Search Results for author: Jian Zhang

Found 244 papers, 87 papers with code

SSPFusion: A Semantic Structure-Preserving Approach for Infrared and Visible Image Fusion

no code implementations26 Sep 2023 Qiao Yang, Yu Zhang, Jian Zhang, Zijing Zhao, Shunli Zhang, Jinqiao Wang, Junzhe Chen

Most existing learning-based infrared and visible image fusion (IVIF) methods exhibit massive redundant information in the fusion images, i. e., yielding edge-blurring effect or unrecognizable for object detectors.

Infrared And Visible Image Fusion

IAIFNet: An Illumination-Aware Infrared and Visible Image Fusion Network

no code implementations26 Sep 2023 Qiao Yang, Yu Zhang, Jian Zhang, Zijing Zhao, Shunli Zhang, Jinqiao Wang, Junzhe Chen

Infrared and visible image fusion (IVIF) is used to generate fusion images with comprehensive features of both images, which is beneficial for downstream vision tasks.

Infrared And Visible Image Fusion

TextCLIP: Text-Guided Face Image Generation And Manipulation Without Adversarial Training

no code implementations21 Sep 2023 Xiaozhou You, Jian Zhang

Text-guided image generation aimed to generate desired images conditioned on given texts, while text-guided image manipulation refers to semantically edit parts of a given image based on specified texts.

Image Generation Image Manipulation +1

Exploring Flat Minima for Domain Generalization with Large Learning Rates

no code implementations12 Sep 2023 Jian Zhang, Lei Qi, Yinghuan Shi, Yang Gao

Instead, we observe that leveraging a large learning rate can simultaneously promote weight diversity and facilitate the identification of flat regions in the loss landscape.

Domain Generalization Semantic Segmentation

sasdim: self-adaptive noise scaling diffusion model for spatial time series imputation

no code implementations5 Sep 2023 Shunyang Zhang, Senzhang Wang, Xianzhen Tan, Ruochen Liu, Jian Zhang, Jianxin Wang

Spatial time series imputation is critically important to many real applications such as intelligent transportation and air quality monitoring.

Imputation Time Series

Self-Supervised Scalable Deep Compressed Sensing

1 code implementation26 Aug 2023 Bin Chen, Xuanyu Zhang, Shuai Liu, Yongbing Zhang, Jian Zhang

Compressed sensing (CS) is a promising tool for reducing sampling costs.

Masked Cross-image Encoding for Few-shot Segmentation

no code implementations22 Aug 2023 Wenbo Xu, Huaxi Huang, Ming Cheng, Litao Yu, Qiang Wu, Jian Zhang

Few-shot segmentation (FSS) is a dense prediction task that aims to infer the pixel-wise labels of unseen classes using only a limited number of annotated images.

Few-Shot Semantic Segmentation

DomainAdaptor: A Novel Approach to Test-time Adaptation

1 code implementation ICCV 2023 Jian Zhang, Lei Qi, Yinghuan Shi, Yang Gao

To deal with the domain shift between training and test samples, current methods have primarily focused on learning generalizable features during training and ignore the specificity of unseen samples that are also critical during the test.


DiffLLE: Diffusion-guided Domain Calibration for Unsupervised Low-light Image Enhancement

no code implementations18 Aug 2023 Shuzhou Yang, Xuanyu Zhang, Yinhuai Wang, Jiwen Yu, YuHan Wang, Jian Zhang

Specifically, we adopt a naive unsupervised enhancement algorithm to realize preliminary restoration and design two zero-shot plug-and-play modules based on diffusion model to improve generalization and effectiveness.

Denoising Low-Light Image Enhancement

Generalizable Decision Boundaries: Dualistic Meta-Learning for Open Set Domain Generalization

1 code implementation ICCV 2023 Xiran Wang, Jian Zhang, Lei Qi, Yinghuan Shi

Domain generalization (DG) is proposed to deal with the issue of domain shift, which occurs when statistical differences exist between source and target domains.

Domain Generalization Meta-Learning

EFLNet: Enhancing Feature Learning for Infrared Small Target Detection

no code implementations27 Jul 2023 Bo Yang, Xinyu Zhang, Jiahao Zhu, Jian Zhang, Dongjian Tian, Jun Luo, Mingliang Zhou, Yangjun Pi

Single-frame infrared small target detection is considered to be a challenging task, due to the extreme imbalance between target and background, bounding box regression is extremely sensitive to infrared small targets, and small target information is easy to lose in the high-level semantic layer.


Deep Physics-Guided Unrolling Generalization for Compressed Sensing

1 code implementation18 Jul 2023 Bin Chen, Jiechong Song, Jingfen Xie, Jian Zhang

By absorbing the merits of both the model- and data-driven methods, deep physics-engaged learning scheme achieves high-accuracy and interpretable image reconstruction.

Image Compressed Sensing Image Reconstruction

DragonDiffusion: Enabling Drag-style Manipulation on Diffusion Models

1 code implementation5 Jul 2023 Chong Mou, Xintao Wang, Jiechong Song, Ying Shan, Jian Zhang

Specifically, we construct classifier guidance based on the strong correspondence of intermediate features in the diffusion model.

HVTSurv: Hierarchical Vision Transformer for Patient-Level Survival Prediction from Whole Slide Image

1 code implementation30 Jun 2023 Zhuchen Shao, Yang Chen, Hao Bian, Jian Zhang, Guojun Liu, Yongbing Zhang

Many studies adopt random sampling pre-processing strategy and WSI-level aggregation models, which inevitably lose critical prognostic information in the patient-level bag.

Multiple Instance Learning Survival Prediction +1

Dynamic Path-Controllable Deep Unfolding Network for Compressive Sensing

1 code implementation28 Jun 2023 Jiechong Song, Bin Chen, Jian Zhang

Deep unfolding network (DUN) that unfolds the optimization algorithm into a deep neural network has achieved great success in compressive sensing (CS) due to its good interpretability and high performance.

Compressive Sensing

Infrastructure Crack Segmentation: Boundary Guidance Method and Benchmark Dataset

no code implementations15 Jun 2023 Zhili He, Wang Chen, Jian Zhang, Yu-Hsing Wang

Cracks provide an essential indicator of infrastructure performance degradation, and achieving high-precision pixel-level crack segmentation is an issue of concern.

Crack Segmentation

CRoSS: Diffusion Model Makes Controllable, Robust and Secure Image Steganography

1 code implementation26 May 2023 Jiwen Yu, Xuanyu Zhang, Youmin Xu, Jian Zhang

Current image steganography techniques are mainly focused on cover-based methods, which commonly have the risk of leaking secret images and poor robustness against degraded container images.

Image Steganography

On the Tool Manipulation Capability of Open-source Large Language Models

1 code implementation25 May 2023 Qiantong Xu, Fenglu Hong, Bo Li, Changran Hu, Zhengyu Chen, Jian Zhang

In this paper, we ask can we enhance open-source LLMs to be competitive to leading closed LLM APIs in tool manipulation, with practical amount of human supervision.

Cross-source Point Cloud Registration: Challenges, Progress and Prospects

no code implementations23 May 2023 Xiaoshui Huang, Guofeng Mei, Jian Zhang

The emerging topic of cross-source point cloud (CSPC) registration has attracted increasing attention with the fast development background of 3D sensor technologies.

