Search Results for author: Ning Xu

Found 70 papers, 31 papers with code

Variational Label Enhancement

no code implementations ICML 2020 Ning Xu, Yun-Peng Liu, Jun Shu, Xin Geng

Label distribution covers a certain number of labels, representing the degree to which each label describes the instance.

Multi-Label Learning Variational Inference

Self-Attention Graph Residual Convolutional Networks for Event Detection with dependency relations

no code implementations Findings (EMNLP) 2021 AnAn Liu, Ning Xu, Haozhe Liu

While existing GCN-based methods explore latent node-to-node dependency relations according to a stationary adjacency tensor, an attention-based dynamic tensor, which can pay much attention to the key node like event trigger or its neighboring nodes, has not been developed.

Event Detection

Decomposition-based Generation Process for Instance-Dependent Partial Label Learning

no code implementations8 Apr 2022 Congyu Qiao, Ning Xu, Xin Geng

Most existing PLL approaches assume that the incorrect labels in each training example are randomly picked as the candidate labels and model the generation process of the candidate labels in a simple way.

Partial Label Learning

An application of Pixel Interval Down-sampling (PID) for dense tiny microorganism counting on environmental microorganism images

no code implementations4 Apr 2022 Jiawei Zhang, Ning Xu, Chen Li, Md Mamunur Rahaman, Yu-Dong Yao, Yu-Hao Lin, Jinghua Zhang, Tao Jiang, Wenjun Qin, Marcin Grzegorzek

Experimental result shows that the proposed PID-Net has the best performance and potential for dense tiny objects counting tasks, which achieves 96. 97% counting accuracy on the dataset with 2448 yeast cell images.

CM-GAN: Image Inpainting with Cascaded Modulation GAN and Object-Aware Training

1 code implementation22 Mar 2022 Haitian Zheng, Zhe Lin, Jingwan Lu, Scott Cohen, Eli Shechtman, Connelly Barnes, Jianming Zhang, Ning Xu, Sohrab Amirghodsi, Jiebo Luo

Recent image inpainting methods have made great progress but often struggle to generate plausible image structures when dealing with large holes in complex images.

Image Inpainting

Wavelet Knowledge Distillation: Towards Efficient Image-to-Image Translation

no code implementations12 Mar 2022 Linfeng Zhang, Xin Chen, Xiaobing Tu, Pengfei Wan, Ning Xu, Kaisheng Ma

Instead of directly distilling the generated images of teachers, wavelet knowledge distillation first decomposes the images into different frequency bands with discrete wavelet transformation and then only distills the high frequency bands.

Image-to-Image Translation Knowledge Distillation +1

End-to-end video instance segmentation via spatial-temporal graph neural networks

1 code implementation ICCV 2021 Tao Wang, Ning Xu, Kean Chen, Weiyao Lin

Specifically, graph nodes representing instance features are used for detection and segmentation while graph edges representing instance relations are used for tracking.

Frame Instance Segmentation +2

Adaptive Cross-Layer Attention for Image Restoration

1 code implementation4 Mar 2022 Yancheng Wang, Ning Xu, Yingzhen Yang

In order to further enhance the learning capability and reduce the inference cost of CLA, we further propose Adaptive CLA, or ACLA, as an improved CLA.

Demosaicking Image Compression +3

SpaceEdit: Learning a Unified Editing Space for Open-Domain Image Editing

no code implementations30 Nov 2021 Jing Shi, Ning Xu, Haitian Zheng, Alex Smith, Jiebo Luo, Chenliang Xu

Recently, large pretrained models (e. g., BERT, StyleGAN, CLIP) have shown great knowledge transfer and generalization capability on various downstream tasks within their domains.

Image-to-Image Translation Transfer Learning

Exploring the Semi-supervised Video Object Segmentation Problem from a Cyclic Perspective

1 code implementation2 Nov 2021 Yuxi Li, Ning Xu, Wenjie Yang, John See, Weiyao Lin

We conduct comprehensive comparison and detailed analysis on challenging benchmarks of DAVIS16, DAVIS17 and Youtube-VOS, demonstrating that the cyclic mechanism is helpful to enhance segmentation quality, improve the robustness of VOS systems, and further provide qualitative comparison and interpretation on how different VOS algorithms work.

