Search Results for author: Xinbo Gao

Found 147 papers, 45 papers with code

Meta Invariance Defense Towards Generalizable Robustness to Unknown Adversarial Attacks

no code implementations4 Apr 2024 Lei Zhang, YuHang Zhou, Yi Yang, Xinbo Gao

Despite providing high-performance solutions for computer vision tasks, the deep neural network (DNN) model has been proved to be extremely vulnerable to adversarial attacks.

Adversarial Defense Adversarial Robustness +1

InstructBrush: Learning Attention-based Instruction Optimization for Image Editing

no code implementations27 Mar 2024 Ruoyu Zhao, Qingnan Fan, Fei Kou, Shuai Qin, Hong Gu, Wei Wu, Pengcheng Xu, Mingrui Zhu, Nannan Wang, Xinbo Gao

Two key techniques are introduced into InstructBrush, Attention-based Instruction Optimization and Transformation-oriented Instruction Initialization, to address the limitations of the previous method in terms of inversion effects and instruction generalization.

Semi-Supervised Learning for Anomaly Traffic Detection via Bidirectional Normalizing Flows

1 code implementation13 Mar 2024 Zhangxuan Dang, Yu Zheng, Xinglin Lin, Chunlei Peng, Qiuyu Chen, Xinbo Gao

We consider the problem of anomaly network traffic detection and propose a three-stage anomaly detection framework using only normal traffic.

Anomaly Detection Benchmarking

Are Dense Labels Always Necessary for 3D Object Detection from Point Cloud?

no code implementations5 Mar 2024 Chenqiang Gao, Chuandong Liu, Jun Shu, Fangcen Liu, Jiang Liu, Luyu Yang, Xinbo Gao, Deyu Meng

Current state-of-the-art (SOTA) 3D object detection methods often require a large amount of 3D bounding box annotations for training.

3D Object Detection object-detection +1

DAMSDet: Dynamic Adaptive Multispectral Detection Transformer with Competitive Query Selection and Adaptive Feature Fusion

no code implementations1 Mar 2024 Junjie Guo, Chenqiang Gao, Fangcen Liu, Deyu Meng, Xinbo Gao

To effectively mine the complementary information and adapt to misalignment situations, we propose a Multispectral Deformable Cross-attention module to adaptively sample and aggregate multi-semantic level features of infrared and visible images for each object.

Object object-detection +1

Diffusion Model Based Visual Compensation Guidance and Visual Difference Analysis for No-Reference Image Quality Assessment

no code implementations22 Feb 2024 Zhaoyang Wang, Bo Hu, Mingyang Zhang, Jie Li, Leida Li, Maoguo Gong, Xinbo Gao

Firstly, we devise a new diffusion restoration network that leverages the produced enhanced image and noise-containing images, incorporating nonlinear features obtained during the denoising process of the diffusion model, as high-level visual information.

Denoising No-Reference Image Quality Assessment +1

Jailbreaking Attack against Multimodal Large Language Model

1 code implementation4 Feb 2024 Zhenxing Niu, Haodong Ren, Xinbo Gao, Gang Hua, Rong Jin

This paper focuses on jailbreaking attacks against multi-modal large language models (MLLMs), seeking to elicit MLLMs to generate objectionable responses to harmful user queries.

Language Modelling Large Language Model

Exploring Homogeneous and Heterogeneous Consistent Label Associations for Unsupervised Visible-Infrared Person ReID

no code implementations1 Feb 2024 Lingfeng He, De Cheng, Nannan Wang, Xinbo Gao

In response, we introduce a Modality-Unified Label Transfer (MULT) module that simultaneously accounts for both homogeneous and heterogeneous fine-grained instance-level structures, yielding high-quality cross-modality label associations.

Person Re-Identification Pseudo Label +1

Bridging Generative and Discriminative Models for Unified Visual Perception with Diffusion Priors

no code implementations29 Jan 2024 Shiyin Dong, Mingrui Zhu, Kun Cheng, Nannan Wang, Xinbo Gao

Our purpose is to establish a unified visual perception framework, capitalizing on the potential synergies between generative and discriminative models.

Image Generation Open Vocabulary Semantic Segmentation +2

Masked Attribute Description Embedding for Cloth-Changing Person Re-identification

1 code implementation11 Jan 2024 Chunlei Peng, Boyu Wang, Decheng Liu, Nannan Wang, Ruimin Hu, Xinbo Gao

To address this, we mask the clothing and color information in the personal attribute description extracted through an attribute detection model.

Attribute Cloth-Changing Person Re-Identification

EmMixformer: Mix transformer for eye movement recognition

no code implementations10 Jan 2024 Huafeng Qin, Hongyu Zhu, Xin Jin, Qun Song, Mounim A. El-Yacoubi, Xinbo Gao

To this end, we propose a mixed block consisting of three modules, transformer, attention Long short-term memory (attention LSTM), and Fourier transformer.

Point Deformable Network with Enhanced Normal Embedding for Point Cloud Analysis

no code implementations20 Dec 2023 Xingyilang Yin, Xi Yang, Liangchen Liu, Nannan Wang, Xinbo Gao

Additional offsets and modulation scalars are learned on the whole point features, which shift the deformable reference points to the regions of interest.

Adversarial AutoMixup

2 code implementations19 Dec 2023 Huafeng Qin, Xin Jin, Yun Jiang, Mounim A. El-Yacoubi, Xinbo Gao

In this paper, we propose AdAutomixup, an adversarial automatic mixup augmentation approach that generates challenging samples to train a robust classifier for image classification, by alternatively optimizing the classifier and the mixup sample generator.

Classification Image Classification

Adv-Diffusion: Imperceptible Adversarial Face Identity Attack via Latent Diffusion Model

1 code implementation18 Dec 2023 Decheng Liu, Xijun Wang, Chunlei Peng, Nannan Wang, Ruiming Hu, Xinbo Gao

Adversarial attacks involve adding perturbations to the source image to cause misclassification by the target model, which demonstrates the potential of attacking face recognition models.

Image Generation

A Dual Domain Multi-exposure Image Fusion Network based on the Spatial-Frequency Integration

1 code implementation17 Dec 2023 Guang Yang, Jie Li, Xinbo Gao

Specifically, we introduce a Spatial-Frequency Fusion Block to facilitate efficient interaction between dual domains and capture complementary information from input images with different exposures.