Point Cloud Registration

An Object SLAM Framework for Association, Mapping, and High-Level Tasks

no code implementations12 May 2023 Yanmin Wu, Yunzhou Zhang, Delong Zhu, Zhiqiang Deng, Wenkai Sun, Xin Chen, Jian Zhang

Taking into consideration the semantic invariance of objects, we convert the object map to a topological map to provide semantic descriptors to enable multi-map matching.

Decision Making Object SLAM +1

Single Node Injection Label Specificity Attack on Graph Neural Networks via Reinforcement Learning

no code implementations4 May 2023 Dayuan Chen, Jian Zhang, Yuqian Lv, Jinhuan Wang, Hongjie Ni, Shanqing Yu, Zhen Wang, Qi Xuan

Furthermore, most methods concentrate on a single attack goal and lack a generalizable adversary to develop distinct attack strategies for diverse goals, thus limiting precise control over victim model behavior in real-world scenarios.


Hierarchical Dialogue Understanding with Special Tokens and Turn-level Attention

1 code implementation Tiny Papers @ ICLR 2023 Xiao Liu, Jian Zhang, Heng Zhang, Fuzhao Xue, Yang You

We evaluate our model on various dialogue understanding tasks including dialogue relation extraction, dialogue emotion recognition, and dialogue act classification.

Dialogue Act Classification Dialogue Understanding +2

Optimization-Inspired Cross-Attention Transformer for Compressive Sensing

1 code implementation CVPR 2023 Jiechong Song, Chong Mou, Shiqi Wang, Siwei Ma, Jian Zhang

And, PGCA block achieves an enhanced information interaction, which introduces the inertia force into the gradient descent step through a cross attention block.

Compressive Sensing

OPDN: Omnidirectional Position-aware Deformable Network for Omnidirectional Image Super-Resolution

no code implementations26 Apr 2023 Xiaopeng Sun, Weiqi Li, Zhenyu Zhang, Qiufang Ma, Xuhan Sheng, Ming Cheng, Haoyu Ma, Shijie Zhao, Jian Zhang, Junlin Li, Li Zhang

Model A aims to enhance the feature extraction ability of 360{\deg} image positional information, while Model B further focuses on the high-frequency information of 360{\deg} images.

Image Super-Resolution

Large-capacity and Flexible Video Steganography via Invertible Neural Network

1 code implementation CVPR 2023 Chong Mou, Youmin Xu, Jiechong Song, Chen Zhao, Bernard Ghanem, Jian Zhang

For large-capacity, we present a reversible pipeline to perform multiple videos hiding and recovering through a single invertible neural network (INN).

A Unified Continual Learning Framework with General Parameter-Efficient Tuning

1 code implementation ICCV 2023 Qiankun Gao, Chen Zhao, Yifan Sun, Teng Xi, Gang Zhang, Bernard Ghanem, Jian Zhang

1) Learning: the pre-trained model adapts to the new task by tuning an online PET module, along with our adaptation speed calibration to align different PET modules, 2) Accumulation: the task-specific knowledge learned by the online PET module is accumulated into an offline PET module through momentum update, 3) Ensemble: During inference, we respectively construct two experts with online/offline PET modules (which are favored by the novel/historical tasks) for prediction ensemble.

Continual Learning

Progressive Content-aware Coded Hyperspectral Compressive Imaging

no code implementations17 Mar 2023 Xuanyu Zhang, Bin Chen, Wenzhen Zou, Shuai Liu, Yongbing Zhang, Ruiqin Xiong, Jian Zhang

Hyperspectral imaging plays a pivotal role in a wide range of applications, like remote sensing, medicine, and cytology.

FreeDoM: Training-Free Energy-Guided Conditional Diffusion Model

1 code implementation ICCV 2023 Jiwen Yu, Yinhuai Wang, Chen Zhao, Bernard Ghanem, Jian Zhang

In this work, we propose a training-Free conditional Diffusion Model (FreeDoM) used for various conditions.

Face Detection

Unlimited-Size Diffusion Restoration

1 code implementation1 Mar 2023 Yinhuai Wang, Jiwen Yu, Runyi Yu, Jian Zhang

Our simple, parameter-free approaches can be used not only for image restoration but also for image generation of unlimited sizes, with the potential to be a general tool for diffusion models.

Image Generation Image Restoration

T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models

2 code implementations16 Feb 2023 Chong Mou, Xintao Wang, Liangbin Xie, Yanze Wu, Jian Zhang, Zhongang Qi, Ying Shan, XiaoHu Qie

In this paper, we aim to ``dig out" the capabilities that T2I models have implicitly learned, and then explicitly use them to control the generation more granularly.

Image Generation Style Transfer

Cross-domain recommendation via user interest alignment

no code implementations26 Jan 2023 Chuang Zhao, Hongke Zhao, Ming He, Jian Zhang, Jianping Fan

Specifically, we first construct a unified cross-domain heterogeneous graph and redefine the message passing mechanism of graph convolutional networks to capture high-order similarity of users and items across domains.

Recommendation Systems

Temporal-Coded Spiking Neural Networks with Dynamic Firing Threshold: Learning with Event-Driven Backpropagation

no code implementations ICCV 2023 Wenjie Wei, Malu Zhang, Hong Qu, Ammar Belatreche, Jian Zhang, Hong Chen

As a temporal encoding scheme for SNNs, Time-To-First-Spike (TTFS) encodes information using the timing of a single spike, which allows spiking neurons to transmit information through sparse spike trains and results in lower power consumption and higher computational efficiency compared to traditional rate-based encoding counterparts.

Image Classification

Panoptic Compositional Feature Field for Editable Scene Rendering With Network-Inferred Labels via Metric Learning

no code implementations CVPR 2023 Xinhua Cheng, Yanmin Wu, Mengxi Jia, Qian Wang, Jian Zhang

In this work, we attempt to learn an object-compositional neural implicit representation for editable scene rendering by leveraging labels inferred from the off-the-shelf 2D panoptic segmentation networks instead of the ground truth annotations.

Metric Learning Novel View Synthesis +1

Latent Evolution Model for Change Point Detection in Time-varying Networks

no code implementations17 Dec 2022 Yongshun Gong, Xue Dong, Jian Zhang, Meng Chen

Our method focuses on learning the low-dimensional representations of networks and capturing the evolving patterns of these learned latent representations simultaneously.

Change Point Detection

Position Embedding Needs an Independent Layer Normalization

1 code implementation10 Dec 2022 Runyi Yu, Zhennan Wang, Yinhuai Wang, Kehan Li, Yian Zhao, Jian Zhang, Guoli Song, Jie Chen

By analyzing the input and output of each encoder layer in VTs using reparameterization and visualization, we find that the default PE joining method (simply adding the PE and patch embedding together) operates the same affine transformation to token embedding and PE, which limits the expressiveness of PE and hence constrains the performance of VTs.

Self-Supervised Object Goal Navigation with In-Situ Finetuning

no code implementations9 Dec 2022 So Yeon Min, Yao-Hung Hubert Tsai, Wei Ding, Ali Farhadi, Ruslan Salakhutdinov, Yonatan Bisk, Jian Zhang

In contrast, our LocCon shows the most robust transfer in the real world among the set of models we compare to, and that the real-world performance of all models can be further improved with self-supervised LocCon in-situ training.

Contrastive Learning Navigate +1

Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model

2 code implementations1 Dec 2022 Yinhuai Wang, Jiwen Yu, Jian Zhang

Most existing Image Restoration (IR) models are task-specific, which can not be generalized to different degradation operators.

