Search Results for author: Chao Xu

Found 111 papers, 45 papers with code

The First International Ancient Chinese Word Segmentation and POS Tagging Bakeoff: Overview of the EvaHan 2022 Evaluation Campaign

no code implementations LT4HALA (LREC) 2022 Bin Li, Yiguo Yuan, Jingya Lu, Minxuan Feng, Chao Xu, Weiguang Qu, Dongbo Wang

This paper presents the results of the First Ancient Chinese Word Segmentation and POS Tagging Bakeoff (EvaHan), which was held at the Second Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA) 2022, in the context of the 13th Edition of the Language Resources and Evaluation Conference (LREC 2022).

Chinese Word Segmentation POS +2

A Cognitively Motivated Approach to Spatial Information Extraction

no code implementations EMNLP (SpLU) 2020 Chao Xu, Emmanuelle-Anna Dietz Saldanha, Dagmar Gromann, Beihai Zhou

We propose an automated spatial semantic analysis (ASSA) framework building on grammar and cognitive linguistic theories to identify spatial entities and relations, bringing together methods of spatial information extraction and cognitive frameworks on spatial language.

Learning to Deblur Polarized Images

no code implementations28 Feb 2024 Chu Zhou, Minggui Teng, Xinyu Zhou, Chao Xu, Boxin Sh

However, since the on-chip micro-polarizers block part of the light so that the sensor often requires a longer exposure time, the captured polarized images are prone to motion blur caused by camera shakes, leading to noticeable degradation in the computed DoP and AoP.

Deblurring Image Deblurring +2

PanGu-$π$: Enhancing Language Model Architectures via Nonlinearity Compensation

no code implementations27 Dec 2023 Yunhe Wang, Hanting Chen, Yehui Tang, Tianyu Guo, Kai Han, Ying Nie, Xutao Wang, Hailin Hu, Zheyuan Bai, Yun Wang, Fangcheng Liu, Zhicheng Liu, Jianyuan Guo, Sinan Zeng, Yinchen Zhang, Qinghua Xu, Qun Liu, Jun Yao, Chao Xu, DaCheng Tao

We then demonstrate that the proposed approach is significantly effective for enhancing the model nonlinearity through carefully designed ablations; thus, we present a new efficient model architecture for establishing modern, namely, PanGu-$\pi$.

Language Modelling

Towards Higher Ranks via Adversarial Weight Pruning

1 code implementation NeurIPS 2023 Yuchuan Tian, Hanting Chen, Tianyu Guo, Chao Xu, Yunhe Wang

To this end, we propose a Rank-based PruninG (RPG) method to maintain the ranks of sparse weights in an adversarial manner.

Model Compression Network Pruning

One-2-3-45++: Fast Single Image to 3D Objects with Consistent Multi-View Generation and 3D Diffusion

no code implementations14 Nov 2023 Minghua Liu, Ruoxi Shi, Linghao Chen, Zhuoyang Zhang, Chao Xu, Xinyue Wei, Hansheng Chen, Chong Zeng, Jiayuan Gu, Hao Su

Recent advancements in open-world 3D object generation have been remarkable, with image-to-3D methods offering superior fine-grained control over their text-to-3D counterparts.

Image Generation Image to 3D +1

Training A Multi-stage Deep Classifier with Feedback Signals

no code implementations12 Nov 2023 Chao Xu, Yu Yang, Rongzhao Wang, Guan Wang, Bojia Lin

Multi-Stage Classifier (MSC) - several classifiers working sequentially in an arranged order and classification decision is partially made at each step - is widely used in industrial applications for various resource limitation reasons.

Binary Classification

Learning with Noisy Labels Using Collaborative Sample Selection and Contrastive Semi-Supervised Learning

no code implementations24 Oct 2023 Qing Miao, Xiaohe Wu, Chao Xu, Yanli Ji, WangMeng Zuo, Yiwen Guo, Zhaopeng Meng

By incorporating auxiliary information from CLIP and utilizing prompt fine-tuning, we effectively eliminate noisy samples from the clean set and mitigate confirmation bias during training.

Learning with noisy labels

Zero123++: a Single Image to Consistent Multi-view Diffusion Base Model

1 code implementation23 Oct 2023 Ruoxi Shi, Hansheng Chen, Zhuoyang Zhang, Minghua Liu, Chao Xu, Xinyue Wei, Linghao Chen, Chong Zeng, Hao Su

We report Zero123++, an image-conditioned diffusion model for generating 3D-consistent multi-view images from a single input view.