Multi-Exposure Image Fusion

Symmetrical Bidirectional Knowledge Alignment for Zero-Shot Sketch-Based Image Retrieval

1 code implementation16 Dec 2023 Decheng Liu, Xu Luo, Chunlei Peng, Nannan Wang, Ruimin Hu, Xinbo Gao

In this paper, we propose a novel Symmetrical Bidirectional Knowledge Alignment for zero-shot sketch-based image retrieval (SBKA).

Knowledge Distillation Retrieval +1

Multi-Scene Generalized Trajectory Global Graph Solver with Composite Nodes for Multiple Object Tracking

no code implementations14 Dec 2023 Yan Gao, Haojun Xu, Nannan Wang, Jie Li, Xinbo Gao

In addition to the previous method of treating objects as nodes, the network innovatively treats object trajectories as nodes for information interaction, improving the graph neural network's feature representation capability.

Multi-Object Tracking Multiple Object Tracking +1

A Multi-scale Information Integration Framework for Infrared and Visible Image Fusion

1 code implementation7 Dec 2023 Guang Yang, Jie Li, Hanxiao Lei, Xinbo Gao

In this study, we propose a multi-scale dual attention (MDA) framework for infrared and visible image fusion, which is designed to measure and integrate complementary information in both structure and loss function at the image and patch level.

Infrared And Visible Image Fusion

DeepFidelity: Perceptual Forgery Fidelity Assessment for Deepfake Detection

2 code implementations7 Dec 2023 Chunlei Peng, Huiqing Guo, Decheng Liu, Nannan Wang, Ruimin Hu, Xinbo Gao

Considering the complexity of the quality distribution of both real and fake faces, we propose a novel Deepfake detection framework named DeepFidelity to adaptively distinguish real and fake faces with varying image quality by mining the perceptual forgery fidelity of face images.

DeepFake Detection Face Swapping

EtC: Temporal Boundary Expand then Clarify for Weakly Supervised Video Grounding with Multimodal Large Language Model

no code implementations5 Dec 2023 Guozhang Li, Xinpeng Ding, De Cheng, Jie Li, Nannan Wang, Xinbo Gao

To further clarify the noise of expanded boundaries, we combine mutual learning with a tailored proposal-level contrastive objective to use a learnable approach to harmonize a balance between incomplete yet clean (initial) and comprehensive yet noisy (expanded) boundaries for more precise ones.

Boundary Detection Language Modelling +2

CatVersion: Concatenating Embeddings for Diffusion-Based Text-to-Image Personalization

no code implementations24 Nov 2023 Ruoyu Zhao, Mingrui Zhu, Shiyin Dong, Nannan Wang, Xinbo Gao

We propose CatVersion, an inversion-based method that learns the personalized concept through a handful of examples.

Image Generation

HFORD: High-Fidelity and Occlusion-Robust De-identification for Face Privacy Protection

no code implementations15 Nov 2023 Dongxin Chen, Mingrui Zhu, Nannan Wang, Xinbo Gao

To disentangle the latent codes in the GAN inversion space, we introduce an Identity Disentanglement Module (IDM).

Attribute De-identification +1

Shape-centered Representation Learning for Visible-Infrared Person Re-identification

no code implementations27 Oct 2023 Shuang Li, Jiaxu Leng, Ji Gan, Mengjingcheng Mo, Xinbo Gao

One pertains to the dependence on auxiliary models for shape feature extraction in the inference phase, along with the errors in generated infrared shapes due to the intrinsic modality disparity.

Person Re-Identification Representation Learning

Gradient constrained sharpness-aware prompt learning for vision-language models

no code implementations14 Sep 2023 Liangchen Liu, Nannan Wang, Dawei Zhou, Xinbo Gao, Decheng Liu, Xi Yang, Tongliang Liu

This paper targets a novel trade-off problem in generalizable prompt learning for vision-language models (VLM), i. e., improving the performance on unseen classes while maintaining the performance on seen classes.

Diff-Privacy: Diffusion-based Face Privacy Protection

no code implementations11 Sep 2023 Xiao He, Mingrui Zhu, Dongxin Chen, Nannan Wang, Xinbo Gao

In this paper, we unify the task of anonymization and visual identity information hiding and propose a novel face privacy protection method based on diffusion models, dubbed Diff-Privacy.

Denoising Scheduling

Hierarchical Point-based Active Learning for Semi-supervised Point Cloud Semantic Segmentation

1 code implementation ICCV 2023 Zongyi Xu, Bo Yuan, Shanshan Zhao, Qianni Zhang, Xinbo Gao

The most recent methods of this kind measure the uncertainty of each pre-divided region for manual labelling but they suffer from redundant information and require additional efforts for region division.

Active Learning Point Cloud Segmentation +2

ESSAformer: Efficient Transformer for Hyperspectral Image Super-resolution

1 code implementation ICCV 2023 Mingjin Zhang, Chi Zhang, Qiming Zhang, Jie Guo, Xinbo Gao, Jing Zhang

Single hyperspectral image super-resolution (single-HSI-SR) aims to restore a high-resolution hyperspectral image from a low-resolution observation.

Hyperspectral Image Super-Resolution Image Super-Resolution

Attention Consistency Refined Masked Frequency Forgery Representation for Generalizing Face Forgery Detection

1 code implementation21 Jul 2023 Decheng Liu, Tao Chen, Chunlei Peng, Nannan Wang, Ruimin Hu, Xinbo Gao

Due to the successful development of deep image generation technology, visual data forgery detection would play a more important role in social and economic security.

Image Generation

PRO-Face S: Privacy-preserving Reversible Obfuscation of Face Images via Secure Flow

no code implementations18 Jul 2023 Lin Yuan, Kai Liang, Xiao Pu, Yan Zhang, Jiaxu Leng, Tao Wu, Nannan Wang, Xinbo Gao

This paper proposes a novel paradigm for facial privacy protection that unifies multiple characteristics including anonymity, diversity, reversibility and security within a single lightweight framework.