Colorization Deblurring +7

GAN Prior based Null-Space Learning for Consistent Super-Resolution

1 code implementation24 Nov 2022 Yinhuai Wang, Yujie Hu, Jiwen Yu, Jian Zhang

Consistency and realness have always been the two critical issues of image super-resolution.

Image Super-Resolution

Complementary Labels Learning with Augmented Classes

no code implementations19 Nov 2022 Zhongnian Li, Jian Zhang, Mengting Xu, Xinzheng Xu, Daoqiang Zhang

In this paper, we propose a novel problem setting called Complementary Labels Learning with Augmented Classes (CLLAC), which brings the challenge that classifiers trained by complementary labels should not only be able to classify the instances from observed classes accurately, but also recognize the instance from the Augmented Classes in the testing phase.

Masked Vision-Language Transformers for Scene Text Recognition

1 code implementation9 Nov 2022 Jie Wu, Ying Peng, Shengming Zhang, Weigang Qi, Jian Zhang

MVLT is trained in two stages: in the first stage, we design a STR-tailored pretraining method based on a masking strategy; in the second stage, we fine-tune our model and adopt an iterative correction method to improve the performance.

Scene Text Recognition

Overlap-guided Gaussian Mixture Models for Point Cloud Registration

1 code implementation17 Oct 2022 Guofeng Mei, Fabio Poiesi, Cristiano Saltori, Jian Zhang, Elisa Ricci, Nicu Sebe

Probabilistic 3D point cloud registration methods have shown competitive performance in overcoming noise, outliers, and density variations.

Point Cloud Registration

Multi-Agent Automated Machine Learning

no code implementations CVPR 2023 Zhaozhi Wang, Kefan Su, Jian Zhang, Huizhu Jia, Qixiang Ye, Xiaodong Xie, Zongqing Lu

In this paper, we propose multi-agent automated machine learning (MA2ML) with the aim to effectively handle joint optimization of modules in automated machine learning (AutoML).

Data Augmentation Multi-agent Reinforcement Learning +1

Data Augmentation-free Unsupervised Learning for 3D Point Cloud Understanding

1 code implementation6 Oct 2022 Guofeng Mei, Cristiano Saltori, Fabio Poiesi, Jian Zhang, Elisa Ricci, Nicu Sebe, Qiang Wu

Unsupervised learning on 3D point clouds has undergone a rapid evolution, especially thanks to data augmentation-based contrastive methods.

3D Object Classification Contrastive Learning +3

EDA: Explicit Text-Decoupling and Dense Alignment for 3D Visual Grounding

2 code implementations CVPR 2023 Yanmin Wu, Xinhua Cheng, Renrui Zhang, Zesen Cheng, Jian Zhang

3D visual grounding aims to find the object within point clouds mentioned by free-form natural language descriptions with rich semantic cues.

Visual Grounding

Towards Multimodal Multitask Scene Understanding Models for Indoor Mobile Agents

no code implementations27 Sep 2022 Yao-Hung Hubert Tsai, Hanlin Goh, Ali Farhadi, Jian Zhang

The perception system in personalized mobile agents requires developing indoor scene understanding models, which can understand 3D geometries, capture objectiveness, analyze human behaviors, etc.

3D Object Detection Autonomous Driving +7

D3C2-Net: Dual-Domain Deep Convolutional Coding Network for Compressive Sensing

no code implementations27 Jul 2022 Weiqi Li, Bin Chen, Jian Zhang

By unfolding the proposed framework into deep neural networks, we further design a novel Dual-Domain Deep Convolutional Coding Network (D3C2-Net) for CS imaging with the capability of transmitting high-throughput feature-level image representation through all the unfolded stages.

Compressive Sensing

TransCL: Transformer Makes Strong and Flexible Compressive Learning

1 code implementation25 Jul 2022 Chong Mou, Jian Zhang

Compressive learning (CL) is an emerging framework that integrates signal acquisition via compressed sensing (CS) and machine learning for inference tasks directly on a small number of measurements.

Image Classification Semantic Segmentation

Spatial-temporal Analysis for Automated Concrete Workability Estimation

no code implementations24 Jul 2022 Litao Yu, Jian Zhang, Mohammed Bennamoun, Xiaojun Chang, Vute Sirivivatnanon, Ali Nezhad

Concrete workability measure is mostly determined based on subjective assessment of a certified assessor with visual inspections.


Content-aware Scalable Deep Compressed Sensing

1 code implementation19 Jul 2022 Bin Chen, Jian Zhang

To more efficiently address image compressed sensing (CS) problems, we present a novel content-aware scalable network dubbed CASNet which collectively achieves adaptive sampling rate allocation, fine granular scalability and high-quality reconstruction.

Blocking Image Compressed Sensing +1

Frequency Domain Model Augmentation for Adversarial Attack

1 code implementation12 Jul 2022 Yuyang Long, Qilong Zhang, Boheng Zeng, Lianli Gao, Xianglong Liu, Jian Zhang, Jingkuan Song

Specifically, we apply a spectrum transformation to the input and thus perform the model augmentation in the frequency domain.

Adversarial Attack

Horizontal and Vertical Attention in Transformers

no code implementations10 Jul 2022 Litao Yu, Jian Zhang

Transformers are built upon multi-head scaled dot-product attention and positional encoding, which aim to learn the feature representations and token dependencies.

Dimensionality Reduction

Self-attention on Multi-Shifted Windows for Scene Segmentation

1 code implementation10 Jul 2022 Litao Yu, Zhibin Li, Jian Zhang, Qiang Wu

Scene segmentation in images is a fundamental yet challenging problem in visual content understanding, which is to learn a model to assign every image pixel to a categorical label.

Descriptive Scene Segmentation

Multiple Instance Learning with Mixed Supervision in Gleason Grading

1 code implementation26 Jun 2022 Hao Bian, Zhuchen Shao, Yang Chen, Yifeng Wang, Haoqian Wang, Jian Zhang, Yongbing Zhang

We achieve the state-of-the-art performance on the SICAPv2 dataset, and the visual analysis shows the accurate prediction results of instance level.

Multiple Instance Learning whole slide images

Learning the policy for mixed electric platoon control of automated and human-driven vehicles at signalized intersection: a random search approach

no code implementations24 Jun 2022 Xia Jiang, Jian Zhang, Xiaoyu Shi, Jian Cheng

Meanwhile, the simulation results demonstrate the effectiveness of the delay reward, which is designed to outperform distributed reward mechanism} Compared with normal car-following behavior, the sensitivity analysis reveals that the energy can be saved to different extends (39. 27%-82. 51%) by adjusting the relative importance of the optimization goal.

reinforcement-learning Reinforcement Learning (RL)

Eco-driving for Electric Connected Vehicles at Signalized Intersections: A Parameterized Reinforcement Learning approach

no code implementations24 Jun 2022 Xia Jiang, Jian Zhang, Dan Li

This paper proposes an eco-driving framework for electric connected vehicles (CVs) based on reinforcement learning (RL) to improve vehicle energy efficiency at signalized intersections.

Reinforcement Learning (RL)

Using EBGAN for Anomaly Intrusion Detection

no code implementations21 Jun 2022 Yi Cui, Wenfeng Shen, Jian Zhang, Weijia Lu, Chuang Liu, Lin Sun, Si Chen

The generator in IDS-EBGAN is responsible for converting the original malicious network traffic in the training set into adversarial malicious examples.

