Search Results for author: Gui-Song Xia

Found 125 papers, 71 papers with code

DMTG: One-Shot Differentiable Multi-Task Grouping

1 code implementation6 Jul 2024 Yuan Gao, Shuguo Jiang, Moran Li, Jin-Gang Yu, Gui-Song Xia

Given N tasks, we propose to simultaneously identify the best task groups from 2^N candidates and train the model weights simultaneously in one-shot, with the high-order task-affinity fully exploited.

Multi-Task Learning

Towards Human-Level 3D Relative Pose Estimation: Generalizable, Training-Free, with Single Reference

1 code implementation26 Jun 2024 Yuan Gao, Yajing Luo, Junhong Wang, Kui Jia, Gui-Song Xia

Motivated by this, we propose a novel 3D generalizable relative pose estimation method by elaborating (i) with a 2. 5D shape from an RGB-D reference, (ii) with an off-the-shelf differentiable renderer, and (iii) with semantic cues from a pretrained model like DINOv2.

Pose Estimation

Optimization-based Structural Pruning for Large Language Models without Back-Propagation

no code implementations15 Jun 2024 Yuan Gao, Zujing Liu, Weizhong Zhang, Bo Du, Gui-Song Xia

Compared to the moderate size of neural network models, structural weight pruning on the Large-Language Models (LLMs) imposes a novel challenge on the efficiency of the pruning algorithms, due to the heavy computation/memory demands of the LLMs.

Aux-NAS: Exploiting Auxiliary Labels with Negligibly Extra Inference Cost

1 code implementation9 May 2024 Yuan Gao, Weizhong Zhang, Wenhan Luo, Lin Ma, Jin-Gang Yu, Gui-Song Xia, Jiayi Ma

We aim at exploiting additional auxiliary labels from an independent (auxiliary) task to boost the primary task performance which we focus on, while preserving a single task inference cost of the primary task.

Auxiliary Learning Neural Architecture Search

Dual Relation Mining Network for Zero-Shot Learning

no code implementations6 May 2024 Jinwei Han, Yingguo Gao, Zhiwen Lin, Ke Yan, Shouhong Ding, Yuan Gao, Gui-Song Xia

Specifically, we introduce a Dual Attention Block (DAB) for visual-semantic relationship mining, which enriches visual information by multi-level feature fusion and conducts spatial attention for visual to semantic embedding.

Attribute Relation +2

Anchor-based Robust Finetuning of Vision-Language Models

no code implementations CVPR 2024 Jinwei Han, Zhiwen Lin, Zhongyisun Sun, Yingguo Gao, Ke Yan, Shouhong Ding, Yuan Gao, Gui-Song Xia

Specifically, two types of anchors are elaborated in our method, including i) text-compensated anchor which uses the images from the finetune set but enriches the text supervision from a pretrained captioner, ii) image-text-pair anchor which is retrieved from the dataset similar to pretraining data of CLIP according to the downstream task, associating with the original CLIP text with rich semantics.

Language Modelling Zero-Shot Learning

3D Building Reconstruction from Monocular Remote Sensing Images with Multi-level Supervisions

1 code implementation CVPR 2024 Weijia Li, Haote Yang, Zhenghao Hu, Juepeng Zheng, Gui-Song Xia, Conghui He

3D building reconstruction from monocular remote sensing images is an important and challenging research problem that has received increasing attention in recent years, owing to its low cost of data acquisition and availability for large-scale applications.

3D Reconstruction

H2RSVLM: Towards Helpful and Honest Remote Sensing Large Vision Language Model

1 code implementation29 Mar 2024 Chao Pang, Jiang Wu, Jiayu Li, Yi Liu, Jiaxing Sun, Weijia Li, Xingxing Weng, Shuai Wang, Litong Feng, Gui-Song Xia, Conghui He

The generic large Vision-Language Models (VLMs) is rapidly developing, but still perform poorly in Remote Sensing (RS) domain, which is due to the unique and specialized nature of RS imagery and the comparatively limited spatial perception of current VLMs.