FaceChain: A Playground for Human-centric Artificial Intelligence Generated Content

1 code implementation28 Aug 2023 Yang Liu, Cheng Yu, Lei Shang, Yongyi He, Ziheng Wu, Xingjun Wang, Chao Xu, Haoyu Xie, Weida Wang, Yuze Zhao, Lin Zhu, Chen Cheng, Weitao Chen, Yuan YAO, Wenmeng Zhou, Jiaqi Xu, Qiang Wang, Yingda Chen, Xuansong Xie, Baigui Sun

In this paper, we present FaceChain, a personalized portrait generation framework that combines a series of customized image-generation model and a rich set of face-related perceptual understanding models (\eg, face detection, deep face embedding extraction, and facial attribute recognition), to tackle aforementioned challenges and to generate truthful personalized portraits, with only a handful of portrait images as input.

Attribute Potrait Generation +1

WanJuan: A Comprehensive Multimodal Dataset for Advancing English and Chinese Large Models

1 code implementation21 Aug 2023 Conghui He, Zhenjiang Jin, Chao Xu, Jiantao Qiu, Bin Wang, Wei Li, Hang Yan, Jiaqi Wang, Dahua Lin

The rise in popularity of ChatGPT and GPT-4 has significantly accelerated the development of large models, leading to the creation of numerous impressive large language models(LLMs) and multimodal large language models (MLLMs).

GPT4Image: Can Large Pre-trained Models Help Vision Models on Perception Tasks?

1 code implementation1 Jun 2023 Ning Ding, Yehui Tang, Zhongqian Fu, Chao Xu, Kai Han, Yunhe Wang

We present a new learning paradigm in which the knowledge extracted from large pre-trained models are utilized to help models like CNN and ViT learn enhanced representations and achieve better performance.

Descriptive Image Classification

Multiscale Positive-Unlabeled Detection of AI-Generated Texts

3 code implementations29 May 2023 Yuchuan Tian, Hanting Chen, Xutao Wang, Zheyuan Bai, Qinghua Zhang, Ruifeng Li, Chao Xu, Yunhe Wang

Recent releases of Large Language Models (LLMs), e. g. ChatGPT, are astonishing at generating human-like texts, but they may impact the authenticity of texts.

Language Modelling text-classification +2

High-fidelity Generalized Emotional Talking Face Generation with Multi-modal Emotion Space Learning

no code implementations CVPR 2023 Chao Xu, Junwei Zhu, Jiangning Zhang, Yue Han, Wenqing Chu, Ying Tai, Chengjie Wang, Zhifeng Xie, Yong liu

Specifically, we supplement the emotion style in text prompts and use an Aligned Multi-modal Emotion encoder to embed the text, image, and audio emotion modality into a unified space, which inherits rich semantic prior from CLIP.

Talking Face Generation

Multimodal-driven Talking Face Generation via a Unified Diffusion-based Generator

no code implementations4 May 2023 Chao Xu, Shaoting Zhu, Junwei Zhu, Tianxin Huang, Jiangning Zhang, Ying Tai, Yong liu

More specifically, given a textured face as the source and the rendered face projected from the desired 3DMM coefficients as the target, our proposed Texture-Geometry-aware Diffusion Model decomposes the complex transfer problem into multi-conditional denoising process, where a Texture Attention-based module accurately models the correspondences between appearance and geometry cues contained in source and target conditions, and incorporate extra implicit information for high-fidelity talking face generation.

Denoising Face Swapping +1

Accelerated Distributed Aggregative Optimization

no code implementations17 Apr 2023 Jiaxu Liu, Song Chen, Shengze Cai, Chao Xu

In this paper, we investigate a distributed aggregative optimization problem in a network, where each agent has its own local cost function which depends not only on the local state variable but also on an aggregated function of state variables from all agents.

HybrIK-X: Hybrid Analytical-Neural Inverse Kinematics for Whole-body Mesh Recovery

1 code implementation12 Apr 2023 Jiefeng Li, Siyuan Bian, Chao Xu, Zhicun Chen, Lixin Yang, Cewu Lu

To address these issues, this paper presents a novel hybrid inverse kinematics solution, HybrIK, that integrates the merits of 3D keypoint estimation and body mesh recovery in a unified framework.

3D Human Pose Estimation 3D Human Reconstruction +1

DPP-based Client Selection for Federated Learning with Non-IID Data

no code implementations30 Mar 2023 Yuxuan Zhang, Chao Xu, Howard H. Yang, Xijun Wang, Tony Q. S. Quek

This paper proposes a client selection (CS) method to tackle the communication bottleneck of federated learning (FL) while concurrently coping with FL's data heterogeneity issue.

Federated Learning

The Novel Adaptive Fractional Order Gradient Decent Algorithms Design via Robust Control

no code implementations8 Mar 2023 Jiaxu Liu, Song Chen, Shengze Cai, Chao Xu

The vanilla fractional order gradient descent may oscillatively converge to a region around the global minimum instead of converging to the exact minimum point, or even diverge, in the case where the objective function is strongly convex.

Differentially Private Deep Q-Learning for Pattern Privacy Preservation in MEC Offloading

no code implementations9 Feb 2023 Shuying Gan, Marie Siew, Chao Xu, Tony Q. S. Quek

Mobile edge computing (MEC) is a promising paradigm to meet the quality of service (QoS) requirements of latency-sensitive IoT applications.