Intrusion Detection

Hierarchical Similarity Learning for Aliasing Suppression Image Super-Resolution

no code implementations7 Jun 2022 Yuqing Liu, Qi Jia, Jian Zhang, Xin Fan, Shanshe Wang, Siwei Ma, Wen Gao

As a highly ill-posed issue, single image super-resolution (SISR) has been widely investigated in recent years.

Image Super-Resolution

MM-RealSR: Metric Learning based Interactive Modulation for Real-World Super-Resolution

1 code implementation10 May 2022 Chong Mou, Yanze Wu, Xintao Wang, Chao Dong, Jian Zhang, Ying Shan

Instead of using known degradation levels as explicit supervision to the interactive mechanism, we propose a metric learning strategy to map the unquantifiable degradation levels in real-world scenarios to a metric space, which is trained in an unsupervised manner.

Image Restoration Metric Learning +1

Deep Generalized Unfolding Networks for Image Restoration

1 code implementation CVPR 2022 Chong Mou, Qian Wang, Jian Zhang

Concretely, without loss of interpretability, we integrate a gradient estimation strategy into the gradient descent step of the Proximal Gradient Descent (PGD) algorithm, driving it to deal with complex and real-world image degradation.

Image Restoration

Investigating Accuracy-Novelty Performance for Graph-based Collaborative Filtering

1 code implementation26 Apr 2022 Minghao Zhao, Le Wu, Yile Liang, Lei Chen, Jian Zhang, Qilin Deng, Kai Wang, Xudong Shen, Tangjie Lv, Runze Wu

While conventional CF models are known for facing the challenges of the popularity bias that favors popular items, one may wonder "Whether the existing graph-based CF models alleviate or exacerbate popularity bias of recommender systems?"

Collaborative Filtering Recommendation Systems

Learning Weighting Map for Bit-Depth Expansion within a Rational Range

1 code implementation26 Apr 2022 Yuqing Liu, Qi Jia, Jian Zhang, Xin Fan, Shanshe Wang, Siwei Ma, Wen Gao

Existing BDE methods have no unified solution for various BDE situations, and directly learn a mapping for each pixel from LBD image to the desired value in HBD image, which may change the given high-order bits and lead to a huge deviation from the ground truth.


PUERT: Probabilistic Under-sampling and Explicable Reconstruction Network for CS-MRI

1 code implementation24 Apr 2022 Jingfen Xie, Jian Zhang, Yongbing Zhang, Xiangyang Ji

Compressed Sensing MRI (CS-MRI) aims at reconstructing de-aliased images from sub-Nyquist sampling k-space data to accelerate MR Imaging, thus presenting two basic issues, i. e., where to sample and how to reconstruct.


R-DFCIL: Relation-Guided Representation Learning for Data-Free Class Incremental Learning

1 code implementation24 Mar 2022 Qiankun Gao, Chen Zhao, Bernard Ghanem, Jian Zhang

After RRL, the classification head is refined with global class-balanced classification loss to address the data imbalance issue as well as learn the decision boundaries between new and previous classes.

class-incremental learning Class Incremental Learning +3

A Prompting-based Approach for Adversarial Example Generation and Robustness Enhancement

no code implementations21 Mar 2022 Yuting Yang, Pei Huang, Juan Cao, Jintao Li, Yun Lin, Jin Song Dong, Feifei Ma, Jian Zhang

Our attack technique targets the inherent vulnerabilities of NLP models, allowing us to generate samples even without interacting with the victim NLP model, as long as it is based on pre-trained language models (PLMs).

Adversarial Attack

Series Photo Selection via Multi-view Graph Learning

no code implementations18 Mar 2022 Jin Huang, Lu Zhang, Yongshun Gong, Jian Zhang, Xiushan Nie, Yilong Yin

Series photo selection (SPS) is an important branch of the image aesthetics quality assessment, which focuses on finding the best one from a series of nearly identical photos.

Aesthetics Quality Assessment Graph Learning

Panini-Net: GAN Prior Based Degradation-Aware Feature Interpolation for Face Restoration

1 code implementation16 Mar 2022 Yinhuai Wang, Yujie Hu, Jian Zhang

Emerging high-quality face restoration (FR) methods often utilize pre-trained GAN models (\textit{i. e.}, StyleGAN2) as GAN Prior.

Representation Learning Super-Resolution

NeRFocus: Neural Radiance Field for 3D Synthetic Defocus

1 code implementation10 Mar 2022 Yinhuai Wang, Shuzhou Yang, Yujie Hu, Jian Zhang

Unlike the pinhole, the thin lens refracts rays of a scene point, so its imaging on the sensor plane is scattered as a circle of confusion (CoC).

Unsupervised Learning on 3D Point Clouds by Clustering and Contrasting

no code implementations5 Feb 2022 Guofeng Mei, Litao Yu, Qiang Wu, Jian Zhang, Mohammed Bennamoun

This paper proposes a general unsupervised approach, named \textbf{ConClu}, to perform the learning of point-wise and global features by jointly leveraging point-level clustering and instance-level contrasting.

3D Object Classification Clustering +2

Quantifying Robustness to Adversarial Word Substitutions

no code implementations11 Jan 2022 Yuting Yang, Pei Huang, Feifei Ma, Juan Cao, Meishan Zhang, Jian Zhang, Jintao Li

Deep-learning-based NLP models are found to be vulnerable to word substitution perturbations.

Robust Invertible Image Steganography

no code implementations CVPR 2022 Youmin Xu, Chong Mou, Yujie Hu, Jingfen Xie, Jian Zhang

Previous image steganography methods are limited in hiding capacity and robustness, commonly vulnerable to distortion on container images such as Gaussian noise, Poisson noise, and lossy compression.

Image Steganography

Image Disentanglement Autoencoder for Steganography Without Embedding

1 code implementation CVPR 2022 Xiyao Liu, Ziping Ma, Junxing Ma, Jian Zhang, Gerald Schaefer, Hui Fang

Conventional steganography approaches embed a secret message into a carrier for concealed communication but are prone to attack by recent advanced steganalysis tools.

Disentanglement Steganalysis

CSformer: Bridging Convolution and Transformer for Compressive Sensing

1 code implementation31 Dec 2021 Dongjie Ye, Zhangkai Ni, Hanli Wang, Jian Zhang, Shiqi Wang, Sam Kwong

The proposed approach is an end-to-end compressive image sensing method, composed of adaptive sampling and recovery.

Compressive Sensing Inductive Bias +1

COTReg:Coupled Optimal Transport based Point Cloud Registration

no code implementations29 Dec 2021 Guofeng Mei, Xiaoshui Huang, Litao Yu, Jian Zhang, Mohammed Bennamoun

Generating a set of high-quality correspondences or matches is one of the most critical steps in point cloud registration.

Point Cloud Registration

MVDG: A Unified Multi-view Framework for Domain Generalization

1 code implementation23 Dec 2021 Jian Zhang, Lei Qi, Yinghuan Shi, Yang Gao

Beyond the training stage, overfitting could also cause unstable prediction in the test stage.

Domain Generalization Meta-Learning

HerosNet: Hyperspectral Explicable Reconstruction and Optimal Sampling Deep Network for Snapshot Compressive Imaging

1 code implementation CVPR 2022 Xuanyu Zhang, Yongbing Zhang, Ruiqin Xiong, Qilin Sun, Jian Zhang

Hyperspectral imaging is an essential imaging modality for a wide range of applications, especially in remote sensing, agriculture, and medicine.

