Search Results for author: Xiaopeng Zhang

Found 57 papers, 15 papers with code

Don’t Miss the Potential Customers! Retrieving Similar Ads to Improve User Targeting

no code implementations Findings (EMNLP) 2021 Yi Feng, Ting Wang, Chuanyi Li, Vincent Ng, Jidong Ge, Bin Luo, Yucheng Hu, Xiaopeng Zhang

User targeting is an essential task in the modern advertising industry: given a package of ads for a particular category of products (e. g., green tea), identify the online users to whom the ad package should be targeted.

Gradient Concealment: Free Lunch for Defending Adversarial Attacks

no code implementations21 May 2022 Sen Pei, Jiaxi Sun, Xiaopeng Zhang, Gaofeng Meng

Recent studies show that the deep neural networks (DNNs) have achieved great success in various tasks.

Robust classification

Deep Point Cloud Simplification for High-quality Surface Reconstruction

no code implementations17 Mar 2022 Yuanqi Li, Jianwei Guo, Xinran Yang, Shun Liu, Jie Guo, Xiaopeng Zhang, Yanwen Guo

In this paper, we propose a novel point cloud simplification network (PCS-Net) dedicated to high-quality surface mesh reconstruction while maintaining geometric fidelity.

Scene Understanding Surface Reconstruction

MTLDesc: Looking Wider to Describe Better

1 code implementation14 Mar 2022 Changwei Wang, Rongtao Xu, Yuyang Zhang, Shibiao Xu, Weiliang Meng, Bin Fan, Xiaopeng Zhang

Limited by the locality of convolutional neural networks, most existing local features description methods only learn local descriptors with local information and lack awareness of global and surrounding spatial context.

Indoor Localization

TAPE: Task-Agnostic Prior Embedding for Image Restoration

no code implementations11 Mar 2022 Lin Liu, Lingxi Xie, Xiaopeng Zhang, Shanxin Yuan, Xiangyu Chen, Wengang Zhou, Houqiang Li, Qi Tian

Learning an generalized prior for natural image restoration is an important yet challenging task.

Image Restoration

The KFIoU Loss for Rotated Object Detection

2 code implementations29 Jan 2022 Xue Yang, Yue Zhou, Gefan Zhang, Jirui Yang, Wentao Wang, Junchi Yan, Xiaopeng Zhang, Qi Tian

Differing from the well-developed horizontal object detection area whereby the computing-friendly IoU based loss is readily adopted and well fits with the detection metrics.

Object Detection In Aerial Images

NeuSample: Neural Sample Field for Efficient View Synthesis

no code implementations30 Nov 2021 Jiemin Fang, Lingxi Xie, Xinggang Wang, Xiaopeng Zhang, Wenyu Liu, Qi Tian

Neural radiance fields (NeRF) have shown great potentials in representing 3D scenes and synthesizing novel views, but the computational overhead of NeRF at the inference stage is still heavy.

Semantic-Aware Generation for Self-Supervised Visual Representation Learning

1 code implementation25 Nov 2021 Yunjie Tian, Lingxi Xie, Xiaopeng Zhang, Jiemin Fang, Haohang Xu, Wei Huang, Jianbin Jiao, Qi Tian, Qixiang Ye

In this paper, we propose a self-supervised visual representation learning approach which involves both generative and discriminative proxies, where we focus on the former part by requiring the target network to recover the original image based on the mid-level features.

Ranked #56 on Semantic Segmentation on Cityscapes test (using extra training data)

Representation Learning Semantic Segmentation

Self-supervised High-fidelity and Re-renderable 3D Facial Reconstruction from a Single Image

no code implementations16 Nov 2021 Mingxin Yang, Jianwei Guo, Zhanglin Cheng, Xiaopeng Zhang, Dong-Ming Yan

Although each method has its own advantage, none of them is capable of recovering a high-fidelity and re-renderable facial texture, where the term 're-renderable' demands the facial texture to be spatially complete and disentangled with environmental illumination.

3D Face Reconstruction Disentanglement +1

Understanding Self-supervised Learning via Information Bottleneck Principle

no code implementations29 Sep 2021 Jin Li, Yaoming Wang, Dongsheng Jiang, Xiaopeng Zhang, Wenrui Dai, Hongkai Xiong

To address this issue, we introduce the information bottleneck principle and propose the Self-supervised Variational Information Bottleneck (SVIB) learning framework.