Edge-computing Q-Learning

Reference Twice: A Simple and Unified Baseline for Few-Shot Instance Segmentation

1 code implementation3 Jan 2023 Yue Han, Jiangning Zhang, Zhucun Xue, Chao Xu, Xintian Shen, Yabiao Wang, Chengjie Wang, Yong liu, Xiangtai Li

In this work, we explore a simple yet unified solution for FSIS as well as its incremental variants, and introduce a new framework named Reference Twice (RefT) to fully explore the relationship between support/query features based on a Transformer-like framework.

Benchmarking Few-Shot Object Detection +3

Network Expansion for Practical Training Acceleration

1 code implementation CVPR 2023 Ning Ding, Yehui Tang, Kai Han, Chao Xu, Yunhe Wang

Recently, the sizes of deep neural networks and training datasets both increase drastically to pursue better performance in a practical sense.

1000 FPS HDR Video With a Spike-RGB Hybrid Camera

no code implementations CVPR 2023 Yakun Chang, Chu Zhou, Yuchen Hong, Liwen Hu, Chao Xu, Tiejun Huang, Boxin Shi

Capturing high frame rate and high dynamic range (HFR&HDR) color videos in high-speed scenes with conventional frame-based cameras is very challenging.

Video Reconstruction

GhostNetV2: Enhance Cheap Operation with Long-Range Attention

15 code implementations23 Nov 2022 Yehui Tang, Kai Han, Jianyuan Guo, Chang Xu, Chao Xu, Yunhe Wang

The convolutional operation can only capture local information in a window region, which prevents performance from being further improved.

GotFlow3D: Recurrent Graph Optimal Transport for Learning 3D Flow Motion in Particle Tracking

no code implementations31 Oct 2022 Jiaming Liang, Chao Xu, Shengze Cai

By introducing a novel deep neural network based on recurrent Graph Optimal Transport, called GotFlow3D, we present an end-to-end solution to learn the 3D fluid flow motion from double-frame particle sets.

Motion Estimation

D&D: Learning Human Dynamics from Dynamic Camera

1 code implementation19 Sep 2022 Jiefeng Li, Siyuan Bian, Chao Xu, Gang Liu, Gang Yu, Cewu Lu

In this work, we present D&D (Learning Human Dynamics from Dynamic Camera), which leverages the laws of physics to reconstruct 3D human motion from the in-the-wild videos with a moving camera.

3D Human Pose Estimation Human Dynamics

Linear TreeShap

1 code implementation16 Sep 2022 Peng Yu, Chao Xu, Albert Bifet, Jesse Read

Decision trees are well-known due to their ease of interpretability.

Neural Observer with Lyapunov Stability Guarantee for Uncertain Nonlinear Systems

no code implementations27 Aug 2022 Song Chen, Shengze Cai, Tehuan Chen, Chao Xu, Jian Chu

In this paper, we propose a novel nonlinear observer based on neural networks, called neural observer, for observation tasks of linear time-invariant (LTI) systems and uncertain nonlinear systems.

NPU-BOLT: A Dataset for Bolt Object Detection in Natural Scene Images

no code implementations23 May 2022 Yadian Zhao, Zhenglin Yang, Chao Xu

Therefore, the aim of this study is to develop a dataset named NPU-BOLT for bolt object detection in natural scene images and open it to researchers for public use and further development.

object-detection Object Detection

Source-Free Domain Adaptation via Distribution Estimation

no code implementations CVPR 2022 Ning Ding, Yixing Xu, Yehui Tang, Chao Xu, Yunhe Wang, DaCheng Tao

Domain Adaptation aims to transfer the knowledge learned from a labeled source domain to an unlabeled target domain whose data distributions are different.

Privacy Preserving Source-Free Domain Adaptation

Towards Homogeneous Modality Learning and Multi-Granularity Information Exploration for Visible-Infrared Person Re-Identification

no code implementations11 Apr 2022 Haojie Liu, Daoxun Xia, Wei Jiang, Chao Xu

In order to mitigate the impact of large modality discrepancy existing in heterogeneous images, previous methods attempt to apply generative adversarial network (GAN) to generate the modality-consisitent data.

Generative Adversarial Network Person Re-Identification +1

Region-Aware Face Swapping

no code implementations CVPR 2022 Chao Xu, Jiangning Zhang, Miao Hua, Qian He, Zili Yi, Yong liu

This paper presents a novel Region-Aware Face Swapping (RAFSwap) network to achieve identity-consistent harmonious high-resolution face generation in a local-global manner: \textbf{1)} Local Facial Region-Aware (FRA) branch augments local identity-relevant features by introducing the Transformer to effectively model misaligned cross-scale semantic interaction.

