xu, Changjian Chen

Neural networks in the real domain have been studied for a long time and achieved promising results in many vision tasks for recent years.

Denoising Image Classification

Disentangled Deep Autoencoding Regularization for Robust Image Classification

no code implementations27 Feb 2019 Zhenyu Duan, Martin Renqiang Min, Li Erran Li, Mingbo Cai, Yi Xu, Bingbing Ni

In spite of achieving revolutionary successes in machine learning, deep convolutional neural networks have been recently found to be vulnerable to adversarial attacks and difficult to generalize to novel test images with reasonably large geometric transformations.

Classification General Classification +2

Analogy Search Engine: Finding Analogies in Cross-Domain Research Papers

no code implementations17 Dec 2018 Jieli Zhou, Yuntao Zhou, Yi Xu

ASE combines recent theories and methods from Computational Analogy and Natural Language Processing to go beyond keyword-based lexical search and discover the deeper analogical relationships among research paper abstracts.

Stochastic Optimization for DC Functions and Non-smooth Non-convex Regularizers with Non-asymptotic Convergence

no code implementations28 Nov 2018 Yi Xu, Qi Qi, Qihang Lin, Rong Jin, Tianbao Yang

In this paper, we propose new stochastic optimization algorithms and study their first-order convergence theories for solving a broad family of DC functions.

Stochastic Optimization

Geometric Constrained Joint Lane Segmentation and Lane Boundary Detection

no code implementations ECCV 2018 Jie Zhang, Yi Xu, Bingbing Ni, Zhenyu Duan

The main contributions of the proposed frame- work are highlighted in two facets: (1) We put forward a multiple-task learning framework with mutually interlinked sub-structures between lane segmentation and lane boundary detection to improve overall performance.

Boundary Detection Lane Detection

SADAGRAD: Strongly Adaptive Stochastic Gradient Methods

no code implementations ICML 2018 Zaiyi Chen, Yi Xu, Enhong Chen, Tianbao Yang

Although the convergence rates of existing variants of ADAGRAD have a better dependence on the number of iterations under the strong convexity condition, their iteration complexities have a explicitly linear dependence on the dimensionality of the problem.

A Variational Prosody Model for the decomposition and synthesis of speech prosody

1 code implementation22 Jun 2018 Branislav Gerazov, Gérard Bailly, Omar Mohammed, Yi Xu, Philip N. Garner

Our work bridges between a comprehensive generative model of intonation and state-of-the-art AI techniques.

Speech Synthesis

Crowd Counting via Adversarial Cross-Scale Consistency Pursuit

1 code implementation CVPR 2018 Zan Shen, Yi Xu, Bingbing Ni, Minsi Wang, Jianguo Hu, Xiaokang Yang

Crowd counting or density estimation is a challenging task in computer vision due to large scale variations, perspective distortions and serious occlusions, etc.

Crowd Counting Density Estimation

Learning with Non-Convex Truncated Losses by SGD

no code implementations21 May 2018 Yi Xu, Shenghuo Zhu, Sen yang, Chi Zhang, Rong Jin, Tianbao Yang

Learning with a {\it convex loss} function has been a dominating paradigm for many years.

NEON+: Accelerated Gradient Methods for Extracting Negative Curvature for Non-Convex Optimization

no code implementations4 Dec 2017 Yi Xu, Rong Jin, Tianbao Yang

Accelerated gradient (AG) methods are breakthroughs in convex optimization, improving the convergence rate of the gradient descent method for optimization with smooth functions.

Adaptive SVRG Methods under Error Bound Conditions with Unknown Growth Parameter

no code implementations NeurIPS 2017 Yi Xu, Qihang Lin, Tianbao Yang

The most studied error bound is the quadratic error bound, which generalizes strong convexity and is satisfied by a large family of machine learning problems.

BIG-bench Machine Learning Stochastic Optimization

ADMM without a Fixed Penalty Parameter: Faster Convergence with New Adaptive Penalization

no code implementations NeurIPS 2017 Yi Xu, Mingrui Liu, Qihang Lin, Tianbao Yang

The novelty of the proposed scheme lies at that it is adaptive to a local sharpness property of the objective function, which marks the key difference from previous adaptive scheme that adjusts the penalty parameter per-iteration based on certain conditions on iterates.

Stochastic Optimization

First-order Stochastic Algorithms for Escaping From Saddle Points in Almost Linear Time

no code implementations NeurIPS 2018 Yi Xu, Rong Jin, Tianbao Yang

Two classes of methods have been proposed for escaping from saddle points with one using the second-order information carried by the Hessian and the other adding the noise into the first-order information.

Flexible Network Binarization with Layer-wise Priority

no code implementations13 Sep 2017 Lixue Zhuang, Yi Xu, Bingbing Ni, Hongteng Xu

In this work, we reveal an important fact that binarizing different layers has a widely-varied effect on the compression ratio of network and the loss of performance.

Binarization Pedestrian Detection

Stochastic Convex Optimization: Faster Local Growth Implies Faster Global Convergence

no code implementations ICML 2017 Yi Xu, Qihang Lin, Tianbao Yang

In this paper, a new theory is developed for first-order stochastic convex optimization, showing that the global convergence rate is sufficiently quantified by a local growth rate of the objective function in a neighborhood of the optimal solutions.

Stochastic Optimization

Efficient Non-oblivious Randomized Reduction for Risk Minimization with Improved Excess Risk Guarantee

no code implementations6 Dec 2016 Yi Xu, Haiqin Yang, Lijun Zhang, Tianbao Yang

Previously, oblivious random projection based approaches that project high dimensional features onto a random subspace have been used in practice for tackling high-dimensionality challenge in machine learning.

BIG-bench Machine Learning

Homotopy Smoothing for Non-Smooth Problems with Lower Complexity than O(1/\epsilon)

no code implementations NeurIPS 2016 Yi Xu, Yan Yan, Qihang Lin, Tianbao Yang

To the best of our knowledge, this is the lowest iteration complexity achieved so far for the considered non-smooth optimization problems without strong convexity assumption.

Homotopy Smoothing for Non-Smooth Problems with Lower Complexity than $O(1/ε)$

no code implementations NeurIPS 2016 Yi Xu, Yan Yan, Qihang Lin, Tianbao Yang

In this work, we will show that the proposed HOPS achieved a lower iteration complexity of $\widetilde O(1/\epsilon^{1-\theta})$\footnote{$\widetilde O()$ suppresses a logarithmic factor.}

Accelerate Stochastic Subgradient Method by Leveraging Local Growth Condition

no code implementations4 Jul 2016 Yi Xu, Qihang Lin, Tianbao Yang

In particular, if the objective function $F(\mathbf w)$ in the $\epsilon$-sublevel set grows as fast as $\|\mathbf w - \mathbf w_*\|_2^{1/\theta}$, where $\mathbf w_*$ represents the closest optimal solution to $\mathbf w$ and $\theta\in(0, 1]$ quantifies the local growth rate, the iteration complexity of first-order stochastic optimization for achieving an $\epsilon$-optimal solution can be $\widetilde O(1/\epsilon^{2(1-\theta)})$, which is optimal at most up to a logarithmic factor.

Stochastic Optimization

Feature Selection Based on Confidence Machine

no code implementations20 Oct 2014 Chang Liu, Yi Xu

We propose a filter method for unsupervised feature selection which is based on the Confidence Machine.

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