Contrastive Learning Self-Supervised Learning

Bag of Instances Aggregation Boosts Self-supervised Distillation

1 code implementation ICLR 2022 Haohang Xu, Jiemin Fang, Xiaopeng Zhang, Lingxi Xie, Xinggang Wang, Wenrui Dai, Hongkai Xiong, Qi Tian

Here bag of instances indicates a set of similar samples constructed by the teacher and are grouped within a bag, and the goal of distillation is to aggregate compact representations over the student with respect to instances in a bag.

Contrastive Learning Self-Supervised Learning

Multi-dataset Pretraining: A Unified Model for Semantic Segmentation

no code implementations8 Jun 2021 Bowen Shi, Xiaopeng Zhang, Haohang Xu, Wenrui Dai, Junni Zou, Hongkai Xiong, Qi Tian

This is achieved by first pretraining the network via the proposed pixel-to-prototype contrastive loss over multiple datasets regardless of their taxonomy labels, and followed by fine-tuning the pretrained model over specific dataset as usual.

Semantic Segmentation

Mixture of Virtual-Kernel Experts for Multi-Objective User Profile Modeling

no code implementations4 Jun 2021 Zhenhui Xu, Meng Zhao, Liqun Liu, Xiaopeng Zhang, Bifeng Zhang

Besides, limited by the lack of information fusion between the two towers, the model learning is insufficient to represent users' preferences on various topics well.

Recommendation Systems

Deep Deformation Detail Synthesis for Thin Shell Models

no code implementations23 Feb 2021 Lan Chen, Lin Gao, Jie Yang, Shibiao Xu, Juntao Ye, Xiaopeng Zhang, Yu-Kun Lai

Moreover, as such methods only add details, they require coarse meshes to be close to fine meshes, which can be either impossible, or require unrealistic constraints when generating fine meshes.


Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss

2 code implementations28 Jan 2021 Xue Yang, Junchi Yan, Qi Ming, Wentao Wang, Xiaopeng Zhang, Qi Tian

Boundary discontinuity and its inconsistency to the final detection metric have been the bottleneck for rotating detection regression loss design.

Object Detection In Aerial Images Small Object Detection

Seed the Views: Hierarchical Semantic Alignment for Contrastive Representation Learning

no code implementations4 Dec 2020 Haohang Xu, Xiaopeng Zhang, Hao Li, Lingxi Xie, Hongkai Xiong, Qi Tian

In this paper, we propose a hierarchical semantic alignment strategy via expanding the views generated by a single image to \textbf{Cross-samples and Multi-level} representation, and models the invariance to semantically similar images in a hierarchical way.

Contrastive Learning Representation Learning +2

Scene text removal via cascaded text stroke detection and erasing

1 code implementation19 Nov 2020 Xuewei Bian, Chaoqun Wang, Weize Quan, Juntao Ye, Xiaopeng Zhang, Dong-Ming Yan

Specifically, we decouple the text removal problem into text stroke detection and stroke removal.

Heterogeneous Contrastive Learning: Encoding Spatial Information for Compact Visual Representations

no code implementations19 Nov 2020 Xinyue Huo, Lingxi Xie, Longhui Wei, Xiaopeng Zhang, Hao Li, Zijie Yang, Wengang Zhou, Houqiang Li, Qi Tian

Contrastive learning has achieved great success in self-supervised visual representation learning, but existing approaches mostly ignored spatial information which is often crucial for visual representation.

Contrastive Learning Data Augmentation +1

Center-wise Local Image Mixture For Contrastive Representation Learning

no code implementations5 Nov 2020 Hao Li, Xiaopeng Zhang, Hongkai Xiong

Contrastive learning based on instance discrimination trains model to discriminate different transformations of the anchor sample from other samples, which does not consider the semantic similarity among samples.

Contrastive Learning Data Augmentation +3

Accurate Lung Nodules Segmentation with Detailed Representation Transfer and Soft Mask Supervision

no code implementations29 Jul 2020 Changwei Wang, Rongtao Xu, Shibiao Xu, Weiliang Meng, Jun Xiao, Xiaopeng Zhang

Then, a novel Network with detailed representation transfer and Soft Mask supervision (DSNet) is proposed to process the input low-resolution images of lung nodules into high-quality segmentation results.

Computed Tomography (CT) Lesion Segmentation +2

Searching towards Class-Aware Generators for Conditional Generative Adversarial Networks

1 code implementation25 Jun 2020 Peng Zhou, Lingxi Xie, Xiaopeng Zhang, Bingbing Ni, Qi Tian

To learn the sampling policy, a Markov decision process is embedded into the search algorithm and a moving average is applied for better stability.