Face Generation Face Swapping +1

PartAfford: Part-level Affordance Discovery from 3D Objects

no code implementations28 Feb 2022 Chao Xu, Yixin Chen, He Wang, Song-Chun Zhu, Yixin Zhu, Siyuan Huang

We propose a novel learning framework for PartAfford, which discovers part-level representations by leveraging only the affordance set supervision and geometric primitive regularization, without dense supervision.


SCSNet: An Efficient Paradigm for Learning Simultaneously Image Colorization and Super-Resolution

no code implementations12 Jan 2022 Jiangning Zhang, Chao Xu, Jian Li, Yue Han, Yabiao Wang, Ying Tai, Yong liu

In the practical application of restoring low-resolution gray-scale images, we generally need to run three separate processes of image colorization, super-resolution, and dows-sampling operation for the target device.

Colorization Image Colorization +1

Learning to dehaze with polarization

no code implementations NeurIPS 2021 Chu Zhou, Minggui Teng, Yufei Han, Chao Xu, Boxin Shi

Haze, a common kind of bad weather caused by atmospheric scattering, decreases the visibility of scenes and degenerates the performance of computer vision algorithms.

Image Dehazing Single Image Dehazing

An Image Patch is a Wave: Phase-Aware Vision MLP

10 code implementations CVPR 2022 Yehui Tang, Kai Han, Jianyuan Guo, Chang Xu, Yanxi Li, Chao Xu, Yunhe Wang

To dynamically aggregate tokens, we propose to represent each token as a wave function with two parts, amplitude and phase.

Image Classification object-detection +2

Positive and Unlabeled Federated Learning

no code implementations29 Sep 2021 Lin Xinyang, Hanting Chen, Yixing Xu, Chao Xu, Xiaolin Gui, Yiping Deng, Yunhe Wang

We study the problem of learning from positive and unlabeled (PU) data in the federated setting, where each client only labels a little part of their dataset due to the limitation of resources and time.

Federated Learning

TotalRecall: A Bidirectional Candidates Generation Framework for Large Scale Recommender \& Advertising Systems

no code implementations29 Sep 2021 Qifang Zhao, Yu Jiang, Yuqing Liu, Meng Du, Qinghui Sun, Chao Xu, Huan Xu, Zhongyao Wang

Recommender (RS) and Advertising/Marketing Systems (AS) play the key roles in E-commerce companies like Amazaon and Alibaba.


Hire-MLP: Vision MLP via Hierarchical Rearrangement

9 code implementations CVPR 2022 Jianyuan Guo, Yehui Tang, Kai Han, Xinghao Chen, Han Wu, Chao Xu, Chang Xu, Yunhe Wang

Previous vision MLPs such as MLP-Mixer and ResMLP accept linearly flattened image patches as input, making them inflexible for different input sizes and hard to capture spatial information.

Image Classification object-detection +2

Augmented Shortcuts for Vision Transformers

4 code implementations NeurIPS 2021 Yehui Tang, Kai Han, Chang Xu, An Xiao, Yiping Deng, Chao Xu, Yunhe Wang

Transformer models have achieved great progress on computer vision tasks recently.

Federated Learning with Positive and Unlabeled Data

1 code implementation21 Jun 2021 Xinyang Lin, Hanting Chen, Yixing Xu, Chao Xu, Xiaolin Gui, Yiping Deng, Yunhe Wang

We study the problem of learning from positive and unlabeled (PU) data in the federated setting, where each client only labels a little part of their dataset due to the limitation of resources and time.

Federated Learning

Learning Student Networks in the Wild

1 code implementation CVPR 2021 Hanting Chen, Tianyu Guo, Chang Xu, Wenshuo Li, Chunjing Xu, Chao Xu, Yunhe Wang

Experiments on various datasets demonstrate that the student networks learned by the proposed method can achieve comparable performance with those using the original dataset.

Knowledge Distillation Model Compression

Patch Slimming for Efficient Vision Transformers

no code implementations CVPR 2022 Yehui Tang, Kai Han, Yunhe Wang, Chang Xu, Jianyuan Guo, Chao Xu, DaCheng Tao

We first identify the effective patches in the last layer and then use them to guide the patch selection process of previous layers.

Analogous to Evolutionary Algorithm: Designing a Unified Sequence Model

1 code implementation NeurIPS 2021 Jiangning Zhang, Chao Xu, Jian Li, Wenzhou Chen, Yabiao Wang, Ying Tai, Shuo Chen, Chengjie Wang, Feiyue Huang, Yong liu

Inspired by biological evolution, we explain the rationality of Vision Transformer by analogy with the proven practical Evolutionary Algorithm (EA) and derive that both of them have consistent mathematical representation.

Image Retrieval Retrieval

Universal Adder Neural Networks

no code implementations29 May 2021 Hanting Chen, Yunhe Wang, Chang Xu, Chao Xu, Chunjing Xu, Tong Zhang

The widely-used convolutions in deep neural networks are exactly cross-correlation to measure the similarity between input feature and convolution filters, which involves massive multiplications between float values.

