Search Results for author: Xin Fan

Found 69 papers, 30 papers with code

Learn from the Past: A Proxy based Adversarial Defense Framework to Boost Robustness

no code implementations19 Oct 2023 Yaohua Liu, Jiaxin Gao, Zhu Liu, Xianghao Jiao, Xin Fan, Risheng Liu

In light of the vulnerability of deep learning models to adversarial samples and the ensuing security issues, a range of methods, including Adversarial Training (AT) as a prominent representative, aimed at enhancing model robustness against various adversarial attacks, have seen rapid development.

Adversarial Defense

Diving into Darkness: A Dual-Modulated Framework for High-Fidelity Super-Resolution in Ultra-Dark Environments

no code implementations11 Sep 2023 Jiaxin Gao, Ziyu Yue, Yaohua Liu, Sihan Xie, Xin Fan, Risheng Liu

Super-resolution tasks oriented to images captured in ultra-dark environments is a practical yet challenging problem that has received little attention.


Fearless Luminance Adaptation: A Macro-Micro-Hierarchical Transformer for Exposure Correction

no code implementations2 Sep 2023 Gehui Li, JinYuan Liu, Long Ma, Zhiying Jiang, Xin Fan, Risheng Liu

To overcome these limitations, we propose a Macro-Micro-Hierarchical transformer, which consists of a macro attention to capture long-range dependencies, a micro attention to extract local features, and a hierarchical structure for coarse-to-fine correction.

Face Recognition Semantic Segmentation

Learning Heavily-Degraded Prior for Underwater Object Detection

1 code implementation24 Aug 2023 Chenping Fu, Xin Fan, Jiewen Xiao, Wanqi Yuan, Risheng Liu, Zhongxuan Luo

Therefore, we propose a residual feature transference module (RFTM) to learn a mapping between deep representations of the heavily degraded patches of DFUI- and underwater- images, and make the mapping as a heavily degraded prior (HDP) for underwater detection.

object-detection Object Detection

PAIF: Perception-Aware Infrared-Visible Image Fusion for Attack-Tolerant Semantic Segmentation

1 code implementation8 Aug 2023 Zhu Liu, JinYuan Liu, Benzhuang Zhang, Long Ma, Xin Fan, Risheng Liu

We first conduct systematic analyses about the components of image fusion, investigating the correlation with segmentation robustness under adversarial perturbations.

Infrared And Visible Image Fusion Segmentation +2

Bilevel Generative Learning for Low-Light Vision

1 code implementation7 Aug 2023 Yingchi Liu, Zhu Liu, Long Ma, JinYuan Liu, Xin Fan, Zhongxuan Luo, Risheng Liu

In this study, we propose a generic low-light vision solution by introducing a generative block to convert data from the RAW to the RGB domain.

Bilevel Optimization

WaterFlow: Heuristic Normalizing Flow for Underwater Image Enhancement and Beyond

no code implementations2 Aug 2023 Zengxi Zhang, Zhiying Jiang, JinYuan Liu, Xin Fan, Risheng Liu

Underwater images suffer from light refraction and absorption, which impairs visibility and interferes the subsequent applications.

Image Enhancement

Multi-Spectral Image Stitching via Spatial Graph Reasoning

no code implementations31 Jul 2023 Zhiying Jiang, Zengxi Zhang, JinYuan Liu, Xin Fan, Risheng Liu

Multi-spectral image stitching leverages the complementarity between infrared and visible images to generate a robust and reliable wide field-of-view (FOV) scene.

Image Stitching

Learning with Constraint Learning: New Perspective, Solution Strategy and Various Applications

no code implementations28 Jul 2023 Risheng Liu, Jiaxin Gao, Xuan Liu, Xin Fan

The complexity of learning problems, such as Generative Adversarial Network (GAN) and its variants, multi-task and meta-learning, hyper-parameter learning, and a variety of real-world vision applications, demands a deeper understanding of their underlying coupling mechanisms.


Joint Perceptual Learning for Enhancement and Object Detection in Underwater Scenarios

no code implementations7 Jul 2023 Chenping Fu, Wanqi Yuan, Jiewen Xiao, Risheng Liu, Xin Fan

Based on these factual opinions, we propose a bilevel optimization formulation for jointly learning underwater object detection and image enhancement, and then unroll to a dual perception network (DPNet) for the two tasks.