Privacy Preserving

MMNet: Multi-Collaboration and Multi-Supervision Network for Sequential Deepfake Detection

no code implementations6 Jul 2023 Ruiyang Xia, Decheng Liu, Jie Li, Lin Yuan, Nannan Wang, Xinbo Gao

Advanced manipulation techniques have provided criminals with opportunities to make social panic or gain illicit profits through the generation of deceptive media, such as forged face images.

DeepFake Detection Face Swapping

SAR-to-Optical Image Translation via Thermodynamics-inspired Network

no code implementations23 May 2023 Mingjin Zhang, Jiamin Xu, Chengyu He, Wenteng Shang, Yunsong Li, Xinbo Gao

Synthetic aperture radar (SAR) is prevalent in the remote sensing field but is difficult to interpret in human visual perception.

Translation

Efficient Bilateral Cross-Modality Cluster Matching for Unsupervised Visible-Infrared Person ReID

no code implementations22 May 2023 De Cheng, Lingfeng He, Nannan Wang, Shizhou Zhang, Zhen Wang, Xinbo Gao

To this end, we propose a novel bilateral cluster matching-based learning framework to reduce the modality gap by matching cross-modality clusters.

Contrastive Learning Person Re-Identification

Unsupervised Visible-Infrared Person ReID by Collaborative Learning with Neighbor-Guided Label Refinement

no code implementations22 May 2023 De Cheng, Xiaojian Huang, Nannan Wang, Lingfeng He, Zhihui Li, Xinbo Gao

Unsupervised learning visible-infrared person re-identification (USL-VI-ReID) aims at learning modality-invariant features from unlabeled cross-modality dataset, which is crucial for practical applications in video surveillance systems.

Person Re-Identification

Language Knowledge-Assisted Representation Learning for Skeleton-Based Action Recognition

1 code implementation21 May 2023 Haojun Xu, Yan Gao, Zheng Hui, Jie Li, Xinbo Gao

Also, humans have brain regions dedicated to understanding the minds of others and analyzing their intentions, such as the medial prefrontal cortex of the temporal lobe.

Ranked #2 on Skeleton Based Action Recognition on NTU RGB+D 120 (using extra training data)

Action Recognition GPR +2

Selecting Learnable Training Samples is All DETRs Need in Crowded Pedestrian Detection

no code implementations18 May 2023 Feng Gao, Jiaxu Leng, Gan Ji, Xinbo Gao

However, in crowded pedestrian detection, the performance of DETRs is still unsatisfactory due to the inappropriate sample selection method which results in more false positives.

object-detection Object Detection +1

Rethinking k-means from manifold learning perspective

no code implementations12 May 2023 Quanxue Gao, Qianqian Wang, Han Lu, Wei Xia, Xinbo Gao

Although numerous clustering algorithms have been developed, many existing methods still leverage k-means technique to detect clusters of data points.

Clustering

Adapt and Align to Improve Zero-Shot Sketch-Based Image Retrieval

no code implementations9 May 2023 Shiyin Dong, Mingrui Zhu, Nannan Wang, Xinbo Gao

Zero-shot sketch-based image retrieval (ZS-SBIR) is challenging due to the cross-domain nature of sketches and photos, as well as the semantic gap between seen and unseen image distributions.

Retrieval Sketch-Based Image Retrieval +1

Boosting Weakly-Supervised Temporal Action Localization with Text Information

1 code implementation CVPR 2023 Guozhang Li, De Cheng, Xinpeng Ding, Nannan Wang, Xiaoyu Wang, Xinbo Gao

For the discriminative objective, we propose a Text-Segment Mining (TSM) mechanism, which constructs a text description based on the action class label, and regards the text as the query to mine all class-related segments.

Sentence Weakly-supervised Temporal Action Localization +1

Weakly-Supervised Temporal Action Localization with Bidirectional Semantic Consistency Constraint

1 code implementation25 Apr 2023 Guozhang Li, De Cheng, Xinpeng Ding, Nannan Wang, Jie Li, Xinbo Gao

The proposed Bi-SCC firstly adopts a temporal context augmentation to generate an augmented video that breaks the correlation between positive actions and their co-scene actions in the inter-video; Then, a semantic consistency constraint (SCC) is used to enforce the predictions of the original video and augmented video to be consistent, hence suppressing the co-scene actions.

Weakly-supervised Temporal Action Localization Weakly Supervised Temporal Action Localization

SAWU-Net: Spatial Attention Weighted Unmixing Network for Hyperspectral Images

no code implementations22 Apr 2023 Lin Qi, Xuewen Qin, Feng Gao, Junyu Dong, Xinbo Gao

To this end, we put forward a spatial attention weighted unmixing network, dubbed as SAWU-Net, which learns a spatial attention network and a weighted unmixing network in an end-to-end manner for better spatial feature exploitation.

Hyperspectral Unmixing

Granular-ball computing: an efficient, robust, and interpretable adaptive multi-granularity representation and computation method

no code implementations21 Apr 2023 Shuyin Xia, Guoyin Wang, Xinbo Gao, Xiaoyu Lian

This mechanism inherently possesses an adaptive multi-granularity description capacity, resulting in computational traits such as efficiency, robustness, and interpretability.

Multi-View Clustering via Semi-non-negative Tensor Factorization

no code implementations29 Mar 2023 Jing Li, Quanxue Gao, Qianqian Wang, Wei Xia, Xinbo Gao

Multi-view clustering (MVC) based on non-negative matrix factorization (NMF) and its variants have received a huge amount of attention in recent years due to their advantages in clustering interpretability.

Clustering

GBMST: An Efficient Minimum Spanning Tree Clustering Based on Granular-Ball Computing

no code implementations2 Mar 2023 Jiang Xie, Shuyin Xia, Guoyin Wang, Xinbo Gao

We construct coarsegrained granular-balls, and then use granular-balls and MST to implement the clustering method based on "large-scale priority", which can greatly avoid the influence of outliers and accelerate the construction process of MST.

Clustering

Few-shot Font Generation by Learning Style Difference and Similarity

no code implementations24 Jan 2023 Xiao He, Mingrui Zhu, Nannan Wang, Xinbo Gao, Heng Yang

To address this issue, we propose a novel font generation approach by learning the Difference between different styles and the Similarity of the same style (DS-Font).