Semantic Segmentation Semi-Supervised Video Object Segmentation +1

Instance-Dependent Partial Label Learning

1 code implementation NeurIPS 2021 Ning Xu, Congyu Qiao, Xin Geng, Min-Ling Zhang

In this paper, we consider instance-dependent PLL and assume that each example is associated with a latent label distribution constituted by the real number of each label, representing the degree to each label describing the feature.

Partial Label Learning

TVT: Transferable Vision Transformer for Unsupervised Domain Adaptation

1 code implementation12 Aug 2021 Jinyu Yang, Jingjing Liu, Ning Xu, Junzhou Huang

With the recent exponential increase in applying Vision Transformer (ViT) to vision tasks, the capability of ViT in adapting cross-domain knowledge, however, remains unexplored in the literature.

Transfer Learning Unsupervised Domain Adaptation

Learning by Planning: Language-Guided Global Image Editing

1 code implementation CVPR 2021 Jing Shi, Ning Xu, Yihang Xu, Trung Bui, Franck Dernoncourt, Chenliang Xu

Recently, language-guided global image editing draws increasing attention with growing application potentials.

Learngene: From Open-World to Your Learning Task

1 code implementation12 Jun 2021 Qiufeng Wang, Xin Geng, Shuxia Lin, Shiyu Xia, Lei Qi, Ning Xu

Moreover, the learngene, i. e., the gene for learning initialization rules of the target model, is proposed to inherit the meta-knowledge from the collective model and reconstruct a lightweight individual model on the target task.

Language-Guided Global Image Editing via Cross-Modal Cyclic Mechanism

no code implementations ICCV 2021 Wentao Jiang, Ning Xu, Jiayun Wang, Chen Gao, Jing Shi, Zhe Lin, Si Liu

Given the cycle, we propose several free augmentation strategies to help our model understand various editing requests given the imbalanced dataset.

A Simple Baseline for Weakly-Supervised Scene Graph Generation

no code implementations ICCV 2021 Jing Shi, Yiwu Zhong, Ning Xu, Yin Li, Chenliang Xu

We investigate the weakly-supervised scene graph generation, which is a challenging task since no correspondence of label and object is provided.

Contrastive Learning Graph Generation +2

Semantic Layout Manipulation with High-Resolution Sparse Attention

1 code implementation14 Dec 2020 Haitian Zheng, Zhe Lin, Jingwan Lu, Scott Cohen, Jianming Zhang, Ning Xu, Jiebo Luo

A core problem of this task is how to transfer visual details from the input images to the new semantic layout while making the resulting image visually realistic.

Mask Guided Matting via Progressive Refinement Network

1 code implementation CVPR 2021 Qihang Yu, Jianming Zhang, He Zhang, Yilin Wang, Zhe Lin, Ning Xu, Yutong Bai, Alan Yuille

We propose Mask Guided (MG) Matting, a robust matting framework that takes a general coarse mask as guidance.

Image Matting

A Benchmark and Baseline for Language-Driven Image Editing

no code implementations5 Oct 2020 Jing Shi, Ning Xu, Trung Bui, Franck Dernoncourt, Zheng Wen, Chenliang Xu

To solve this new task, we first present a new language-driven image editing dataset that supports both local and global editing with editing operation and mask annotations.

Compact Learning for Multi-Label Classification

no code implementations18 Sep 2020 Jiaqi Lv, Tianran Wu, Chenglun Peng, Yun-Peng Liu, Ning Xu, Xin Geng

In this paper, we present a compact learning (CL) framework to embed the features and labels simultaneously and with mutual guidance.

Classification Dimensionality Reduction +3

High-Resolution Deep Image Matting

no code implementations14 Sep 2020 Haichao Yu, Ning Xu, Zilong Huang, Yuqian Zhou, Humphrey Shi

Image matting is a key technique for image and video editing and composition.

Image Matting

Finding Action Tubes with a Sparse-to-Dense Framework

no code implementations30 Aug 2020 Yuxi Li, Weiyao Lin, Tao Wang, John See, Rui Qian, Ning Xu, Li-Min Wang, Shugong Xu

The task of spatial-temporal action detection has attracted increasing attention among researchers.