Compressive Sensing

GenReg: Deep Generative Method for Fast Point Cloud Registration

no code implementations23 Nov 2021 Xiaoshui Huang, Zongyi Xu, Guofeng Mei, Sheng Li, Jian Zhang, Yifan Zuo, Yucheng Wang

To solve this challenge, we propose a new data-driven registration algorithm by investigating deep generative neural networks to point cloud registration.

Point Cloud Registration

Can Graph Neural Networks Learn to Solve MaxSAT Problem?

no code implementations15 Nov 2021 Minghao Liu, Fuqi Jia, Pei Huang, Fan Zhang, Yuchen Sun, Shaowei Cai, Feifei Ma, Jian Zhang

With the rapid development of deep learning techniques, various recent work has tried to apply graph neural networks (GNNs) to solve NP-hard problems such as Boolean Satisfiability (SAT), which shows the potential in bridging the gap between machine learning and symbolic reasoning.

ε-weakened Robustness of Deep Neural Networks

no code implementations29 Oct 2021 Pei Huang, Yuting Yang, Minghao Liu, Fuqi Jia, Feifei Ma, Jian Zhang

This paper introduces a notation of $\varepsilon$-weakened robustness for analyzing the reliability and stability of deep neural networks (DNNs).

Research on the Inverse Kinematics Prediction of a Soft Biomimetic Actuator via BP Neural Network

no code implementations26 Oct 2021 Huichen Ma, Junjie Zhou, Jian Zhang, Lingyu Zhang

After training with sample data, the BP neural network model can represent the relation between the manipulator tip position and the pressure applied to the chambers.

Motion Planning

Memory-Augmented Deep Unfolding Network for Compressive Sensing

1 code implementation19 Oct 2021 Jiechong Song, Bin Chen, Jian Zhang

By understanding DUNs from the perspective of the human brain's memory processing, we find there exists two issues in existing DUNs.

Compressive Sensing

Inconsistency-aware Uncertainty Estimation for Semi-supervised Medical Image Segmentation

1 code implementation17 Oct 2021 Yinghuan Shi, Jian Zhang, Tong Ling, Jiwen Lu, Yefeng Zheng, Qian Yu, Lei Qi, Yang Gao

In semi-supervised medical image segmentation, most previous works draw on the common assumption that higher entropy means higher uncertainty.

Image Segmentation Semantic Segmentation +1

Dyn-Backdoor: Backdoor Attack on Dynamic Link Prediction

no code implementations8 Oct 2021 Jinyin Chen, Haiyang Xiong, Haibin Zheng, Jian Zhang, Guodong Jiang, Yi Liu

Backdoor attacks induce the DLP methods to make wrong prediction by the malicious training data, i. e., generating a subgraph sequence as the trigger and embedding it to the training data.

Backdoor Attack Dynamic Link Prediction

Dynamic Attentive Graph Learning for Image Restoration

1 code implementation ICCV 2021 Chong Mou, Jian Zhang, Zhuoyuan Wu

Specifically, we propose an improved graph model to perform patch-wise graph convolution with a dynamic and adaptive number of neighbors for each node.

Demosaicking Graph Learning +1

Dense Deep Unfolding Network with 3D-CNN Prior for Snapshot Compressive Imaging

1 code implementation ICCV 2021 Zhuoyuan Wu, Jian Zhang, Chong Mou

To better exploit the spatial-temporal correlation among frames and address the problem of information loss between adjacent phases in existing DUNs, we propose to adopt the 3D-CNN prior in our proximal mapping module and develop a novel dense feature map (DFM) strategy, respectively.

Structure Destruction and Content Combination for Face Anti-Spoofing

no code implementations22 Jul 2021 Ke-Yue Zhang, Taiping Yao, Jian Zhang, Shice Liu, Bangjie Yin, Shouhong Ding, Jilin Li

In pursuit of consolidating the face verification systems, prior face anti-spoofing studies excavate the hidden cues in original images to discriminate real persons and diverse attack types with the assistance of auxiliary supervision.

Face Anti-Spoofing Face Verification +1

EGC2: Enhanced Graph Classification with Easy Graph Compression

1 code implementation16 Jul 2021 Jinyin Chen, Haiyang Xiong, Haibin Zhenga, Dunjie Zhang, Jian Zhang, Mingwei Jia, Yi Liu

To achieve lower-complexity defense applied to graph classification models, EGC2 utilizes a centrality-based edge-importance index to compress the graphs, filtering out trivial structures and adversarial perturbations in the input graphs, thus improving the model's robustness.

Graph Classification

Multi-Level Contrastive Learning for Few-Shot Problems

no code implementations15 Jul 2021 Qing Chen, Jian Zhang

Most current applications of contrastive learning benefit only a single representation from the last layer of an encoder. In this paper, we propose a multi-level contrasitive learning approach which applies contrastive losses at different layers of an encoder to learn multiple representations from the encoder.

Contrastive Learning Few-Shot Learning

COAST: COntrollable Arbitrary-Sampling NeTwork for Compressive Sensing

1 code implementation15 Jul 2021 Di You, Jian Zhang, Jingfen Xie, Bin Chen, Siwei Ma

In this paper, we propose a novel COntrollable Arbitrary-Sampling neTwork, dubbed COAST, to solve CS problems of arbitrary-sampling matrices (including unseen sampling matrices) with one single model.

Blocking Compressive Sensing

Learning Disentangled Representation Implicitly via Transformer for Occluded Person Re-Identification

no code implementations6 Jul 2021 Mengxi Jia, Xinhua Cheng, Shijian Lu, Jian Zhang

To better eliminate interference from occlusions, we design a contrast feature learning technique (CFL) for better separation of occlusion features and discriminative ID features.

Person Re-Identification Representation Learning

Spk2ImgNet: Learning To Reconstruct Dynamic Scene From Continuous Spike Stream

no code implementations CVPR 2021 Jing Zhao, Ruiqin Xiong, Hangfan Liu, Jian Zhang, Tiejun Huang

Different from the conventional digital cameras that compact the photoelectric information within the exposure interval into a single snapshot, the spike camera produces a continuous spike stream to record the dynamic light intensity variation process.

Image Reconstruction

A Multi-Branch Hybrid Transformer Networkfor Corneal Endothelial Cell Segmentation

no code implementations21 May 2021 Yinglin Zhang, Risa Higashita, Huazhu Fu, Yanwu Xu, Yang Zhang, Haofeng Liu, Jian Zhang, Jiang Liu

Corneal endothelial cell segmentation plays a vital role inquantifying clinical indicators such as cell density, coefficient of variation, and hexagonality.

Cell Segmentation

Uncertainty Weighted Actor-Critic for Offline Reinforcement Learning

2 code implementations17 May 2021 Yue Wu, Shuangfei Zhai, Nitish Srivastava, Joshua Susskind, Jian Zhang, Ruslan Salakhutdinov, Hanlin Goh

Offline Reinforcement Learning promises to learn effective policies from previously-collected, static datasets without the need for exploration.

Offline RL Q-Learning +2

Unsupervised Sentiment Analysis by Transferring Multi-source Knowledge

no code implementations9 May 2021 Yong Dai, Jian Liu, Jian Zhang, Hongguang Fu, Zenglin Xu

The first mechanism is a selective domain adaptation (SDA) method, which transfers knowledge from the closest source domain.