Contrastive Learning Font Generation

DLBD: A Self-Supervised Direct-Learned Binary Descriptor

1 code implementation CVPR 2023 Bin Xiao, Yang Hu, Bo Liu, Xiuli Bi, Weisheng Li, Xinbo Gao

Since their binarization processes are not a component of the network, the learning-based binary descriptor cannot fully utilize the advances of deep learning.

Binarization Image Retrieval +1

MCF: Mutual Correction Framework for Semi-Supervised Medical Image Segmentation

1 code implementation CVPR 2023 Yongchao Wang, Bin Xiao, Xiuli Bi, Weisheng Li, Xinbo Gao

Inspired by the plain contrast idea, MCF introduces two different subnets to explore and utilize the discrepancies between subnets to correct cognitive bias of the model.

Image Segmentation Pseudo Label +3

Multi-adversarial Faster-RCNN with Paradigm Teacher for Unrestricted Object Detection

no code implementations International Journal of Computer Vision 2022 Zhenwei He, Lei Zhang, Xinbo Gao, David Zhang

Our proposed MAF has two distinct contributions: (1) The Hierarchical Domain Feature Alignment (HDFA) module is introduced to minimize the image-level domain disparity, where Scale Reduction Module (SRM) reduces the feature map size without information loss and increases the training efficiency.

Domain Adaptation Knowledge Distillation +2

All-to-key Attention for Arbitrary Style Transfer

no code implementations ICCV 2023 Mingrui Zhu, Xiao He, Nannan Wang, Xiaoyu Wang, Xinbo Gao

In this paper, we propose a novel all-to-key attention mechanism -- each position of content features is matched to stable key positions of style features -- that is more in line with the characteristics of style transfer.

Position Style Transfer

Neighbour Consistency Guided Pseudo-Label Refinement for Unsupervised Person Re-Identification

no code implementations30 Nov 2022 De Cheng, Haichun Tai, Nannan Wang, Zhen Wang, Xinbo Gao

In this paper, we propose a Neighbour Consistency guided Pseudo Label Refinement (NCPLR) framework, which can be regarded as a transductive form of label propagation under the assumption that the prediction of each example should be similar to its nearest neighbours'.

Clustering Person Retrieval +3

Class-Dependent Label-Noise Learning with Cycle-Consistency Regularization Feature Space

1 code implementation NIPS 2022 De Cheng, Yixiong Ning, Nannan Wang, Xinbo Gao, Heng Yang, Yuxuan Du, Bo Han, Tongliang Liu

We show that the cycle-consistency regularization helps to minimize the volume of the transition matrix T indirectly without exploiting the estimated noisy class posterior, which could further encourage the estimated transition matrix T to converge to its optimal solution.

Contextual Learning in Fourier Complex Field for VHR Remote Sensing Images

1 code implementation28 Oct 2022 Yan Zhang, Xiyuan Gao, Qingyan Duan, Jiaxu Leng, Xiao Pu, Xinbo Gao

By stacking various layers of CSA blocks, we propose the Fourier Complex Transformer (FCT) model to learn global contextual information from VHR aerial images following the hierarchical manners.

Classification Image Classification

Granular-Ball Fuzzy Set and Its Implementation in SVM

no code implementations21 Oct 2022 Shuyin Xia, Xiaoyu Lian, Guoyin Wang, Xinbo Gao, Yabin Shao

Most existing fuzzy set methods use points as their input, which is the finest granularity from the perspective of granular computing.

FedForgery: Generalized Face Forgery Detection with Residual Federated Learning

1 code implementation18 Oct 2022 Decheng Liu, Zhan Dang, Chunlei Peng, Yu Zheng, Shuang Li, Nannan Wang, Xinbo Gao

Experiments conducted on publicly available face forgery detection datasets prove the superior performance of the proposed FedForgery.

Federated Learning Image Generation

GBSVM: Granular-ball Support Vector Machine

1 code implementation6 Oct 2022 Shuyin Xia, Xiaoyu Lian, Guoyin Wang, Xinbo Gao, Jiancu Chen, Xiaoli Peng

Furthermore, a particle swarm optimization algorithm is designed to solve the dual model.

Hiding Visual Information via Obfuscating Adversarial Perturbations

1 code implementation ICCV 2023 Zhigang Su, Dawei Zhou, Nannan Wangu, Decheng Li, Zhen Wang, Xinbo Gao

Growing leakage and misuse of visual information raise security and privacy concerns, which promotes the development of information protection.

Adversarial Attack De-identification +1

LKD-Net: Large Kernel Convolution Network for Single Image Dehazing

1 code implementation5 Sep 2022 Pinjun Luo, GuoQiang Xiao, Xinbo Gao, Song Wu

The designed DLKCB can split the deep-wise large kernel convolution into a smaller depth-wise convolution and a depth-wise dilated convolution without introducing massive parameters and computational overhead.

Image Dehazing Single Image Dehazing

Improving Adversarial Robustness via Mutual Information Estimation

1 code implementation25 Jul 2022 Dawei Zhou, Nannan Wang, Xinbo Gao, Bo Han, Xiaoyu Wang, Yibing Zhan, Tongliang Liu

To alleviate this negative effect, in this paper, we investigate the dependence between outputs of the target model and input adversarial samples from the perspective of information theory, and propose an adversarial defense method.

Adversarial Defense Adversarial Robustness +1

Seeking Subjectivity in Visual Emotion Distribution Learning

no code implementations25 Jul 2022 Jingyuan Yang, Jie Li, Leida Li, Xiumei Wang, Yuxuan Ding, Xinbo Gao

In psychology, the \textit{Object-Appraisal-Emotion} model has demonstrated that each individual's emotion is affected by his/her subjective appraisal, which is further formed by the affective memory.

Emotion Recognition

TransFA: Transformer-based Representation for Face Attribute Evaluation

1 code implementation12 Jul 2022 Decheng Liu, Weijie He, Chunlei Peng, Nannan Wang, Jie Li, Xinbo Gao

The multiple branches transformer is employed to explore the inter-correlation between different attributes in similar semantic regions for attribute feature learning.

Attribute Multi-Label Classification +1

Spatial-Temporal Frequency Forgery Clue for Video Forgery Detection in VIS and NIR Scenario

no code implementations5 Jul 2022 Yukai Wang, Chunlei Peng, Decheng Liu, Nannan Wang, Xinbo Gao

In recent years, with the rapid development of face editing and generation, more and more fake videos are circulating on social media, which has caused extreme public concerns.