Action Detection

CFAD: Coarse-to-Fine Action Detector for Spatiotemporal Action Localization

no code implementations ECCV 2020 Yuxi Li, Weiyao Lin, John See, Ning Xu, Shugong Xu, Ke Yan, Cong Yang

Most current pipelines for spatio-temporal action localization connect frame-wise or clip-wise detection results to generate action proposals, where only local information is exploited and the efficiency is hindered by dense per-frame localization.

Action Detection Frame +2

Rademacher upper bounds for cross-validation errors with an application to the lasso

1 code implementation30 Jul 2020 Ning Xu, Timothy C. G. Fisher, Jian Hong

We establish a general upper bound for $K$-fold cross-validation ($K$-CV) errors that can be adapted to many $K$-CV-based estimators and learning algorithms.

Variable Selection

Instrument variable detection with graph learning : an application to high dimensional GIS-census data for house pricing

1 code implementation30 Jul 2020 Ning Xu, Timothy C. G. Fisher, Jian Hong

In this paper, we merge two well-known tools from machine learning and biostatistics---variable selection algorithms and probablistic graphs---to estimate house prices and the corresponding causal structure using 2010 data on Sydney.

Graph Learning Variable Selection

Solar: $L_0$ solution path averaging for fast and accurate variable selection in high-dimensional data

1 code implementation30 Jul 2020 Ning Xu, Timothy C. G. Fisher

We propose a new variable selection algorithm, subsample-ordered least-angle regression (solar), and its coordinate descent generalization, solar-cd.

Variable Selection

Accuracy and stability of solar variable selection comparison under complicated dependence structures

2 code implementations30 Jul 2020 Ning Xu, Timothy C. G. Fisher, Jian Hong

In this paper we focus on the empirical variable-selection peformance of subsample-ordered least angle regression (Solar) -- a novel ultrahigh dimensional redesign of lasso -- on the empirical data with complicated dependence structures and, hence, severe multicollinearity and grouping effect issues.

Graph Learning Variable Selection

Incorporating Reinforced Adversarial Learning in Autoregressive Image Generation

no code implementations ECCV 2020 Kenan E. Ak, Ning Xu, Zhe Lin, Yilin Wang

To our best knowledge, the proposed method is first to enable adversarial learning in autoregressive models for image generation.

Image Generation

Multiple Sound Sources Localization from Coarse to Fine

1 code implementation ECCV 2020 Rui Qian, Di Hu, Heinrich Dinkel, Mengyue Wu, Ning Xu, Weiyao Lin

How to visually localize multiple sound sources in unconstrained videos is a formidable problem, especially when lack of the pairwise sound-object annotations.

AOWS: Adaptive and optimal network width search with latency constraints

1 code implementation CVPR 2020 Maxim Berman, Leonid Pishchulin, Ning Xu, Matthew B. Blaschko, Gerard Medioni

We introduce a novel efficient one-shot NAS approach to optimally search for channel numbers, given latency constraints on a specific hardware.

Neural Architecture Search

Human in Events: A Large-Scale Benchmark for Human-centric Video Analysis in Complex Events

no code implementations9 May 2020 Weiyao Lin, Huabin Liu, Shizhan Liu, Yuxi Li, Rui Qian, Tao Wang, Ning Xu, Hongkai Xiong, Guo-Jun Qi, Nicu Sebe

We demonstrate that the proposed method is able to boost the performance of existing pose estimation pipelines on our HiEve dataset.

Pose Estimation

Minimizing FLOPs to Learn Efficient Sparse Representations

1 code implementation ICLR 2020 Biswajit Paria, Chih-Kuan Yeh, Ian E. H. Yen, Ning Xu, Pradeep Ravikumar, Barnabás Póczos

Deep representation learning has become one of the most widely adopted approaches for visual search, recommendation, and identification.

Quantization Representation Learning

Getting to 99% Accuracy in Interactive Segmentation

3 code implementations17 Mar 2020 Marco Forte, Brian Price, Scott Cohen, Ning Xu, François Pitié

We propose a novel interactive architecture and a novel training scheme that are both tailored to better exploit the user workflow.

Interactive Segmentation

MILA: Multi-Task Learning from Videos via Efficient Inter-Frame Attention

no code implementations18 Feb 2020 Donghyun Kim, Tian Lan, Chuhang Zou, Ning Xu, Bryan A. Plummer, Stan Sclaroff, Jayan Eledath, Gerard Medioni

We embed the attention module in a ``slow-fast'' architecture, where the slower network runs on sparsely sampled keyframes and the light-weight shallow network runs on non-keyframes at a high frame rate.