Image Generation

Distilling Object Detectors with Task Adaptive Regularization

no code implementations23 Jun 2020 Ruoyu Sun, Fuhui Tang, Xiaopeng Zhang, Hongkai Xiong, Qi Tian

Knowledge distillation, which aims at training a smaller student network by transferring knowledge from a larger teacher model, is one of the promising solutions for model miniaturization.

Knowledge Distillation Region Proposal

A survey on deep hashing for image retrieval

no code implementations10 Jun 2020 Xiaopeng Zhang

To this end, I propose a concept: shadow of the CNN output.

Image Retrieval

Effective and Robust Detection of Adversarial Examples via Benford-Fourier Coefficients

no code implementations12 May 2020 Chengcheng Ma, Baoyuan Wu, Shibiao Xu, Yanbo Fan, Yong Zhang, Xiaopeng Zhang, Zhifeng Li

In this work, we study the detection of adversarial examples, based on the assumption that the output and internal responses of one DNN model for both adversarial and benign examples follow the generalized Gaussian distribution (GGD), but with different parameters (i. e., shape factor, mean, and variance).

Image Classification

Circumventing Outliers of AutoAugment with Knowledge Distillation

no code implementations ECCV 2020 Longhui Wei, An Xiao, Lingxi Xie, Xin Chen, Xiaopeng Zhang, Qi Tian

AutoAugment has been a powerful algorithm that improves the accuracy of many vision tasks, yet it is sensitive to the operator space as well as hyper-parameters, and an improper setting may degenerate network optimization.

Data Augmentation General Classification +1

MGCN: Descriptor Learning using Multiscale GCNs

no code implementations28 Jan 2020 Yiqun Wang, Jing Ren, Dong-Ming Yan, Jianwei Guo, Xiaopeng Zhang, Peter Wonka

Second, we propose a new multiscale graph convolutional network (MGCN) to transform a non-learned feature to a more discriminative descriptor.

Latency-Aware Differentiable Neural Architecture Search

1 code implementation17 Jan 2020 Yuhui Xu, Lingxi Xie, Xiaopeng Zhang, Xin Chen, Bowen Shi, Qi Tian, Hongkai Xiong

However, these methods suffer the difficulty in optimizing network, so that the searched network is often unfriendly to hardware.

Neural Architecture Search

Wasserstein-Bounded Generative Adversarial Networks

no code implementations ICLR 2020 Peng Zhou, Bingbing Ni, Lingxi Xie, Xiaopeng Zhang, Hang Wang, Cong Geng, Qi Tian

In the field of Generative Adversarial Networks (GANs), how to design a stable training strategy remains an open problem.

Capacity Preserving Mapping for High-dimensional Data Visualization

1 code implementation29 Sep 2019 Rongrong Wang, Xiaopeng Zhang

We provide a rigorous mathematical treatment to the crowding issue in data visualization when high dimensional data sets are projected down to low dimensions for visualization.

Data Visualization Dimensionality Reduction

Central Similarity Quantization for Efficient Image and Video Retrieval

1 code implementation CVPR 2020 Li Yuan, Tao Wang, Xiaopeng Zhang, Francis EH Tay, Zequn Jie, Wei Liu, Jiashi Feng

In this work, we propose a new \emph{global} similarity metric, termed as \emph{central similarity}, with which the hash codes of similar data pairs are encouraged to approach a common center and those for dissimilar pairs to converge to different centers, to improve hash learning efficiency and retrieval accuracy.

Quantization Video Retrieval

PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture Search

6 code implementations ICLR 2020 Yuhui Xu, Lingxi Xie, Xiaopeng Zhang, Xin Chen, Guo-Jun Qi, Qi Tian, Hongkai Xiong

Differentiable architecture search (DARTS) provided a fast solution in finding effective network architectures, but suffered from large memory and computing overheads in jointly training a super-network and searching for an optimal architecture.

Neural Architecture Search

Distilling Object Detectors with Fine-grained Feature Imitation

3 code implementations CVPR 2019 Tao Wang, Li Yuan, Xiaopeng Zhang, Jiashi Feng

To address the challenge of distilling knowledge in detection model, we propose a fine-grained feature imitation method exploiting the cross-location discrepancy of feature response.

Knowledge Distillation Object Detection

Few-shot Adaptive Faster R-CNN

no code implementations CVPR 2019 Tao Wang, Xiaopeng Zhang, Li Yuan, Jiashi Feng

To address these challenges, we first introduce a pairing mechanism over source and target features to alleviate the issue of insufficient target domain samples.