Bilevel Optimization Image Enhancement +3

Bilevel Fast Scene Adaptation for Low-Light Image Enhancement

1 code implementation2 Jun 2023 Long Ma, Dian Jin, Nan An, JinYuan Liu, Xin Fan, Risheng Liu

A bilevel learning framework is constructed to endow the scene-irrelevant generality of the encoder towards diverse scenes (i. e., freezing the encoder in the adaptation and testing phases).

Denoising Hyperparameter Optimization +1

Contrastive Learning Based Recursive Dynamic Multi-Scale Network for Image Deraining

no code implementations29 May 2023 Zhiying Jiang, Risheng Liu, Shuzhou Yang, Zengxi Zhang, Xin Fan

Extensive experiments on synthetic benchmarks and real-world images demonstrate that the proposed RDMC delivers strong performance on the depiction of rain streaks and outperforms the state-of-the-art methods.

Contrastive Learning object-detection +3

PEARL: Preprocessing Enhanced Adversarial Robust Learning of Image Deraining for Semantic Segmentation

no code implementations25 May 2023 Xianghao Jiao, Yaohua Liu, Jiaxin Gao, Xinyuan Chu, Risheng Liu, Xin Fan

In light of the significant progress made in the development and application of semantic segmentation tasks, there has been increasing attention towards improving the robustness of segmentation models against natural degradation factors (e. g., rain streaks) or artificially attack factors (e. g., adversarial attack).

Adversarial Attack Rain Removal +2

A Task-guided, Implicitly-searched and Meta-initialized Deep Model for Image Fusion

1 code implementation25 May 2023 Risheng Liu, Zhu Liu, JinYuan Liu, Xin Fan, Zhongxuan Luo

Qualitative and quantitative experimental results on different categories of image fusion problems and related downstream tasks (e. g., visual enhancement and semantic understanding) substantiate the flexibility and effectiveness of our TIM.

An Interactively Reinforced Paradigm for Joint Infrared-Visible Image Fusion and Saliency Object Detection

1 code implementation17 May 2023 Di Wang, JinYuan Liu, Risheng Liu, Xin Fan

Their common characteristic of seeking complementary cues from different source images motivates us to explore the collaborative relationship between Fusion and Salient object detection tasks on infrared and visible images via an Interactively Reinforced multi-task paradigm for the first time, termed IRFS.

Infrared And Visible Image Fusion object-detection +2

Bi-level Dynamic Learning for Jointly Multi-modality Image Fusion and Beyond

2 code implementations11 May 2023 Zhu Liu, JinYuan Liu, Guanyao Wu, Long Ma, Xin Fan, Risheng Liu

Recently, multi-modality scene perception tasks, e. g., image fusion and scene understanding, have attracted widespread attention for intelligent vision systems.

Scene Understanding

Breaking Modality Disparity: Harmonized Representation for Infrared and Visible Image Registration

no code implementations12 Apr 2023 Zhiying Jiang, Zengxi Zhang, JinYuan Liu, Xin Fan, Risheng Liu

Since the differences in viewing range, resolution and relative position, the multi-modality sensing module composed of infrared and visible cameras needs to be registered so as to have more accurate scene perception.

Image Registration

Pixels, Regions, and Objects: Multiple Enhancement for Salient Object Detection

1 code implementation CVPR 2023 Yi Wang, Ruili Wang, Xin Fan, Tianzhu Wang, Xiangjian He

A multi-level hybrid loss is firstly designed to guide the network to learn pixel-level, region-level, and object-level features.

object-detection Object Detection +1

Practical Exposure Correction: Great Truths Are Always Simple

no code implementations29 Dec 2022 Long Ma, Tianjiao Ma, Xinwei Xue, Xin Fan, Zhongxuan Luo, Risheng Liu

Improving the visual quality of the given degraded observation by correcting exposure level is a fundamental task in the computer vision community.

Breaking Free from Fusion Rule: A Fully Semantic-driven Infrared and Visible Image Fusion

1 code implementation22 Nov 2022 Yuhui Wu, Zhu Liu, JinYuan Liu, Xin Fan, Risheng Liu

To address these challenges, in this letter, we develop a semantic-level fusion network to sufficiently utilize the semantic guidance, emancipating the experimental designed fusion rules.

Infrared And Visible Image Fusion

Semantic-aware Texture-Structure Feature Collaboration for Underwater Image Enhancement

1 code implementation19 Nov 2022 Di Wang, Long Ma, Risheng Liu, Xin Fan

To address the above limitations, we develop an efficient and compact enhancement network in collaboration with a high-level semantic-aware pretrained model, aiming to exploit its hierarchical feature representation as an auxiliary for the low-level underwater image enhancement.