Hallucination Language Modelling +2

Unleashing Unlabeled Data: A Paradigm for Cross-View Geo-Localization

1 code implementation CVPR 2024 Guopeng Li, Ming Qian, Gui-Song Xia

This paper investigates the effective utilization of unlabeled data for large-area cross-view geo-localization (CVGL), encompassing both unsupervised and semi-supervised settings.


Learning Cross-view Visual Geo-localization without Ground Truth

no code implementations19 Mar 2024 Haoyuan Li, Chang Xu, Wen Yang, Huai Yu, Gui-Song Xia

We observe that training on unlabeled cross-view images presents significant challenges, including the need to establish relationships within unlabeled data and reconcile view discrepancies between uncertain queries and references.

Self-Supervised Learning

Few-Shot Learning for Annotation-Efficient Nucleus Instance Segmentation

no code implementations26 Feb 2024 Yu Ming, Zihao Wu, Jie Yang, Danyi Li, Yuan Gao, Changxin Gao, Gui-Song Xia, Yuanqing Li, Li Liang, Jin-Gang Yu

In this paper, we propose to formulate annotation-efficient nucleus instance segmentation from the perspective of few-shot learning (FSL).

Few-Shot Learning Instance Segmentation +3

GOOD: Towards Domain Generalized Orientated Object Detection

no code implementations20 Feb 2024 Qi Bi, Beichen Zhou, Jingjun Yi, Wei Ji, Haolan Zhan, Gui-Song Xia

In this paper, we propose the task of domain generalized oriented object detection, which intends to explore the generalization of oriented object detectors on arbitrary unseen target domains.

Hallucination Object +3

Robust Tiny Object Detection in Aerial Images amidst Label Noise

1 code implementation16 Jan 2024 Haoran Zhu, Chang Xu, Wen Yang, Ruixiang Zhang, Yan Zhang, Gui-Song Xia

In this study, we address the intricate issue of tiny object detection under noisy label supervision.

Denoising Object +2

Cross-Level Multi-Instance Distillation for Self-Supervised Fine-Grained Visual Categorization

no code implementations16 Jan 2024 Qi Bi, Wei Ji, Jingjun Yi, Haolan Zhan, Gui-Song Xia

To comprehensively learn the relation between informative patches and fine-grained semantics, the multi-instance knowledge distillation is implemented on both the region/image crop pairs from the teacher and student net, and the region-image crops inside the teacher / student net, which we term as intra-level multi-instance distillation and inter-level multi-instance distillation.

Fine-Grained Visual Categorization Knowledge Distillation +2

CrossZoom: Simultaneously Motion Deblurring and Event Super-Resolving

1 code implementation29 Sep 2023 Chi Zhang, Xiang Zhang, Mingyuan Lin, Cheng Li, Chu He, Wen Yang, Gui-Song Xia, Lei Yu

Even though the collaboration between traditional and neuromorphic event cameras brings prosperity to frame-event based vision applications, the performance is still confined by the resolution gap crossing two modalities in both spatial and temporal domains.

Deblurring Event-based vision

QuadricsNet: Learning Concise Representation for Geometric Primitives in Point Clouds

1 code implementation25 Sep 2023 Ji Wu, Huai Yu, Wen Yang, Gui-Song Xia

This paper presents a novel framework to learn a concise geometric primitive representation for 3D point clouds.

Patched Line Segment Learning for Vector Road Mapping

no code implementations6 Sep 2023 Jiakun Xu, Bowen Xu, Gui-Song Xia, Liang Dong, Nan Xue

In our experiments, we demonstrate how an effective representation of a road graph significantly enhances the performance of vector road mapping on established benchmarks, without requiring extensive modifications to the neural network architecture.

On the Robustness of Object Detection Models in Aerial Images

1 code implementation29 Aug 2023 Haodong He, Jian Ding, Gui-Song Xia

The robustness of object detection models is a major concern when applied to real-world scenarios.

Data Augmentation Object +3

Towards Generic and Controllable Attacks Against Object Detection

1 code implementation23 Jul 2023 Guopeng Li, Yue Xu, Jian Ding, Gui-Song Xia

To this end, we propose a generic white-box attack, LGP (local perturbations with adaptively global attacks), to blind mainstream object detectors with controllable perturbations.