Domain Adaptation Sentiment Analysis

Underwater Target Recognition based on Multi-Decision LOFAR Spectrum Enhancement: A Deep Learning Approach

no code implementations26 Apr 2021 Jie Chen, Jie Liu, Chang Liu, Jian Zhang, Bing Han

To overcome this issue and to further improve the recognition performance, we adopt a deep learning approach for underwater target recognition and propose a LOFAR spectrum enhancement (LSE)-based underwater target recognition scheme, which consists of preprocessing, offline training, and online testing.

Super-Resolving Compressed Video in Coding Chain

no code implementations26 Mar 2021 Dewang Hou, Yang Zhao, Yuyao Ye, Jiayu Yang, Jian Zhang, Ronggang Wang

Scaling and lossy coding are widely used in video transmission and storage.

Jo-SRC: A Contrastive Approach for Combating Noisy Labels

no code implementations CVPR 2021 Yazhou Yao, Zeren Sun, Chuanyi Zhang, Fumin Shen, Qi Wu, Jian Zhang, Zhenmin Tang

Due to the memorization effect in Deep Neural Networks (DNNs), training with noisy labels usually results in inferior model performance.

Contrastive Learning Memorization

ISTA-Net++: Flexible Deep Unfolding Network for Compressive Sensing

1 code implementation22 Mar 2021 Di You, Jingfen Xie, Jian Zhang

While deep neural networks have achieved impressive success in image compressive sensing (CS), most of them lack flexibility when dealing with multi-ratio tasks and multi-scene images in practical applications.

Blocking Compressive Sensing

Thousand to One: Semantic Prior Modeling for Conceptual Coding

no code implementations12 Mar 2021 Jianhui Chang, Zhenghui Zhao, Lingbo Yang, Chuanmin Jia, Jian Zhang, Siwei Ma

To this end, we propose a novel end-to-end semantic prior modeling-based conceptual coding scheme towards extremely low bitrate image compression, which leverages semantic-wise deep representations as a unified prior for entropy estimation and texture synthesis.

Image Compression Semantic Segmentation +1

COLA-Net: Collaborative Attention Network for Image Restoration

2 code implementations10 Mar 2021 Chong Mou, Jian Zhang, Xiaopeng Fan, Hangfan Liu, Ronggang Wang

Local and non-local attention-based methods have been well studied in various image restoration tasks while leading to promising performance.

CoLA Image Denoising +1

A comprehensive survey on point cloud registration

no code implementations3 Mar 2021 Xiaoshui Huang, Guofeng Mei, Jian Zhang, Rana Abbas

This survey conducts a comprehensive survey, including both same-source and cross-source registration methods, and summarize the connections between optimization-based and deep learning methods, to provide further research insight.

3D Reconstruction Point Cloud Registration

Temperature dependent coherence properties of NV ensemble in diamond up to 600K

no code implementations25 Feb 2021 Shengran Lin, Changfeng Weng, Yuanjie Yang, Jiaxin Zhao, Yuhang Guo, Jian Zhang, Liren Lou, Wei Zhu, Guanzhong Wang

Nitrogen-vacancy (NV) center in diamond is an ideal candidate for quantum sensors because of its excellent optical and coherence property.

Quantum Physics Mesoscale and Nanoscale Physics

Temporal-Amount Snapshot MultiGraph for Ethereum Transaction Tracking

no code implementations16 Feb 2021 Yunyi Xie, Jie Jin, Jian Zhang, Shanqing Yu, Qi Xuan

With the wide application of blockchain in the financial field, the rise of various types of cybercrimes has brought great challenges to the security of blockchain.

Link Prediction

Exploiting Web Images for Fine-Grained Visual Recognition by Eliminating Noisy Samples and Utilizing Hard Ones

1 code implementation23 Jan 2021 Huafeng Liu, Chuanyi Zhang, Yazhou Yao, Xiushen Wei, Fumin Shen, Jian Zhang, Zhenmin Tang

Labeling objects at a subordinate level typically requires expert knowledge, which is not always available when using random annotators.

Fine-Grained Visual Recognition

Revisiting BFfloat16 Training

no code implementations1 Jan 2021 Pedram Zamirai, Jian Zhang, Christopher R Aberger, Christopher De Sa

We ask can we do pure 16-bit training which requires only 16-bit compute units, while still matching the model accuracy attained by 32-bit training.

Uncertainty Weighted Offline Reinforcement Learning

no code implementations1 Jan 2021 Yue Wu, Shuangfei Zhai, Nitish Srivastava, Joshua M. Susskind, Jian Zhang, Ruslan Salakhutdinov, Hanlin Goh

Offline Reinforcement Learning promises to learn effective policies from previously-collected, static datasets without the need for exploration.

Offline RL Q-Learning +2

Multi-Representation Ensemble in Few-Shot Learning

no code implementations1 Jan 2021 Qing Chen, Jian Zhang

Deep neural networks (DNNs) compute representations in a layer by layer fashion, producing a final representation at the top layer of the pipeline, and classification or regression is made using the final representation.

Few-Shot Learning

Super Resolve Dynamic Scene From Continuous Spike Streams

no code implementations ICCV 2021 Jing Zhao, Jiyu Xie, Ruiqin Xiong, Jian Zhang, Zhaofei Yu, Tiejun Huang

In this paper, we properly exploit the relative motion and derive the relationship between light intensity and each spike, so as to recover the external scene with both high temporal and high spatial resolution.


Counting the Number of Solutions to Constraints

no code implementations28 Dec 2020 Jian Zhang, Cunjing Ge, Feifei Ma

Compared with constraint satisfaction problems, counting problems have received less attention.

Multiple Instance Segmentation in Brachial Plexus Ultrasound Image Using BPMSegNet

no code implementations22 Dec 2020 Yi Ding, Qiqi Yang, Guozheng Wu, Jian Zhang, Zhiguang Qin

In this paper, a network called Brachial Plexus Multi-instance Segmentation Network (BPMSegNet) is proposed to identify different tissues (nerves, arteries, veins, muscles) in ultrasound images.

Instance Segmentation Semantic Segmentation

PTN: A Poisson Transfer Network for Semi-supervised Few-shot Learning

no code implementations20 Dec 2020 Huaxi Huang, Junjie Zhang, Jian Zhang, Qiang Wu, Chang Xu

Second, the extra unlabeled samples are employed to transfer the knowledge from base classes to novel classes through contrastive learning.

Contrastive Learning Few-Shot Learning

Self-Supervised Learning of Lidar Segmentation for Autonomous Indoor Navigation

2 code implementations10 Dec 2020 Hugues Thomas, Ben Agro, Mona Gridseth, Jian Zhang, Timothy D. Barfoot

We provide insights into our network predictions and show that our approach can also improve the performances of common localization techniques.

Navigate Point Cloud Segmentation +3

Rigid and Articulated Point Registration with Expectation Conditional Maximization

no code implementations9 Dec 2020 Radu Horaud, Florence Forbes, Manuel Yguel, Guillaume Dewaele, Jian Zhang

This paper addresses the issue of matching rigid and articulated shapes through probabilistic point registration.

Field-wise Learning for Multi-field Categorical Data

1 code implementation NeurIPS 2020 Zhibin Li, Jian Zhang, Yongshun Gong, Yazhou Yao, Qiang Wu

We present a model that utilizes linear models with variance and low-rank constraints, to help it generalize better and reduce the number of parameters.

Time-Series Snapshot Network for Partner Recommendation: A Case Study on OSS

no code implementations18 Nov 2020 Jinyin Chen, Yunyi Xie, Jian Zhang, Xincheng Shu, Qi Xuan

In this paper, we introduce time-series snapshot network (TSSN) which is a mixture network to model the interactions among users and developers.