Object Detection Unsupervised Domain Adaptation

Low Power Inference for On-Device Visual Recognition with a Quantization-Friendly Solution

no code implementations12 Mar 2019 Chen Feng, Tao Sheng, Zhiyu Liang, Shaojie Zhuo, Xiaopeng Zhang, Liang Shen, Matthew Ardi, Alexander C. Berg, Yiran Chen, Bo Chen, Kent Gauen, Yung-Hsiang Lu

The IEEE Low-Power Image Recognition Challenge (LPIRC) is an annual competition started in 2015 that encourages joint hardware and software solutions for computer vision systems with low latency and power.


Detecting Colorized Images via Convolutional Neural Networks: Toward High Accuracy and Good Generalization

no code implementations17 Feb 2019 Weize Quan, Dong-Ming Yan, Kai Wang, Xiaopeng Zhang, Denis Pellerin

First, we design and implement a base network, which can attain better performance in terms of classification accuracy and generalization (in most cases) compared with state-of-the-art methods.

Colorization General Classification

Learning 3D Keypoint Descriptors for Non-Rigid Shape Matching

no code implementations ECCV 2018 Hanyu Wang, Jianwei Guo, Dong-Ming Yan, Weize Quan, Xiaopeng Zhang

In this paper, we present a novel deep learning framework that derives discriminative local descriptors for 3D surface shapes.

Metric Learning

Zigzag Learning for Weakly Supervised Object Detection

no code implementations CVPR 2018 Xiaopeng Zhang, Jiashi Feng, Hongkai Xiong, Qi Tian

Unlike them, we propose a zigzag learning strategy to simultaneously discover reliable object instances and prevent the model from overfitting initial seeds.

Weakly Supervised Object Detection

A Quantization-Friendly Separable Convolution for MobileNets

no code implementations22 Mar 2018 Tao Sheng, Chen Feng, Shaojie Zhuo, Xiaopeng Zhang, Liang Shen, Mickey Aleksic

As deep learning (DL) is being rapidly pushed to edge computing, researchers invented various ways to make inference computation more efficient on mobile/IoT devices, such as network pruning, parameter compression, and etc.

Edge-computing Image Classification +2

Hardware-Efficient Guided Image Filtering For Multi-Label Problem

no code implementations CVPR 2017 Longquan Dai, Mengke Yuan, Zechao Li, Xiaopeng Zhang, Jinhui Tang

In this paper we propose a hardware-efficient Guided Filter (HGF), which solves the efficiency problem of multichannel guided image filtering and yields competent results when applying it to multi-label problems with synthesized polynomial multichannel guidance.

Speeding Up the Bilateral Filter: A Joint Acceleration Way

no code implementations28 Feb 2018 Longquan Dai, Mengke Yuan, Xiaopeng Zhang

To achieve the constant-time BF whose complexity is irrelevant to the kernel size, many techniques have been proposed, such as 2D box filtering, dimension promotion, and shiftability property.

Picking Deep Filter Responses for Fine-Grained Image Recognition

no code implementations CVPR 2016 Xiaopeng Zhang, Hongkai Xiong, Wengang Zhou, Weiyao Lin, Qi Tian

Recognizing fine-grained sub-categories such as birds and dogs is extremely challenging due to the highly localized and subtle differences in some specific parts.

Fine-Grained Image Recognition

Segment Graph Based Image Filtering: Fast Structure-Preserving Smoothing

no code implementations ICCV 2015 Feihu Zhang, Longquan Dai, Shiming Xiang, Xiaopeng Zhang

In our SGF, we use the tree distance on the segment graph to define the internal weight function of the filtering kernel, which enables the filter to smooth out high-contrast details and textures while preserving major image structures very well.

Optical Flow Estimation Stereo Matching +1

Fully Connected Guided Image Filtering

no code implementations ICCV 2015 Longquan Dai, Mengke Yuan, Feihu Zhang, Xiaopeng Zhang

This paper presents a linear time fully connected guided filter by introducing the minimum spanning tree (MST) to the guided filter (GF).

Image Retargeting by Content-Aware Synthesis

no code implementations26 Mar 2014 Weiming Dong, Fuzhang Wu, Yan Kong, Xing Mei, Tong-Yee Lee, Xiaopeng Zhang

We propose to retarget the textural regions by content-aware synthesis and non-textural regions by fast multi-operators.

Segment-Tree Based Cost Aggregation for Stereo Matching

no code implementations CVPR 2013 Xing Mei, Xun Sun, Wei-Ming Dong, Haitao Wang, Xiaopeng Zhang

Instead of employing the minimum spanning tree (MST) and its variants, a new tree structure, "Segment-Tree", is proposed for non-local matching cost aggregation.

Scene Segmentation Stereo Matching +1

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