Optimizing the Long-Term Average Reward for Continuing MDPs: A Technical Report

no code implementations13 Apr 2021 Chao Xu, Yiping Xie, Xijun Wang, Howard H. Yang, Dusit Niyato, Tony Q. S. Quek

cost), by integrating R-learning, a tabular reinforcement learning (RL) algorithm tailored for maximizing the long-term average reward, and traditional DRL algorithms, initially developed to optimize the discounted long-term cumulative reward rather than the average one.

reinforcement-learning Reinforcement Learning (RL)

Visibility-aware Trajectory Optimization with Application to Aerial Tracking

1 code implementation11 Mar 2021 Qianhao Wang, Yuman Gao, Jialin Ji, Chao Xu, Fei Gao

The visibility of targets determines performance and even success rate of various applications, such as active slam, exploration, and target tracking.

Trajectory Planning Robotics

Manifold Regularized Dynamic Network Pruning

6 code implementations CVPR 2021 Yehui Tang, Yunhe Wang, Yixing Xu, Yiping Deng, Chao Xu, DaCheng Tao, Chang Xu

Then, the manifold relationship between instances and the pruned sub-networks will be aligned in the training procedure.

Network Pruning

Integrating Fast Regional Optimization into Sampling-based Kinodynamic Planning for Multirotor Flight

1 code implementation9 Mar 2021 Hongkai Ye, Tianyu Liu, Chao Xu, Fei Gao

For real-time multirotor kinodynamic motion planning, the efficiency of sampling-based methods is usually hindered by difficult-to-sample homotopy classes like narrow passages.

Motion Planning Robotics

EvIntSR-Net: Event Guided Multiple Latent Frames Reconstruction and Super-Resolution

no code implementations ICCV 2021 Jin Han, Yixin Yang, Chu Zhou, Chao Xu, Boxin Shi

To reconstruct high-resolution intensity images from event data, we propose EvIntSR-Net that converts event data to multiple latent intensity frames to achieve super-resolution on intensity images in this paper.


Pre-Trained Image Processing Transformer

6 code implementations CVPR 2021 Hanting Chen, Yunhe Wang, Tianyu Guo, Chang Xu, Yiping Deng, Zhenhua Liu, Siwei Ma, Chunjing Xu, Chao Xu, Wen Gao

To maximally excavate the capability of transformer, we present to utilize the well-known ImageNet benchmark for generating a large amount of corrupted image pairs.

 Ranked #1 on Single Image Deraining on Rain100L (using extra training data)

Color Image Denoising Contrastive Learning +2

UnModNet: Learning to Unwrap a Modulo Image for High Dynamic Range Imaging

no code implementations NeurIPS 2020 Chu Zhou, Hang Zhao, Jin Han, Chang Xu, Chao Xu, Tiejun Huang, Boxin Shi

A conventional camera often suffers from over- or under-exposure when recording a real-world scene with a very high dynamic range (HDR).

HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation

3 code implementations CVPR 2021 Jiefeng Li, Chao Xu, Zhicun Chen, Siyuan Bian, Lixin Yang, Cewu Lu

We show that HybrIK preserves both the accuracy of 3D pose and the realistic body structure of the parametric human model, leading to a pixel-aligned 3D body mesh and a more accurate 3D pose than the pure 3D keypoint estimation methods.

3D human pose and shape estimation Keypoint Estimation

Learning-based 3D Occupancy Prediction for Autonomous Navigation in Occluded Environments

1 code implementation8 Nov 2020 Lizi Wang, Hongkai Ye, Qianhao Wang, Yuman Gao, Chao Xu, Fei Gao

In autonomous navigation of mobile robots, sensors suffer from massive occlusion in cluttered environments, leaving significant amount of space unknown during planning.

Autonomous Navigation

APB2FaceV2: Real-Time Audio-Guided Multi-Face Reenactment

1 code implementation25 Oct 2020 Jiangning Zhang, Xianfang Zeng, Chao Xu, Jun Chen, Yong liu, Yunliang Jiang

Audio-guided face reenactment aims to generate a photorealistic face that has matched facial expression with the input audio.

Face Reenactment

SCOP: Scientific Control for Reliable Neural Network Pruning

4 code implementations NeurIPS 2020 Yehui Tang, Yunhe Wang, Yixing Xu, DaCheng Tao, Chunjing Xu, Chao Xu, Chang Xu

To increase the reliability of the results, we prefer to have a more rigorous research design by including a scientific control group as an essential part to minimize the effect of all factors except the association between the filter and expected network output.

Network Pruning

Deep Learning Based Antenna Selection for Channel Extrapolation in FDD Massive MIMO

no code implementations3 Sep 2020 Yindi Yang, Shun Zhang, Feifei Gao, Chao Xu, Jianpeng Ma, Octavia A. Dobre

In massive multiple-input multiple-output (MIMO) systems, the large number of antennas would bring a great challenge for the acquisition of the accurate channel state information, especially in the frequency division duplex mode.