Instance-Dependent Label-Noise Learning with Manifold-Regularized Transition Matrix Estimation

no code implementations CVPR 2022 De Cheng, Tongliang Liu, Yixiong Ning, Nannan Wang, Bo Han, Gang Niu, Xinbo Gao, Masashi Sugiyama

In label-noise learning, estimating the transition matrix has attracted more and more attention as the matrix plays an important role in building statistically consistent classifiers.

Two-Stream Graph Convolutional Network for Intra-oral Scanner Image Segmentation

1 code implementation19 Apr 2022 Yue Zhao, Lingming Zhang, Yang Liu, Deyu Meng, Zhiming Cui, Chenqiang Gao, Xinbo Gao, Chunfeng Lian, Dinggang Shen

The state-of-the-art deep learning-based methods often simply concatenate the raw geometric attributes (i. e., coordinates and normal vectors) of mesh cells to train a single-stream network for automatic intra-oral scanner image segmentation.

Graph Learning Image Segmentation +3

Robust Single Image Dehazing Based on Consistent and Contrast-Assisted Reconstruction

no code implementations29 Mar 2022 De Cheng, Yan Li, Dingwen Zhang, Nannan Wang, Xinbo Gao, Jiande Sun

To properly address this problem, we propose a novel density-variational learning framework to improve the robustness of the image dehzing model assisted by a variety of negative hazy images, to better deal with various complex hazy scenarios.

Image Dehazing Single Image Dehazing

Towards Semi-Supervised Deep Facial Expression Recognition with An Adaptive Confidence Margin

1 code implementation CVPR 2022 Hangyu Li, Nannan Wang, Xi Yang, Xiaoyu Wang, Xinbo Gao

In this paper, we learn an Adaptive Confidence Margin (Ada-CM) to fully leverage all unlabeled data for semi-supervised deep facial expression recognition.

Facial Expression Recognition Facial Expression Recognition (FER)

SSCU-Net: Spatial-Spectral Collaborative Unmixing Network for Hyperspectral Images

no code implementations12 Mar 2022 Lin Qi, Feng Gao, Junyu Dong, Xinbo Gao, Qian Du

Important findings on the use of spatial and spectral information in the autoencoder framework are discussed.

Hyperspectral Unmixing

Semi-parametric Makeup Transfer via Semantic-aware Correspondence

1 code implementation4 Mar 2022 Mingrui Zhu, Yun Yi, Nannan Wang, Xiaoyu Wang, Xinbo Gao

The large discrepancy between the source non-makeup image and the reference makeup image is one of the key challenges in makeup transfer.

An Efficient and Adaptive Granular-ball Generation Method in Classification Problem

no code implementations12 Jan 2022 Shuyin Xia, Xiaochuan Dai, Guoyin Wang, Xinbo Gao, Elisabeth Giem

In addition, this paper first provides the mathematical models for the granular-ball covering.

A Unified Granular-ball Learning Model of Pawlak Rough Set and Neighborhood Rough Set

no code implementations10 Jan 2022 Shuyin Xia, Cheng Wang, Guoyin Wang, Weiping Ding, Xinbo Gao, JianHang Yu, Yujia Zhai, Zizhong Chen

The granular-ball rough set can simultaneously represent Pawlak rough sets, and the neighborhood rough set, so as to realize the unified representation of the two.

feature selection

SS3D: Sparsely-Supervised 3D Object Detection From Point Cloud

no code implementations CVPR 2022 Chuandong Liu, Chenqiang Gao, Fangcen Liu, Jiang Liu, Deyu Meng, Xinbo Gao

In the meantime, we design a reliable background mining module and a point cloud filling data augmentation strategy to generate the confident data for iteratively learning with reliable supervision.

3D Object Detection Data Augmentation +2

An Efficient and Accurate Rough Set for Feature Selection, Classification and Knowledge Representation

no code implementations29 Dec 2021 Shuyin Xia, Xinyu Bai, Guoyin Wang, Deyu Meng, Xinbo Gao, Zizhong Chen, Elisabeth Giem

This paper present a strong data mining method based on rough set, which can realize feature selection, classification and knowledge representation at the same time.

Attribute feature selection

Image-specific Convolutional Kernel Modulation for Single Image Super-resolution

1 code implementation16 Nov 2021 Yuanfei Huang, Jie Li, Yanting Hu, Xinbo Gao, Hua Huang

Recently, deep-learning-based super-resolution methods have achieved excellent performances, but mainly focus on training a single generalized deep network by feeding numerous samples.

Image Super-Resolution

SOLVER: Scene-Object Interrelated Visual Emotion Reasoning Network

no code implementations24 Oct 2021 Jingyuan Yang, Xinbo Gao, Leida Li, Xiumei Wang, Jinshan Ding

Inspired by this, we propose a novel Scene-Object interreLated Visual Emotion Reasoning network (SOLVER) to predict emotions from images.

Emotion Recognition Object

Self-supervised Contrastive Attributed Graph Clustering

no code implementations15 Oct 2021 Wei Xia, Quanxue Gao, Ming Yang, Xinbo Gao

Thus, for the OOS nodes, SCAGC can directly calculate their clustering labels.

Attribute Clustering +3

Hybrid Dynamic Contrast and Probability Distillation for Unsupervised Person Re-Id

no code implementations29 Sep 2021 De Cheng, Jingyu Zhou, Nannan Wang, Xinbo Gao

However, since person Re-Id is an open-set problem, the clustering based methods often leave out lots of outlier instances or group the instances into the wrong clusters, thus they can not make full use of the training samples as a whole.

Clustering Contrastive Learning +3

Infrared Small-Dim Target Detection with Transformer under Complex Backgrounds

no code implementations29 Sep 2021 Fangcen Liu, Chenqiang Gao, Fang Chen, Deyu Meng, WangMeng Zuo, Xinbo Gao

We adopt the self-attention mechanism of the transformer to learn the interaction information of image features in a larger range.