Image Enhancement object-detection +2

Distributed Swarm Learning for Internet of Things at the Edge: Where Artificial Intelligence Meets Biological Intelligence

no code implementations29 Oct 2022 Yue Wang, Zhi Tian, Xin Fan, Yan Huo, Cameron Nowzari, Kai Zeng

With the proliferation of versatile Internet of Things (IoT) services, smart IoT devices are increasingly deployed at the edge of wireless networks to perform collaborative machine learning tasks using locally collected data, giving rise to the edge learning paradigm.

CB-DSL: Communication-efficient and Byzantine-robust Distributed Swarm Learning on Non-i.i.d. Data

no code implementations10 Aug 2022 Xin Fan, Yue Wang, Yan Huo, Zhi Tian

data issues and Byzantine attacks, global data samples are introduced in CB-DSL and shared among IoT workers, which not only alleviates the local data heterogeneity effectively but also enables to fully utilize the exploration-exploitation mechanism of swarm intelligence.

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

Unsupervised Misaligned Infrared and Visible Image Fusion via Cross-Modality Image Generation and Registration

1 code implementation24 May 2022 Di Wang, JinYuan Liu, Xin Fan, Risheng Liu

Moreover, to better fuse the registered infrared images and visible images, we present a feature Interaction Fusion Module (IFM) to adaptively select more meaningful features for fusion in the Dual-path Interaction Fusion Network (DIFN).

Image Generation Infrared And Visible Image Fusion +1

Revisiting GANs by Best-Response Constraint: Perspective, Methodology, and Application

no code implementations20 May 2022 Risheng Liu, Jiaxin Gao, Xuan Liu, Xin Fan

In past years, the minimax type single-level optimization formulation and its variations have been widely utilized to address Generative Adversarial Networks (GANs).

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.


Toward Fast, Flexible, and Robust Low-Light Image Enhancement

1 code implementation CVPR 2022 Long Ma, Tengyu Ma, Risheng Liu, Xin Fan, Zhongxuan Luo

Existing low-light image enhancement techniques are mostly not only difficult to deal with both visual quality and computational efficiency but also commonly invalid in unknown complex scenarios.

Face Detection Low-Light Image Enhancement +1

Cross-SRN: Structure-Preserving Super-Resolution Network with Cross Convolution

no code implementations5 Jan 2022 Yuqing Liu, Qi Jia, Xin Fan, Shanshe Wang, Siwei Ma, Wen Gao

It is challenging to restore low-resolution (LR) images to super-resolution (SR) images with correct and clear details.


Segment, Magnify and Reiterate: Detecting Camouflaged Objects the Hard Way

1 code implementation CVPR 2022 Qi Jia, Shuilian Yao, Yu Liu, Xin Fan, Risheng Liu, Zhongxuan Luo

To tackle camouflaged object detection (COD), we are inspired by humans attention coupled with the coarse-to-fine detection strategy, and thereby propose an iterative refinement framework, coined SegMaR, which integrates Segment, Magnify and Reiterate in a multi-stage detection fashion.

object-detection Object Detection

Learning Deep Context-Sensitive Decomposition for Low-Light Image Enhancement

1 code implementation9 Dec 2021 Long Ma, Risheng Liu, Jiaao Zhang, Xin Fan, Zhongxuan Luo

Further, by sharing an encoder for these two components, we obtain a more lightweight version (SLiteCSDNet for short).

Low-Light Image Enhancement

Learning with Nested Scene Modeling and Cooperative Architecture Search for Low-Light Vision

1 code implementation9 Dec 2021 Risheng Liu, Long Ma, Tengyu Ma, Xin Fan, Zhongxuan Luo

To partially address above issues, we establish Retinex-inspired Unrolling with Architecture Search (RUAS), a general learning framework, which not only can address low-light enhancement task, but also has the flexibility to handle other more challenging downstream vision applications.

Rolling Shutter Correction

Triple-level Model Inferred Collaborative Network Architecture for Video Deraining

no code implementations8 Nov 2021 Pan Mu, Zhu Liu, Yaohua Liu, Risheng Liu, Xin Fan

In this paper, we develop a model-guided triple-level optimization framework to deduce network architecture with cooperating optimization and auto-searching mechanism, named Triple-level Model Inferred Cooperating Searching (TMICS), for dealing with various video rain circumstances.