EGO-Planner: An ESDF-free Gradient-based Local Planner for Quadrotors

2 code implementations20 Aug 2020 Xin Zhou, Zhepei Wang, Chao Xu, Fei Gao

Gradient-based planners are widely used for quadrotor local planning, in which a Euclidean Signed Distance Field (ESDF) is crucial for evaluating gradient magnitude and direction.


CMPCC: Corridor-based Model Predictive Contouring Control for Aggressive Drone Flight

1 code implementation7 Jul 2020 Jialin Ji, Xin Zhou, Chao Xu, Fei Gao

In this paper, we propose an efficient, receding horizon, local adaptive low-level planner as the middle layer between our original planner and controller.


HourNAS: Extremely Fast Neural Architecture Search Through an Hourglass Lens

5 code implementations CVPR 2021 Zhaohui Yang, Yunhe Wang, Xinghao Chen, Jianyuan Guo, Wei zhang, Chao Xu, Chunjing Xu, DaCheng Tao, Chang Xu

To achieve an extremely fast NAS while preserving the high accuracy, we propose to identify the vital blocks and make them the priority in the architecture search.

Neural Architecture Search

Hierarchical and Efficient Learning for Person Re-Identification

no code implementations18 May 2020 Jiangning Zhang, Liang Liu, Chao Xu, Yong liu

Recent works in the person re-identification task mainly focus on the model accuracy while ignore factors related to the efficiency, e. g. model size and latency, which are critical for practical application.

Person Re-Identification

A Semi-Supervised Assessor of Neural Architectures

no code implementations CVPR 2020 Yehui Tang, Yunhe Wang, Yixing Xu, Hanting Chen, Chunjing Xu, Boxin Shi, Chao Xu, Qi Tian, Chang Xu

A graph convolutional neural network is introduced to predict the performance of architectures based on the learned representations and their relation modeled by the graph.

Neural Architecture Search

Distilling portable Generative Adversarial Networks for Image Translation

no code implementations7 Mar 2020 Hanting Chen, Yunhe Wang, Han Shu, Changyuan Wen, Chunjing Xu, Boxin Shi, Chao Xu, Chang Xu

To promote the capability of student generator, we include a student discriminator to measure the distances between real images, and images generated by student and teacher generators.

Image-to-Image Translation Knowledge Distillation +1

Beyond Dropout: Feature Map Distortion to Regularize Deep Neural Networks

2 code implementations23 Feb 2020 Yehui Tang, Yunhe Wang, Yixing Xu, Boxin Shi, Chao Xu, Chunjing Xu, Chang Xu

On one hand, massive trainable parameters significantly enhance the performance of these deep networks.

Discernible Image Compression

no code implementations17 Feb 2020 Zhaohui Yang, Yunhe Wang, Chang Xu, Peng Du, Chao Xu, Chunjing Xu, Qi Tian

Experiments on benchmarks demonstrate that images compressed by using the proposed method can also be well recognized by subsequent visual recognition and detection models.

Image Compression object-detection +1

On Positive-Unlabeled Classification in GAN

1 code implementation CVPR 2020 Tianyu Guo, Chang Xu, Jiajun Huang, Yunhe Wang, Boxin Shi, Chao Xu, DaCheng Tao

In contrast, it is more reasonable to treat the generated data as unlabeled, which could be positive or negative according to their quality.

Classification General Classification

AdderNet: Do We Really Need Multiplications in Deep Learning?

7 code implementations CVPR 2020 Hanting Chen, Yunhe Wang, Chunjing Xu, Boxin Shi, Chao Xu, Qi Tian, Chang Xu

The widely-used convolutions in deep neural networks are exactly cross-correlation to measure the similarity between input feature and convolution filters, which involves massive multiplications between float values.

Training Object Detectors from Few Weakly-Labeled and Many Unlabeled Images

no code implementations arXiv 2019 Zhaohui Yang, Miaojing Shi, Chao Xu, Vittorio Ferrari, Yannis Avrithis

Weakly-supervised object detection attempts to limit the amount of supervision by dispensing the need for bounding boxes, but still assumes image-level labels on the entire training set.

Ranked #23 on Weakly Supervised Object Detection on PASCAL VOC 2012 test (using extra training data)

object-detection Weakly Supervised Object Detection

Learning from Bad Data via Generation

no code implementations NeurIPS 2019 Tianyu Guo, Chang Xu, Boxin Shi, Chao Xu, DaCheng Tao

A worst-case formulation can be developed over this distribution set, and then be interpreted as a generation task in an adversarial manner.