Single Image Dehazing with An Independent Detail-Recovery Network

no code implementations22 Sep 2021 Yan Li, De Cheng, Jiande Sun, Dingwen Zhang, Nannan Wang, Xinbo Gao

In this paper, we propose a single image dehazing method with an independent Detail Recovery Network (DRN), which considers capturing the details from the input image over a separate network and then integrates them into a coarse dehazed image.

Image Dehazing Single Image Dehazing

Stimuli-Aware Visual Emotion Analysis

no code implementations4 Sep 2021 Jingyuan Yang, Jie Li, Xiumei Wang, Yuxuan Ding, Xinbo Gao

Then, we design three specific networks, i. e., Global-Net, Semantic-Net and Expression-Net, to extract distinct emotional features from different stimuli simultaneously.

Emotion Recognition

Support-Set Based Cross-Supervision for Video Grounding

no code implementations ICCV 2021 Xinpeng Ding, Nannan Wang, Shiwei Zhang, De Cheng, Xiaomeng Li, Ziyuan Huang, Mingqian Tang, Xinbo Gao

The contrastive objective aims to learn effective representations by contrastive learning, while the caption objective can train a powerful video encoder supervised by texts.

Contrastive Learning Video Grounding

Effective and Efficient Graph Learning for Multi-view Clustering

no code implementations15 Aug 2021 Quanxue Gao, Wei Xia, Xinbo Gao, Xiangdong Zhang, Qin Li, DaCheng Tao

Despite the impressive clustering performance and efficiency in characterizing both the relationship between data and cluster structure, existing graph-based multi-view clustering methods still have the following drawbacks.

Clustering Graph Learning

Multiple Graph Learning for Scalable Multi-view Clustering

no code implementations29 Jun 2021 Tianyu Jiang, Quanxue Gao, Xinbo Gao

Specifically, we construct a hidden and tractable large graph by anchor graph for each view and well exploit complementary information embedded in anchor graphs of different views by tensor Schatten p-norm regularizer.

Clustering graph construction +1

A Circular-Structured Representation for Visual Emotion Distribution Learning

no code implementations CVPR 2021 Jingyuan Yang, Jie Li, Leida Li, Xiumei Wang, Xinbo Gao

Visual Emotion Analysis (VEA) has attracted increasing attention recently with the prevalence of sharing images on social networks.

Emotion Recognition

TSGCNet: Discriminative Geometric Feature Learning With Two-Stream Graph Convolutional Network for 3D Dental Model Segmentation

no code implementations CVPR 2021 Lingming Zhang, Yue Zhao, Deyu Meng, Zhiming Cui, Chenqiang Gao, Xinbo Gao, Chunfeng Lian, Dinggang Shen

State-of-the-art methods directly concatenate the raw attributes of 3D inputs, namely coordinates and normal vectors of mesh cells, to train a single-stream network for fully-automated tooth segmentation.

Graph Learning

Learning the Non-Differentiable Optimization for Blind Super-Resolution

no code implementations CVPR 2021 Zheng Hui, Jie Li, Xiumei Wang, Xinbo Gao

Instead of considering iterative strategy, we make the blur kernel predictor trainable in the whole blind SR model, in which AMNet is well-trained.

Blind Super-Resolution Super-Resolution

Improving White-box Robustness of Pre-processing Defenses via Joint Adversarial Training

no code implementations10 Jun 2021 Dawei Zhou, Nannan Wang, Xinbo Gao, Bo Han, Jun Yu, Xiaoyu Wang, Tongliang Liu

However, pre-processing methods may suffer from the robustness degradation effect, in which the defense reduces rather than improving the adversarial robustness of a target model in a white-box setting.

Adversarial Defense Adversarial Robustness

Towards Defending against Adversarial Examples via Attack-Invariant Features

no code implementations9 Jun 2021 Dawei Zhou, Tongliang Liu, Bo Han, Nannan Wang, Chunlei Peng, Xinbo Gao

However, given the continuously evolving attacks, models trained on seen types of adversarial examples generally cannot generalize well to unseen types of adversarial examples.

Adversarial Robustness

Removing Adversarial Noise in Class Activation Feature Space

no code implementations ICCV 2021 Dawei Zhou, Nannan Wang, Chunlei Peng, Xinbo Gao, Xiaoyu Wang, Jun Yu, Tongliang Liu

Then, we train a denoising model to minimize the distances between the adversarial examples and the natural examples in the class activation feature space.

Adversarial Robustness Denoising

Drafting and Revision: Laplacian Pyramid Network for Fast High-Quality Artistic Style Transfer

2 code implementations CVPR 2021 Tianwei Lin, Zhuoqi Ma, Fu Li, Dongliang He, Xin Li, Errui Ding, Nannan Wang, Jie Li, Xinbo Gao

Inspired by the common painting process of drawing a draft and revising the details, we introduce a novel feed-forward method named Laplacian Pyramid Network (LapStyle).

Style Transfer

Transitional Learning: Exploring the Transition States of Degradation for Blind Super-resolution

1 code implementation29 Mar 2021 Yuanfei Huang, Jie Li, Yanting Hu, Xinbo Gao, Hua Huang

Being extremely dependent on iterative estimation of the degradation prior or optimization of the model from scratch, the existing blind super-resolution (SR) methods are generally time-consuming and less effective, as the estimation of degradation proceeds from a blind initialization and lacks interpretable degradation priors.

Blind Super-Resolution Super-Resolution

ADD-Defense: Towards Defending Widespread Adversarial Examples via Perturbation-Invariant Representation

no code implementations1 Jan 2021 Dawei Zhou, Tongliang Liu, Bo Han, Nannan Wang, Xinbo Gao

Motivated by this observation, we propose a defense framework ADD-Defense, which extracts the invariant information called \textit{perturbation-invariant representation} (PIR) to defend against widespread adversarial examples.

Syncretic Modality Collaborative Learning for Visible Infrared Person Re-Identification

no code implementations ICCV 2021 Ziyu Wei, Xi Yang, Nannan Wang, Xinbo Gao

Visible infrared person re-identification (VI-REID) aims to match pedestrian images between the daytime visible and nighttime infrared camera views.