Optical Flow Estimation Rain Removal

BEV-SGD: Best Effort Voting SGD for Analog Aggregation Based Federated Learning against Byzantine Attackers

no code implementations18 Oct 2021 Xin Fan, Yue Wang, Yan Huo, Zhi Tian

As a promising distributed learning technology, analog aggregation based federated learning over the air (FLOA) provides high communication efficiency and privacy provisioning under the edge computing paradigm.

Edge-computing Federated Learning

An Underwater Image Semantic Segmentation Method Focusing on Boundaries and a Real Underwater Scene Semantic Segmentation Dataset

2 code implementations26 Aug 2021 Zhiwei Ma, Haojie Li, Zhihui Wang, Dan Yu, Tianyi Wang, Yingshuang Gu, Xin Fan, Zhongxuan Luo

Based on this dataset, we propose a semi-supervised underwater semantic segmentation network focusing on the boundaries(US-Net: Underwater Segmentation Network).

Boundary Detection Instance Segmentation +6

A Dataset And Benchmark Of Underwater Object Detection For Robot Picking

no code implementations10 Jun 2021 Chongwei Liu, Haojie Li, Shuchang Wang, Ming Zhu, Dong Wang, Xin Fan, Zhihui Wang

Towards these challenges we introduce a dataset, Detecting Underwater Objects (DUO), and a corresponding benchmark, based on the collection and re-annotation of all relevant datasets.

object-detection Object Detection

Joint Optimization of Communications and Federated Learning Over the Air

no code implementations8 Apr 2021 Xin Fan, Yue Wang, Yan Huo, Zhi Tian

Federated learning (FL) is an attractive paradigm for making use of rich distributed data while protecting data privacy.

Federated Learning

1-Bit Compressive Sensing for Efficient Federated Learning Over the Air

no code implementations30 Mar 2021 Xin Fan, Yue Wang, Yan Huo, Zhi Tian

For distributed learning among collaborative users, this paper develops and analyzes a communication-efficient scheme for federated learning (FL) over the air, which incorporates 1-bit compressive sensing (CS) into analog aggregation transmissions.

Compressive Sensing Dimensionality Reduction +3

Optimization-Inspired Learning with Architecture Augmentations and Control Mechanisms for Low-Level Vision

1 code implementation10 Dec 2020 Risheng Liu, Zhu Liu, Pan Mu, Xin Fan, Zhongxuan Luo

Specifically, by introducing a general energy minimization model and formulating its descent direction from different viewpoints (i. e., in a generative manner, based on the discriminative metric and with optimality-based correction), we construct three propagative modules to effectively solve the optimization models with flexible combinations.

Learning Deformable Image Registration from Optimization: Perspective, Modules, Bilevel Training and Beyond

2 code implementations30 Apr 2020 Risheng Liu, Zi Li, Xin Fan, Chenying Zhao, Hao Huang, Zhongxuan Luo

We design a new deep learning based framework to optimize a diffeomorphic model via multi-scale propagation in order to integrate advantages and avoid limitations of these two categories of approaches.

Image Registration Image Segmentation +1

A New Dataset, Poisson GAN and AquaNet for Underwater Object Grabbing

no code implementations3 Mar 2020 Chongwei Liu, Zhihui Wang, Shijie Wang, Tao Tang, Yulong Tao, Caifei Yang, Haojie Li, Xing Liu, Xin Fan

We also propose a novel Poisson-blending Generative Adversarial Network (Poisson GAN) and an efficient object detection network (AquaNet) to address two common issues within related datasets: the class-imbalance problem and the problem of mass small object, respectively.

object-detection Object Detection

Converged Deep Framework Assembling Principled Modules for CS-MRI

no code implementations29 Oct 2019 Risheng Liu, Yuxi Zhang, Shichao Cheng, Zhongxuan Luo, Xin Fan

Compressed Sensing Magnetic Resonance Imaging (CS-MRI) significantly accelerates MR data acquisition at a sampling rate much lower than the Nyquist criterion.

Investigating Task-driven Latent Feasibility for Nonconvex Image Modeling

no code implementations18 Oct 2019 Risheng Liu, Pan Mu, Jian Chen, Xin Fan, Zhongxuan Luo

Properly modeling latent image distributions plays an important role in a variety of image-related vision problems.

Deblurring Image Deblurring

Position Focused Attention Network for Image-Text Matching

1 code implementation23 Jul 2019 Yaxiong Wang, Hao Yang, Xueming Qian, Lin Ma, Jing Lu, Biao Li, Xin Fan

Then, an attention mechanism is proposed to model the relations between the image region and blocks and generate the valuable position feature, which will be further utilized to enhance the region expression and model a more reliable relationship between the visual image and the textual sentence.