CARS: Continuous Evolution for Efficient Neural Architecture Search

1 code implementation CVPR 2020 Zhaohui Yang, Yunhe Wang, Xinghao Chen, Boxin Shi, Chao Xu, Chunjing Xu, Qi Tian, Chang Xu

Architectures in the population that share parameters within one SuperNet in the latest generation will be tuned over the training dataset with a few epochs.

Neural Architecture Search

Bringing Giant Neural Networks Down to Earth with Unlabeled Data

no code implementations13 Jul 2019 Yehui Tang, Shan You, Chang Xu, Boxin Shi, Chao Xu

Specifically, we exploit the unlabeled data to mimic the classification characteristics of giant networks, so that the original capacity can be preserved nicely.

On the computational complexity of the probabilistic label tree algorithms

no code implementations1 Jun 2019 Robert Busa-Fekete, Krzysztof Dembczynski, Alexander Golovnev, Kalina Jasinska, Mikhail Kuznetsov, Maxim Sviridenko, Chao Xu

First, we show that finding a tree with optimal training cost is NP-complete, nevertheless there are some tractable special cases with either perfect approximation or exact solution that can be obtained in linear time in terms of the number of labels $m$.

Multi-class Classification

Strain engineering of epitaxial oxide heterostructures beyond substrate limitations

no code implementations3 May 2019 Xiong Deng, Chao Chen, Deyang Chen, Xiangbin Cai, Xiaozhe Yin, Chao Xu, Fei Sun, Caiwen Li, Yan Li, Han Xu, Mao Ye, Guo Tian, Zhen Fan, Zhipeng Hou, Minghui Qin, Yu Chen, Zhenlin Luo, Xubing Lu, Guofu Zhou, Lang Chen, Ning Wang, Ye Zhu, Xingsen Gao, Jun-Ming Liu

The limitation of commercially available single-crystal substrates and the lack of continuous strain tunability preclude the ability to take full advantage of strain engineering for further exploring novel properties and exhaustively studying fundamental physics in complex oxides.

Materials Science

Multi-View Matrix Completion for Multi-Label Image Classification

no code implementations8 Apr 2019 Yong Luo, Tongliang Liu, DaCheng Tao, Chao Xu

Therefore, we propose to weightedly combine the MC outputs of different views, and present the multi-view matrix completion (MVMC) framework for transductive multi-label image classification.

Classification General Classification +5

Decomposition-Based Transfer Distance Metric Learning for Image Classification

no code implementations8 Apr 2019 Yong Luo, Tongliang Liu, DaCheng Tao, Chao Xu

In particular, DTDML learns a sparse combination of the base metrics to construct the target metric by forcing the target metric to be close to an integration of the source metrics.

Classification General Classification +3

Multi-view Vector-valued Manifold Regularization for Multi-label Image Classification

no code implementations8 Apr 2019 Yong Luo, DaCheng Tao, Chang Xu, Chao Xu, Hong Liu, Yonggang Wen

In computer vision, image datasets used for classification are naturally associated with multiple labels and comprised of multiple views, because each image may contain several objects (e. g. pedestrian, bicycle and tree) and is properly characterized by multiple visual features (e. g. color, texture and shape).

General Classification Multi-Label Image Classification

Multi-View Intact Space Learning

no code implementations4 Apr 2019 Chang Xu, DaCheng Tao, Chao Xu

In this paper, we propose the Multi-view Intact Space Learning (MISL) algorithm, which integrates the encoded complementary information in multiple views to discover a latent intact representation of the data.


Cost-Sensitive Feature Selection by Optimizing F-Measures

no code implementations4 Apr 2019 Meng Liu, Chang Xu, Yong Luo, Chao Xu, Yonggang Wen, DaCheng Tao

Feature selection is beneficial for improving the performance of general machine learning tasks by extracting an informative subset from the high-dimensional features.

feature selection

Data-Free Learning of Student Networks

3 code implementations ICCV 2019 Hanting Chen, Yunhe Wang, Chang Xu, Zhaohui Yang, Chuanjian Liu, Boxin Shi, Chunjing Xu, Chao Xu, Qi Tian

Learning portable neural networks is very essential for computer vision for the purpose that pre-trained heavy deep models can be well applied on edge devices such as mobile phones and micro sensors.

Neural Network Compression

Learning Student Networks via Feature Embedding

no code implementations17 Dec 2018 Hanting Chen, Yunhe Wang, Chang Xu, Chao Xu, DaCheng Tao

Experiments on benchmark datasets and well-trained networks suggest that the proposed algorithm is superior to state-of-the-art teacher-student learning methods in terms of computational and storage complexity.

Knowledge Distillation

Robust Student Network Learning

no code implementations30 Jul 2018 Tianyu Guo, Chang Xu, Shiyi He, Boxin Shi, Chao Xu, DaCheng Tao

In this way, a portable student network with significantly fewer parameters can achieve a considerable accuracy which is comparable to that of teacher network.