Person Re-Identification

TSGCNet: Discriminative Geometric Feature Learning with Two-Stream GraphConvolutional Network for 3D Dental Model Segmentation

no code implementations26 Dec 2020 Lingming Zhang, Yue Zhao, Deyu Meng, Zhiming Cui, Chenqiang Gao, Xinbo Gao, Chunfeng Lian, Dinggang Shen

State-of-the-art methods directly concatenate the raw attributes of 3D inputs, namely coordinates and normal vectors of mesh cells, to train a single-stream network for fully-automated tooth segmentation.

Graph Learning

D-Unet: A Dual-encoder U-Net for Image Splicing Forgery Detection and Localization

no code implementations3 Dec 2020 Bo Liu, Ranglei Wu, Xiuli Bi, Bin Xiao, Weisheng Li, Guoyin Wang, Xinbo Gao

The unfixed encoder autonomously learns the image fingerprints that differentiate between the tampered and non-tampered regions, whereas the fixed encoder intentionally provides the direction information that assists the learning and detection of the network.

Binary Classification

Interpretable Detail-Fidelity Attention Network for Single Image Super-Resolution

1 code implementation28 Sep 2020 Yuanfei Huang, Jie Li, Xinbo Gao, Yanting Hu, Wen Lu

To solve them, we propose a purposeful and interpretable detail-fidelity attention network to progressively process these smoothes and details in divide-and-conquer manner, which is a novel and specific prospect of image super-resolution for the purpose on improving the detail fidelity, instead of blindly designing or employing the deep CNNs architectures for merely feature representation in local receptive fields.

Image Super-Resolution

Tasks Integrated Networks: Joint Detection and Retrieval for Image Search

no code implementations3 Sep 2020 Lei Zhang, Zhenwei He, Yi Yang, Liang Wang, Xinbo Gao

The traditional object retrieval task aims to learn a discriminative feature representation with intra-similarity and inter-dissimilarity, which supposes that the objects in an image are manually or automatically pre-cropped exactly.

Image Retrieval Philosophy +1

Collaborative Boundary-aware Context Encoding Networks for Error Map Prediction

no code implementations25 Jun 2020 Zhenxi Zhang, Chunna Tian, Jie Li, Zhusi Zhong, Zhicheng Jiao, Xinbo Gao

Further, we propose a context encoding module to utilize the global predictor from the error map to enhance the feature representation and regularize the networks.

Image Segmentation Medical Image Segmentation +2

Multi-Margin based Decorrelation Learning for Heterogeneous Face Recognition

no code implementations25 May 2020 Bing Cao, Nannan Wang, Xinbo Gao, Jie Li, Zhifeng Li

Heterogeneous face recognition (HFR) refers to matching face images acquired from different domains with wide applications in security scenarios.

Face Recognition Heterogeneous Face Recognition +1

Facial Attribute Capsules for Noise Face Super Resolution

no code implementations16 Feb 2020 Jingwei Xin, Nannan Wang, Xinrui Jiang, Jie Li, Xinbo Gao, Zhifeng Li

In the SR processing, we first generated a group of FACs from the input LR face, and then reconstructed the HR face from this group of FACs.

Attribute Hallucination +1

Video Face Super-Resolution with Motion-Adaptive Feedback Cell

no code implementations15 Feb 2020 Jingwei Xin, Nannan Wang, Jie Li, Xinbo Gao, Zhifeng Li

Current state-of-the-art CNN methods usually treat the VSR problem as a large number of separate multi-frame super-resolution tasks, at which a batch of low resolution (LR) frames is utilized to generate a single high resolution (HR) frame, and running a slide window to select LR frames over the entire video would obtain a series of HR frames.

Motion Compensation Motion Estimation +2

Asynchronous Tracking-by-Detection on Adaptive Time Surfaces for Event-based Object Tracking

no code implementations13 Feb 2020 Haosheng Chen, Qiangqiang Wu, Yanjie Liang, Xinbo Gao, Hanzi Wang

To achieve this goal, we present an Adaptive Time-Surface with Linear Time Decay (ATSLTD) event-to-frame conversion algorithm, which asynchronously and effectively warps the spatio-temporal information of asynchronous retinal events to a sequence of ATSLTD frames with clear object contours.

Object Object Tracking

Image Fine-grained Inpainting

3 code implementations7 Feb 2020 Zheng Hui, Jie Li, Xiumei Wang, Xinbo Gao

Besides, we devise a geometrical alignment constraint item to compensate for the pixel-based distance between prediction features and ground-truth ones.

Facial Inpainting Fine-Grained Image Inpainting

Lightweight Image Super-Resolution with Information Multi-distillation Network

4 code implementations26 Sep 2019 Zheng Hui, Xinbo Gao, Yunchu Yang, Xiumei Wang

In recent years, single image super-resolution (SISR) methods using deep convolution neural network (CNN) have achieved impressive results.

Image Super-Resolution

Progressive Perception-Oriented Network for Single Image Super-Resolution

1 code implementation24 Jul 2019 Zheng Hui, Jie Li, Xinbo Gao, Xiumei Wang

In this paper, we propose a novel perceptual image super-resolution method that progressively generates visually high-quality results by constructing a stage-wise network.

Image Super-Resolution

Reconstructing Perceived Images from Brain Activity by Visually-guided Cognitive Representation and Adversarial Learning

no code implementations27 Jun 2019 Ziqi Ren, Jie Li, Xuetong Xue, Xin Li, Fan Yang, Zhicheng Jiao, Xinbo Gao

In addition, we introduce a novel three-stage learning approach which enables the (cognitive) encoder to gradually distill useful knowledge from the paired (visual) encoder during the learning process.

Generative Adversarial Network Image Reconstruction +2

An Attention-Guided Deep Regression Model for Landmark Detection in Cephalograms

no code implementations17 Jun 2019 Zhusi Zhong, Jie Li, Zhenxi Zhang, Zhicheng Jiao, Xinbo Gao

We train the deep encoder-decoder for landmark detection, and combine global landmark configuration with local high-resolution feature responses.

regression

Deep Multi-scale Discriminative Networks for Double JPEG Compression Forensics

no code implementations4 Apr 2019 Cheng Deng, Zhao Li, Xinbo Gao, DaCheng Tao

In this area, extracting effective statistical characteristics from a JPEG image for classification remains a challenge.