Social and Information Networks

Conceptual Compression via Deep Structure and Texture Synthesis

2 code implementations10 Nov 2020 Jianhui Chang, Zhenghui Zhao, Chuanmin Jia, Shiqi Wang, Lingbo Yang, Qi Mao, Jian Zhang, Siwei Ma

To this end, we propose a novel conceptual compression framework that encodes visual data into compact structure and texture representations, then decodes in a deep synthesis fashion, aiming to achieve better visual reconstruction quality, flexible content manipulation, and potential support for various vision tasks.

Texture Synthesis

Multi-layer Feature Aggregation for Deep Scene Parsing Models

no code implementations4 Nov 2020 Litao Yu, Yongsheng Gao, Jun Zhou, Jian Zhang, Qiang Wu

The proposed module can auto-select the intermediate visual features to correlate the spatial and semantic information.

Scene Parsing Semantic Segmentation

Parameter Efficient Deep Neural Networks with Bilinear Projections

1 code implementation3 Nov 2020 Litao Yu, Yongsheng Gao, Jun Zhou, Jian Zhang

Recent research on deep neural networks (DNNs) has primarily focused on improving the model accuracy.

Distribution-aware Margin Calibration for Medical Image Segmentation

no code implementations3 Nov 2020 Zhibin Li, Litao Yu, Jian Zhang

In this paper, we present a novel data-distribution-aware margin calibration method for a better generalization of the mIoU over the whole data-distribution, underpinned by a rigid lower bound.

Image Segmentation Medical Image Segmentation +1

Dual Attention on Pyramid Feature Maps for Image Captioning

no code implementations2 Nov 2020 Litao Yu, Jian Zhang, Qiang Wu

In this paper, we propose to apply dual attention on pyramid image feature maps to fully explore the visual-semantic correlations and improve the quality of generated sentences.

Descriptive Image Captioning

AutoBSS: An Efficient Algorithm for Block Stacking Style Search

no code implementations NeurIPS 2020 Yikang Zhang, Jian Zhang, Zhao Zhong

Neural network architecture design mostly focuses on the new convolutional operator or special topological structure of network block, little attention is drawn to the configuration of stacking each block, called Block Stacking Style (BSS).

AutoML Bayesian Optimization +6

Identification of deep breath while moving forward based on multiple body regions and graph signal analysis

no code implementations20 Oct 2020 Yunlu Wang, Cheng Yang, Menghan Hu, Jian Zhang, Qingli Li, Guangtao Zhai, Xiao-Ping Zhang

This paper presents an unobtrusive solution that can automatically identify deep breath when a person is walking past the global depth camera.

Revisiting BFloat16 Training

no code implementations13 Oct 2020 Pedram Zamirai, Jian Zhang, Christopher R. Aberger, Christopher De Sa

State-of-the-art generic low-precision training algorithms use a mix of 16-bit and 32-bit precision, creating the folklore that 16-bit hardware compute units alone are not enough to maximize model accuracy.

Face Mask Assistant: Detection of Face Mask Service Stage Based on Mobile Phone

no code implementations9 Oct 2020 Yuzhen Chen, Menghan Hu, Chunjun Hua, Guangtao Zhai, Jian Zhang, Qingli Li, Simon X. Yang

Aimed at solving the problem that we don't know which service stage of the mask belongs to, we propose a detection system based on the mobile phone.

ASDN: A Deep Convolutional Network for Arbitrary Scale Image Super-Resolution

1 code implementation6 Oct 2020 Jialiang Shen, Yucheng Wang, Jian Zhang

For SR of small-scales (between 1 and 2), images are constructed by interpolation from a sparse set of precalculated Laplacian pyramid levels.

Image Super-Resolution

Implicit Multidimensional Projection of Local Subspaces

1 code implementation7 Sep 2020 Rongzheng Bian, Yumeng Xue, Liang Zhou, Jian Zhang, Baoquan Chen, Daniel Weiskopf, Yunhai Wang

We propose a visualization method to understand the effect of multidimensional projection on local subspaces, using implicit function differentiation.

Scalar Coupling Constant Prediction Using Graph Embedding Local Attention Encoder

no code implementations7 Sep 2020 Caiqing Jian, Xinyu Cheng, Jian Zhang, Lihui Wang

The experimental results demonstrate that, compared to the traditional chemical bond structure representations, the rotation and translation invariant structure representations proposed in this work can improve the SCC prediction accuracy; with the graph embedded local self-attention, the mean absolute error (MAE) of the prediction model in the validation set decreases from 0. 1603 Hz to 0. 1067 Hz; using the classification based loss function instead of the scaled regression loss, the MAE of the predicted SCC can be decreased to 0. 0963 HZ, which is close to the quantum chemistry standard on CHAMPS dataset.

Graph Embedding

Salvage Reusable Samples from Noisy Data for Robust Learning

1 code implementation6 Aug 2020 Zeren Sun, Xian-Sheng Hua, Yazhou Yao, Xiu-Shen Wei, Guosheng Hu, Jian Zhang

To this end, we propose a certainty-based reusable sample selection and correction approach, termed as CRSSC, for coping with label noise in training deep FG models with web images.


Hardware Accelerator for Adversarial Attacks on Deep Learning Neural Networks

no code implementations3 Aug 2020 Haoqiang Guo, Lu Peng, Jian Zhang, Fang Qi, Lide Duan

Recent studies identify that Deep learning Neural Networks (DNNs) are vulnerable to subtle perturbations, which are not perceptible to human visual system but can fool the DNN models and lead to wrong outputs.

Adversarial Attack

MACD R-CNN: An Abnormal Cell Nucleus Detection Method

no code implementations28 Jul 2020 Baoyan Ma, Jian Zhang, Feng Cao, Yongjun He

We design a fixed proposal module to generate fixed-sized feature maps of nuclei, which allows the new information of nucleus is used for classification.

Cell Detection Classification +4

A Similarity Inference Metric for RGB-Infrared Cross-Modality Person Re-identification

no code implementations3 Jul 2020 Mengxi Jia, Yunpeng Zhai, Shijian Lu, Siwei Ma, Jian Zhang

RGB-Infrared (IR) cross-modality person re-identification (re-ID), which aims to search an IR image in RGB gallery or vice versa, is a challenging task due to the large discrepancy between IR and RGB modalities.

Cross-Modality Person Re-identification Person Re-Identification

Stochastic Batch Augmentation with An Effective Distilled Dynamic Soft Label Regularizer

no code implementations27 Jun 2020 Qian Li, Qingyuan Hu, Yong Qi, Saiyu Qi, Jie Ma, Jian Zhang

SBA stochastically decides whether to augment at iterations controlled by the batch scheduler and in which a ''distilled'' dynamic soft label regularization is introduced by incorporating the similarity in the vicinity distribution respect to raw samples.

Data Augmentation

Understanding Graph Neural Networks from Graph Signal Denoising Perspectives

1 code implementation8 Jun 2020 Guoji Fu, Yifan Hou, Jian Zhang, Kaili Ma, Barakeel Fanseu Kamhoua, James Cheng

This paper aims to provide a theoretical framework to understand GNNs, specifically, spectral graph convolutional networks and graph attention networks, from graph signal denoising perspectives.