Frame Multi-Task Learning

An Internal Learning Approach to Video Inpainting

1 code implementation ICCV 2019 Haotian Zhang, Long Mai, Ning Xu, Zhaowen Wang, John Collomosse, Hailin Jin

We propose a novel video inpainting algorithm that simultaneously hallucinates missing appearance and motion (optical flow) information, building upon the recent 'Deep Image Prior' (DIP) that exploits convolutional network architectures to enforce plausible texture in static images.

Optical Flow Estimation Video Inpainting

Large-scale Tag-based Font Retrieval with Generative Feature Learning

no code implementations ICCV 2019 Tianlang Chen, Zhaowen Wang, Ning Xu, Hailin Jin, Jiebo Luo

In this paper, we address the problem of large-scale tag-based font retrieval which aims to bring semantics to the font selection process and enable people without expert knowledge to use fonts effectively.

TAG

Controllable Artistic Text Style Transfer via Shape-Matching GAN

1 code implementation ICCV 2019 Shuai Yang, Zhangyang Wang, Zhaowen Wang, Ning Xu, Jiaying Liu, Zongming Guo

In this paper, we present the first text style transfer network that allows for real-time control of the crucial stylistic degree of the glyph through an adjustable parameter.

Style Transfer Text Style Transfer

Fast User-Guided Video Object Segmentation by Interaction-and-Propagation Networks

1 code implementation CVPR 2019 Seoung Wug Oh, Joon-Young Lee, Ning Xu, Seon Joo Kim

We propose a new multi-round training scheme for the interactive video object segmentation so that the networks can learn how to understand the user's intention and update incorrect estimations during the training.

Interactive Video Object Segmentation Semantic Segmentation +1

Streamlined Dense Video Captioning

1 code implementation CVPR 2019 Jonghwan Mun, Linjie Yang, Zhou Ren, Ning Xu, Bohyung Han

Dense video captioning is an extremely challenging task since accurate and coherent description of events in a video requires holistic understanding of video contents as well as contextual reasoning of individual events.

Dense Video Captioning

M2KD: Multi-model and Multi-level Knowledge Distillation for Incremental Learning

no code implementations3 Apr 2019 Peng Zhou, Long Mai, Jianming Zhang, Ning Xu, Zuxuan Wu, Larry S. Davis

Instead of sequentially distilling knowledge only from the last model, we directly leverage all previous model snapshots.

Incremental Learning Knowledge Distillation

Video Object Segmentation using Space-Time Memory Networks

3 code implementations ICCV 2019 Seoung Wug Oh, Joon-Young Lee, Ning Xu, Seon Joo Kim

In our framework, the past frames with object masks form an external memory, and the current frame as the query is segmented using the mask information in the memory.

Ranked #4 on Interactive Video Object Segmentation on DAVIS 2017 (using extra training data)

Frame Interactive Video Object Segmentation +3

Singing voice conversion with non-parallel data

no code implementations11 Mar 2019 Xin Chen, Wei Chu, Jinxi Guo, Ning Xu

F0 and aperiodic are obtained through the original singing voice, and used with acoustic features to reconstruct the target singing voice through a vocoder.

Automatic Speech Recognition Voice Conversion

Slimmable Neural Networks

3 code implementations ICLR 2019 Jiahui Yu, Linjie Yang, Ning Xu, Jianchao Yang, Thomas Huang

Instead of training individual networks with different width configurations, we train a shared network with switchable batch normalization.

Instance Segmentation Keypoint Detection +2

Deep neural network based i-vector mapping for speaker verification using short utterances

no code implementations16 Oct 2018 Jinxi Guo, Ning Xu, Kailun Qian, Yang Shi, Kaiyuan Xu, Ying-Nian Wu, Abeer Alwan

Experimental results using the NIST SRE 2010 dataset show that both methods provide significant improvement and result in a max of 28. 43% relative improvement in Equal Error Rates from a baseline system, when using deep encoder with residual blocks and adding an additional phoneme vector.

Speaker Recognition Speaker Verification +1

YouTube-VOS: Sequence-to-Sequence Video Object Segmentation

4 code implementations ECCV 2018 Ning Xu, Linjie Yang, Yuchen Fan, Jianchao Yang, Dingcheng Yue, Yuchen Liang, Brian Price, Scott Cohen, Thomas Huang

End-to-end sequential learning to explore spatial-temporal features for video segmentation is largely limited by the scale of available video segmentation datasets, i. e., even the largest video segmentation dataset only contains 90 short video clips.