General Classification

Triplet-Based Deep Hashing Network for Cross-Modal Retrieval

no code implementations4 Apr 2019 Cheng Deng, Zhaojia Chen, Xianglong Liu, Xinbo Gao, DaCheng Tao

Given the benefits of its low storage requirements and high retrieval efficiency, hashing has recently received increasing attention.

Cross-Modal Retrieval Deep Hashing +2

Stacked Semantic-Guided Network for Zero-Shot Sketch-Based Image Retrieval

no code implementations3 Apr 2019 Hao Wang, Cheng Deng, Xinxu Xu, Wei Liu, Xinbo Gao, DaCheng Tao

Previous works mostly focus on a generative approach that takes a highly abstract and sparse sketch as input and then synthesizes the corresponding natural image.

Retrieval Sketch-Based Image Retrieval +1

Transfer Adaptation Learning: A Decade Survey

no code implementations12 Mar 2019 Lei Zhang, Xinbo Gao

Domain is referred to as the state of the world at a certain moment.

A Gated Peripheral-Foveal Convolutional Neural Network for Unified Image Aesthetic Prediction

no code implementations19 Dec 2018 Xiaodan Zhang, Xinbo Gao, Wen Lu, Lihuo He

The former aims to mimic the functions of peripheral vision to encode the holistic information and provide the attended regions.

Channel-wise and Spatial Feature Modulation Network for Single Image Super-Resolution

no code implementations28 Sep 2018 Yanting Hu, Jie Li, Yuanfei Huang, Xinbo Gao

To capture more informative features and maintain long-term information for image super-resolution, we propose a channel-wise and spatial feature modulation (CSFM) network in which a sequence of feature-modulation memory (FMM) modules is cascaded with a densely connected structure to transform low-resolution features to high informative features.

Image Reconstruction Image Super-Resolution

Saliency deep embedding for aurora image search

no code implementations23 May 2018 Xi Yang, Xinbo Gao, Bin Song, Nannan Wang, Dong Yang

In this paper, we aim to explore a new search method for images captured with circular fisheye lens, especially the aurora images.

Image Retrieval Region Proposal

Self-Supervised Adversarial Hashing Networks for Cross-Modal Retrieval

1 code implementation CVPR 2018 Chao Li, Cheng Deng, Ning li, Wei Liu, Xinbo Gao, DaCheng Tao

In addition, we harness a self-supervised semantic network to discover high-level semantic information in the form of multi-label annotations.

Cross-Modal Retrieval Retrieval

Fast and Accurate Single Image Super-Resolution via Information Distillation Network

2 code implementations CVPR 2018 Zheng Hui, Xiumei Wang, Xinbo Gao

Recently, deep convolutional neural networks (CNNs) have been demonstrated remarkable progress on single image super-resolution.

Image Super-Resolution

Single Image Super-Resolution via Cascaded Multi-Scale Cross Network

no code implementations24 Feb 2018 Yanting Hu, Xinbo Gao, Jie Li, Yuanfei Huang, Hanzi Wang

To improve information flow and to capture sufficient knowledge for reconstructing the high-frequency details, we propose a cascaded multi-scale cross network (CMSC) in which a sequence of subnetworks is cascaded to infer high resolution features in a coarse-to-fine manner.

Image Reconstruction Image Super-Resolution

Restricting Greed in Training of Generative Adversarial Network

no code implementations28 Nov 2017 Haoxuan You, Zhicheng Jiao, Haojun Xu, Jie Li, Ying Wang, Xinbo Gao

Generative adversarial network (GAN) has gotten wide re-search interest in the field of deep learning.

Generative Adversarial Network

Hierarchical Multimodal LSTM for Dense Visual-Semantic Embedding

no code implementations ICCV 2017 Zhenxing Niu, Mo Zhou, Le Wang, Xinbo Gao, Gang Hua

We address the problem of dense visual-semantic embedding that maps not only full sentences and whole images but also phrases within sentences and salient regions within images into a multimodal embedding space.

Sentence

Random Sampling for Fast Face Sketch Synthesis

no code implementations8 Jan 2017 Nannan Wang, Xinbo Gao, Jie Li

The most time-consuming or main computation complexity for exemplar-based face sketch synthesis methods lies in the neighbor selection process.

Face Hallucination Face Sketch Synthesis +1

Sparse Graphical Representation based Discriminant Analysis for Heterogeneous Face Recognition

no code implementations1 Jul 2016 Chunlei Peng, Xinbo Gao, Nannan Wang, Jie Li

An adaptive sparse graphical representation scheme is designed to represent heterogeneous face images, where a Markov networks model is constructed to generate adaptive sparse vectors.

Face Recognition Heterogeneous Face Recognition

Ordinal Regression With Multiple Output CNN for Age Estimation

no code implementations CVPR 2016 Zhenxing Niu, Mo Zhou, Le Wang, Xinbo Gao, Gang Hua

To address the non-stationary property of aging patterns, age estimation can be cast as an ordinal regression problem.

Age Estimation Binary Classification +3

Training-Free Synthesized Face Sketch Recognition Using Image Quality Assessment Metrics

no code implementations25 Mar 2016 Nannan Wang, Jie Li, Leiyu Sun, Bin Song, Xinbo Gao

In this paper, we proposed a synthesized face sketch recognition framework based on full-reference image quality assessment metrics.

Face Recognition Face Sketch Synthesis +2

Graphical Representation for Heterogeneous Face Recognition

no code implementations2 Mar 2015 Chunlei Peng, Xinbo Gao, Nannan Wang, Jie Li

Heterogeneous face recognition (HFR) refers to matching face images acquired from different sources (i. e., different sensors or different wavelengths) for identification.

Face Recognition Heterogeneous Face Recognition

Facial Feature Point Detection: A Comprehensive Survey

no code implementations4 Oct 2014 Nannan Wang, Xinbo Gao, DaCheng Tao, Xuelong. Li

CLM-based methods consist of a shape model and a number of local experts, each of which is utilized to detect a facial feature point.

3D Face Modelling Face Alignment +4

Semi-supervised Relational Topic Model for Weakly Annotated Image Recognition in Social Media

no code implementations CVPR 2014 Zhenxing Niu, Gang Hua, Xinbo Gao, Qi Tian

In such way, we can efficiently leverage the loosely related tags, and build an intermediate level representation for a collection of weakly annotated images.

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