Image-text matching Test +1

Underexposed Image Correction via Hybrid Priors Navigated Deep Propagation

no code implementations17 Jul 2019 Risheng Liu, Long Ma, Yuxi Zhang, Xin Fan, Zhongxuan Luo

Plenty of experimental results of underexposed image correction demonstrate that our proposed method performs favorably against the state-of-the-art methods on both subjective and objective assessments.

Face Detection Single Image Haze Removal

Accurate Monocular Object Detection via Color-Embedded 3D Reconstruction for Autonomous Driving

no code implementations27 Mar 2019 Xinzhu Ma, Zhihui Wang, Haojie Li, Peng-Bo Zhang, Xin Fan, Wanli Ouyang

To this end, we first leverage a stand-alone module to transform the input data from 2D image plane to 3D point clouds space for a better input representation, then we perform the 3D detection using PointNet backbone net to obtain objects 3D locations, dimensions and orientations.

3D Reconstruction Autonomous Driving +2

Real-world Underwater Enhancement: Challenges, Benchmarks, and Solutions

1 code implementation15 Jan 2019 Risheng Liu, Xin Fan, Ming Zhu, Minjun Hou, Zhongxuan Luo

Underwater image enhancement is such an important low-level vision task with many applications that numerous algorithms have been proposed in recent years.

Image Enhancement object-detection +1

A Bridging Framework for Model Optimization and Deep Propagation

no code implementations NeurIPS 2018 Risheng Liu, Shichao Cheng, Xiaokun Liu, Long Ma, Xin Fan, Zhongxuan Luo

Different from these existing network based iterations, which often lack theoretical investigations, we provide strict convergence analysis for PODM in the challenging nonconvex and nonsmooth scenarios.

Model Optimization

A Theoretically Guaranteed Deep Optimization Framework for Robust Compressive Sensing MRI

no code implementations9 Nov 2018 Risheng Liu, Yuxi Zhang, Shichao Cheng, Xin Fan, Zhongxuan Luo

Magnetic Resonance Imaging (MRI) is one of the most dynamic and safe imaging techniques available for clinical applications.

Compressive Sensing

On the Convergence of Learning-based Iterative Methods for Nonconvex Inverse Problems

no code implementations16 Aug 2018 Risheng Liu, Shichao Cheng, Yi He, Xin Fan, Zhouchen Lin, Zhongxuan Luo

Moreover, there is a lack of rigorous analysis about the convergence behaviors of these reimplemented iterations, and thus the significance of such methods is a little bit vague.


Toward Designing Convergent Deep Operator Splitting Methods for Task-specific Nonconvex Optimization

no code implementations28 Apr 2018 Risheng Liu, Shichao Cheng, Yi He, Xin Fan, Zhongxuan Luo

Operator splitting methods have been successfully used in computational sciences, statistics, learning and vision areas to reduce complex problems into a series of simpler subproblems.


Self-Reinforced Cascaded Regression for Face Alignment

no code implementations23 Nov 2017 Xin Fan, Risheng Liu, Kang Huyan, Yuyao Feng, Zhongxuan Luo

Cascaded regression is prevailing in face alignment thanks to its accuracy and robustness, but typically demands manually annotated examples having low discrepancy between shape-indexed features and shape updates.

Face Alignment Philosophy +1

Sequential Dual Deep Learning with Shape and Texture Features for Sketch Recognition

no code implementations9 Aug 2017 Qi Jia, Meiyu Yu, Xin Fan, Haojie Li

We develop dual deep networks with memorable gated recurrent units (GRUs), and sequentially feed these two types of features into the dual networks, respectively.

Sketch Recognition

Mining Functional Modules by Multiview-NMF of Phenome-Genome Association

1 code implementation11 May 2017 YaoGong Zhang, YingJie Xu, Xin Fan, YuXiang Hong, Jiahui Liu, ZhiCheng He, YaLou Huang, MaoQiang Xie

In particular, the hierarchical structure of ontology has not been sufficiently utilized in clustering genes while functionally related genes are consistently associated with phenotypes on the same path in the phenotype ontology.


A Fast Ellipse Detector Using Projective Invariant Pruning

2 code implementations26 Aug 2016 Qi Jia, Xin Fan, Zhongxuan Luo, Lianbo Song, Tie Qiu

Detecting elliptical objects from an image is a central task in robot navigation and industrial diagnosis where the detection time is always a critical issue.

Robot Navigation

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