Denoising Graph Attention +2

TOAN: Target-Oriented Alignment Network for Fine-Grained Image Categorization with Few Labeled Samples

no code implementations28 May 2020 Huaxi Huang, Jun-Jie Zhang, Jian Zhang, Qiang Wu, Chang Xu

The challenges of high intra-class variance yet low inter-class fluctuations in fine-grained visual categorization are more severe with few labeled samples, \textit{i. e.,} Fine-Grained categorization problems under the Few-Shot setting (FGFS).

Fine-Grained Visual Categorization

Iterative Network for Image Super-Resolution

1 code implementation20 May 2020 Yuqing Liu, Shiqi Wang, Jian Zhang, Shanshe Wang, Siwei Ma, Wen Gao

A novel iterative super-resolution network (ISRN) is proposed on top of the iterative optimization.

Image Super-Resolution SSIM

Contextual Embeddings: When Are They Worth It?

no code implementations ACL 2020 Simran Arora, Avner May, Jian Zhang, Christopher Ré

We study the settings for which deep contextual embeddings (e. g., BERT) give large improvements in performance relative to classic pretrained embeddings (e. g., GloVe), and an even simpler baseline---random word embeddings---focusing on the impact of the training set size and the linguistic properties of the task.

Word Embeddings

Towards Better Graph Representation: Two-Branch Collaborative Graph Neural Networks for Multimodal Marketing Intention Detection

no code implementations13 May 2020 Lu Zhang, Jian Zhang, Zhibin Li, Jingsong Xu

Inspired by the fact that spreading and collecting information through the Internet becomes the norm, more and more people choose to post for-profit contents (images and texts) in social networks.

Graph Classification Marketing

Feature-metric Registration: A Fast Semi-supervised Approach for Robust Point Cloud Registration without Correspondences

1 code implementation CVPR 2020 Xiaoshui Huang, Guofeng Mei, Jian Zhang

We present a fast feature-metric point cloud registration framework, which enforces the optimisation of registration by minimising a feature-metric projection error without correspondences.

Point Cloud Registration

DyNet: Dynamic Convolution for Accelerating Convolutional Neural Networks

no code implementations22 Apr 2020 Yikang Zhang, Jian Zhang, Qiang Wang, Zhao Zhong

On one hand, we can reduce the computation cost remarkably while maintaining the performance.

GID-Net: Detecting Human-Object Interaction with Global and Instance Dependency

no code implementations11 Mar 2020 Dongming Yang, Yuexian Zou, Jian Zhang, Ge Li

GID block breaks through the local neighborhoods and captures long-range dependency of pixels both in global-level and instance-level from the scene to help detecting interactions between instances.

Human-Object Interaction Detection

Understanding the Downstream Instability of Word Embeddings

1 code implementation29 Feb 2020 Megan Leszczynski, Avner May, Jian Zhang, Sen Wu, Christopher R. Aberger, Christopher Ré

To theoretically explain this tradeoff, we introduce a new measure of embedding instability---the eigenspace instability measure---which we prove bounds the disagreement in downstream predictions introduced by the change in word embeddings.

Word Embeddings

Multi-factorial Optimization for Large-scale Virtual Machine Placement in Cloud Computing

no code implementations18 Jan 2020 Zhengping Liang, Jian Zhang, Liang Feng, Zexuan Zhu

However, as growing demand for cloud services, the existing EAs fail to implement in large-scale virtual machine placement (LVMP) problem due to the high time complexity and poor scalability.

Cloud Computing Evolutionary Algorithms

PMC-GANs: Generating Multi-Scale High-Quality Pedestrian with Multimodal Cascaded GANs

no code implementations30 Dec 2019 Jie Wu, Ying Peng, Chenghao Zheng, Zongbo Hao, Jian Zhang

Recently, generative adversarial networks (GANs) have shown great advantages in synthesizing images, leading to a boost of explorations of using faked images to augment data.

Data Augmentation Pedestrian Detection

Adversarial AutoAugment

no code implementations ICLR 2020 Xin-Yu Zhang, Qiang Wang, Jian Zhang, Zhao Zhong

The augmentation policy network attempts to increase the training loss of a target network through generating adversarial augmentation policies, while the target network can learn more robust features from harder examples to improve the generalization.

Data Augmentation Image Classification

Potential Passenger Flow Prediction: A Novel Study for Urban Transportation Development

no code implementations7 Dec 2019 Yongshun Gong, Zhibin Li, Jian Zhang, Wei Liu, Jin-Feng Yi

In this paper, this specific problem is termed as potential passenger flow (PPF) prediction, which is a novel and important study connected with urban computing and intelligent transportation systems.

MULTI-VIEW LEARNING Recommendation Systems

Adversarial Domain Adaptation with Domain Mixup

1 code implementation4 Dec 2019 Minghao Xu, Jian Zhang, Bingbing Ni, Teng Li, Chengjie Wang, Qi Tian, Wenjun Zhang

In this paper, we present adversarial domain adaptation with domain mixup (DM-ADA), which guarantees domain-invariance in a more continuous latent space and guides the domain discriminator in judging samples' difference relative to source and target domains.

Domain Adaptation

Time-aware Gradient Attack on Dynamic Network Link Prediction

no code implementations24 Nov 2019 Jinyin Chen, Jian Zhang, Zhi Chen, Min Du, Qi Xuan

In this work, we present the first study of adversarial attack on dynamic network link prediction (DNLP).

Adversarial Attack Link Prediction +1

Worst Cases Policy Gradients

no code implementations9 Nov 2019 Yichuan Charlie Tang, Jian Zhang, Ruslan Salakhutdinov

Recent advances in deep reinforcement learning have demonstrated the capability of learning complex control policies from many types of environments.

reinforcement-learning Reinforcement Learning (RL)

Max-min Fairness of K-user Cooperative Rate-Splitting in MISO Broadcast Channel with User Relaying

no code implementations17 Oct 2019 Yijie Mao, Bruno Clerckx, Jian Zhang, Victor O. K. Li, Mohammed Arafah

Cooperative Rate-Splitting (CRS) strategy, relying on linearly precoded rate-splitting at the transmitter and opportunistic transmission of the common message by the relaying user, has recently been shown to outperform typical Non-cooperative Rate-Splitting (NRS), Cooperative Non-Orthogonal Multiple Access (C-NOMA) and Space Division Multiple Access (SDMA) in a two-user Multiple Input Single Output (MISO) Broadcast Channel (BC) with user relaying.

Fairness Scheduling

PipeMare: Asynchronous Pipeline Parallel DNN Training

no code implementations9 Oct 2019 Bowen Yang, Jian Zhang, Jonathan Li, Christopher Ré, Christopher R. Aberger, Christopher De Sa

Pipeline parallelism (PP) when training neural networks enables larger models to be partitioned spatially, leading to both lower network communication and overall higher hardware utilization.

DyNet: Dynamic Convolution for Accelerating Convolution Neural Networks

no code implementations25 Sep 2019 Kane Zhang, Jian Zhang, Qiang Wang, Zhao Zhong

To verify the scalability, we also apply DyNet on segmentation task, the results show that DyNet can reduces 69. 3% FLOPs while maintaining the Mean IoU on segmentation task.

On the Downstream Performance of Compressed Word Embeddings

1 code implementation NeurIPS 2019 Avner May, Jian Zhang, Tri Dao, Christopher Ré

Finally, we show that by using the eigenspace overlap score as a selection criterion between embeddings drawn from a representative set we compressed, we can efficiently identify the better performing embedding with up to $2\times$ lower selection error rates than the next best measure of compression quality, and avoid the cost of training a model for each task of interest.

Generalization Bounds Quantization +1