Revisiting Perspective Information for Efficient Crowd Counting

no code implementations CVPR 2019 Miaojing Shi, Zhaohui Yang, Chao Xu, Qijun Chen

Modern crowd counting methods employ deep neural networks to estimate crowd counts via crowd density regressions.

Crowd Counting regression

AutoEncoder Inspired Unsupervised Feature Selection

1 code implementation23 Oct 2017 Kai Han, Yunhe Wang, Chao Zhang, Chao Li, Chao Xu

High-dimensional data in many areas such as computer vision and machine learning tasks brings in computational and analytical difficulty.

BIG-bench Machine Learning feature selection

Beyond Filters: Compact Feature Map for Portable Deep Model

1 code implementation ICML 2017 Yunhe Wang, Chang Xu, Chao Xu, DaCheng Tao

The filter is then re-configured to establish the mapping from original input to the new compact feature map, and the resulting network can preserve intrinsic information of the original network with significantly fewer parameters, which not only decreases the online memory for launching CNN but also accelerates the computation speed.

Towards Evolutional Compression

no code implementations25 Jul 2017 Yunhe Wang, Chang Xu, Jiayan Qiu, Chao Xu, DaCheng Tao

In contrast to directly recognizing subtle weights or filters as redundant in a given CNN, this paper presents an evolutionary method to automatically eliminate redundant convolution filters.

Parametric T-Spline Face Morphable Model for Detailed Fitting in Shape Subspace

no code implementations CVPR 2017 Weilong Peng, Zhiyong Feng, Chao Xu, Yong Su

As any pre-learnt subspace is not complete to handle the variety and details of faces and expressions, it covers a limited span of morphing.


Privileged Multi-label Learning

no code implementations25 Jan 2017 Shan You, Chang Xu, Yunhe Wang, Chao Xu, DaCheng Tao

This paper presents privileged multi-label learning (PrML) to explore and exploit the relationship between labels in multi-label learning problems.

Multi-Label Learning

A Logic of Knowing Why

no code implementations21 Sep 2016 Chao Xu, Yanjing Wang, Thomas Studer

When we say "I know why he was late", we know not only the fact that he was late, but also an explanation of this fact.

Streaming View Learning

no code implementations28 Apr 2016 Chang Xu, DaCheng Tao, Chao Xu

An underlying assumption in conventional multi-view learning algorithms is that all views can be simultaneously accessed.


Streaming Label Learning for Modeling Labels on the Fly

no code implementations19 Apr 2016 Shan You, Chang Xu, Yunhe Wang, Chao Xu, DaCheng Tao

The core of SLL is to explore and exploit the relationships between new labels and past labels and then inherit the relationship into hypotheses of labels to boost the performance of new classifiers.

Multi-Label Learning

Parts for the Whole: The DCT Norm for Extreme Visual Recovery

no code implementations19 Apr 2016 Yunhe Wang, Chang Xu, Shan You, DaCheng Tao, Chao Xu

Here we study the extreme visual recovery problem, in which over 90\% of pixel values in a given image are missing.

B-spline Shape from Motion & Shading: An Automatic Free-form Surface Modeling for Face Reconstruction

no code implementations21 Jan 2016 Weilong Peng, Zhiyong Feng, Chao Xu

In this paper, B-spline Shape from Motion and Shading (BsSfMS) is proposed to reconstruct continuous B-spline surface for multi-view face images, according to an assumption that shading and motion information in the images contain 1st- and 0th-order derivative of B-spline face respectively.

Face Reconstruction

Tensor Canonical Correlation Analysis for Multi-view Dimension Reduction

3 code implementations9 Feb 2015 Yong Luo, DaCheng Tao, Yonggang Wen, Kotagiri Ramamohanarao, Chao Xu

As a consequence, the high order correlation information contained in the different views is explored and thus a more reliable common subspace shared by all features can be obtained.

Dimensionality Reduction MULTI-VIEW LEARNING

Bi-objective Optimization for Robust RGB-D Visual Odometry

no code implementations27 Nov 2014 Tao Han, Chao Xu, Ryan Loxton, Lei Xie

This paper considers a new bi-objective optimization formulation for robust RGB-D visual odometry.

Visual Odometry

Local Rademacher Complexity for Multi-label Learning

no code implementations26 Oct 2014 Chang Xu, Tongliang Liu, DaCheng Tao, Chao Xu

We analyze the local Rademacher complexity of empirical risk minimization (ERM)-based multi-label learning algorithms, and in doing so propose a new algorithm for multi-label learning.

Multi-Label Learning

A Survey on Multi-view Learning

no code implementations20 Apr 2013 Chang Xu, DaCheng Tao, Chao Xu

Notably, co-training style algorithms train alternately to maximize the mutual agreement on two distinct views of the data; multiple kernel learning algorithms exploit kernels that naturally correspond to different views and combine kernels either linearly or non-linearly to improve learning performance; and subspace learning algorithms aim to obtain a latent subspace shared by multiple views by assuming that the input views are generated from this latent subspace.


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