One-shot visual object segmentation Optical Flow Estimation +4

EIGEN: Ecologically-Inspired GENetic Approach for Neural Network Structure Searching from Scratch

no code implementations CVPR 2019 Jian Ren, Zhe Li, Jianchao Yang, Ning Xu, Tianbao Yang, David J. Foran

In this paper, we propose an Ecologically-Inspired GENetic (EIGEN) approach that uses the concept of succession, extinction, mimicry, and gene duplication to search neural network structure from scratch with poorly initialized simple network and few constraints forced during the evolution, as we assume no prior knowledge about the task domain.

Factorized Adversarial Networks for Unsupervised Domain Adaptation

no code implementations4 Jun 2018 Jian Ren, Jianchao Yang, Ning Xu, David J. Foran

In this paper, we propose Factorized Adversarial Networks (FAN) to solve unsupervised domain adaptation problems for image classification tasks.

General Classification Image Classification +1

Learn to Combine Modalities in Multimodal Deep Learning

1 code implementation29 May 2018 Kuan Liu, Yanen Li, Ning Xu, Prem Natarajan

Combining complementary information from multiple modalities is intuitively appealing for improving the performance of learning-based approaches.

Multimodal Deep Learning

Learning $3$D-FilterMap for Deep Convolutional Neural Networks

no code implementations5 Jan 2018 Yingzhen Yang, Jianchao Yang, Ning Xu, Wei Han

Due to the weight sharing scheme, the parameter size of the $3$D-FilterMap is much smaller than that of the filters to be learned in the conventional convolution layer when $3$D-FilterMap generates the same number of filters.

Deep GrabCut for Object Selection

no code implementations2 Jul 2017 Ning Xu, Brian Price, Scott Cohen, Jimei Yang, Thomas Huang

In this paper, we propose a novel segmentation approach that uses a rectangle as a soft constraint by transforming it into an Euclidean distance map.

Instance Segmentation Interactive Segmentation +1

Multi-Label Learning with Label Enhancement

no code implementations26 Jun 2017 Ruifeng Shao, Ning Xu, Xin Geng

To solve this problem, we assume that each multi-label instance is described by a vector of latent real-valued labels, which can reflect the importance of the corresponding labels.

Multi-Label Learning

$\left( β, \varpi \right)$-stability for cross-validation and the choice of the number of folds

no code implementations20 May 2017 Ning Xu, Jian Hong, Timothy C. G. Fisher

The $\left( \beta, \varpi \right)$-stability mathematically connects the generalization ability and the stability of the cross-validated model via the Rademacher complexity.

Model Selection

Deep Image Matting

7 code implementations CVPR 2017 Ning Xu, Brian Price, Scott Cohen, Thomas Huang

We evaluate our algorithm on the image matting benchmark, our testing set, and a wide variety of real images.

Semantic Image Matting

Finite-sample and asymptotic analysis of generalization ability with an application to penalized regression

no code implementations12 Sep 2016 Ning Xu, Jian Hong, Timothy C. G. Fisher

We show that the error bounds may be used for tuning key estimation hyper-parameters, such as the number of folds $K$ in cross-validation.

Model selection consistency from the perspective of generalization ability and VC theory with an application to Lasso

no code implementations1 Jun 2016 Ning Xu, Jian Hong, Timothy C. G. Fisher

In this paper, we study model selection from the perspective of generalization ability, under the framework of structural risk minimization (SRM) and Vapnik-Chervonenkis (VC) theory.

Model Selection

Intra-and-Inter-Constraint-based Video Enhancement based on Piecewise Tone Mapping

no code implementations21 Feb 2015 Yuanzhe Chen, Weiyao Lin, Chongyang Zhang, Zhenzhong Chen, Ning Xu, Jun Xie

In this paper, we propose a new intra-and-inter-constraint-based video enhancement approach aiming to 1) achieve high intra-frame quality of the entire picture where multiple region-of-interests (ROIs) can be adaptively and simultaneously enhanced, and 2) guarantee the inter-frame quality consistencies among video frames.

Frame Tone Mapping +1

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