Object object-detection +1

NEAT: Distilling 3D Wireframes from Neural Attraction Fields

1 code implementation CVPR 2024 Nan Xue, Bin Tan, Yuxi Xiao, Liang Dong, Gui-Song Xia, Tianfu Wu, Yujun Shen

Instead of leveraging matching-based solutions from 2D wireframes (or line segments) for 3D wireframe reconstruction as done in prior arts, we present NEAT, a rendering-distilling formulation using neural fields to represent 3D line segments with 2D observations, and bipartite matching for perceiving and distilling of a sparse set of 3D global junctions.

3D Wireframe Reconstruction Novel View Synthesis

Depth and DOF Cues Make A Better Defocus Blur Detector

1 code implementation20 Jun 2023 Yuxin Jin, Ming Qian, Jincheng Xiong, Nan Xue, Gui-Song Xia

Our method proposes a depth feature distillation strategy to obtain depth knowledge from a pre-trained monocular depth estimation model and uses a DOF-edge loss to understand the relationship between DOF and depth.

Defocus Blur Detection Monocular Depth Estimation

DAM-Net: Global Flood Detection from SAR Imagery Using Differential Attention Metric-Based Vision Transformers

1 code implementation1 Jun 2023 Tamer Saleh, Xingxing Weng, Shimaa Holail, Chen Hao, Gui-Song Xia

The detection of flooded areas using high-resolution synthetic aperture radar (SAR) imagery is a critical task with applications in crisis and disaster management, as well as environmental resource planning.

HGFormer: Hierarchical Grouping Transformer for Domain Generalized Semantic Segmentation

1 code implementation CVPR 2023 Jian Ding, Nan Xue, Gui-Song Xia, Bernt Schiele, Dengxin Dai

This work studies semantic segmentation under the domain generalization setting, where a model is trained only on the source domain and tested on the unseen target domain.

Domain Generalization Segmentation +1

FreePoint: Unsupervised Point Cloud Instance Segmentation

1 code implementation CVPR 2024 Zhikai Zhang, Jian Ding, Li Jiang, Dengxin Dai, Gui-Song Xia

Based on the point features, we perform a bottom-up multicut algorithm to segment point clouds into coarse instance masks as pseudo labels, which are used to train a point cloud instance segmentation model.

Instance Segmentation Segmentation +2

Dynamic Coarse-to-Fine Learning for Oriented Tiny Object Detection

1 code implementation CVPR 2023 Chang Xu, Jian Ding, Jinwang Wang, Wen Yang, Huai Yu, Lei Yu, Gui-Song Xia

Despite the exploration of adaptive label assignment in recent oriented object detectors, the extreme geometry shape and limited feature of oriented tiny objects still induce severe mismatch and imbalance issues.

object-detection Object Detection +2

Self-Supervised Scene Dynamic Recovery from Rolling Shutter Images and Events

no code implementations14 Apr 2023 Yangguang Wang, Xiang Zhang, Mingyuan Lin, Lei Yu, Boxin Shi, Wen Yang, Gui-Song Xia

Scene Dynamic Recovery (SDR) by inverting distorted Rolling Shutter (RS) images to an undistorted high frame-rate Global Shutter (GS) video is a severely ill-posed problem due to the missing temporal dynamic information in both RS intra-frame scanlines and inter-frame exposures, particularly when prior knowledge about camera/object motions is unavailable.

Self-Supervised Learning

Recovering Continuous Scene Dynamics from A Single Blurry Image with Events

no code implementations5 Apr 2023 Zhangyi Cheng, Xiang Zhang, Lei Yu, Jianzhuang Liu, Wen Yang, Gui-Song Xia

This paper aims at demystifying a single motion-blurred image with events and revealing temporally continuous scene dynamics encrypted behind motion blurs.

Image Restoration SSIM

Learning to Super-Resolve Blurry Images with Events

1 code implementation27 Feb 2023 Lei Yu, Bishan Wang, Xiang Zhang, Haijian Zhang, Wen Yang, Jianzhuang Liu, Gui-Song Xia

Super-Resolution from a single motion Blurred image (SRB) is a severely ill-posed problem due to the joint degradation of motion blurs and low spatial resolution.

Sparse Learning Super-Resolution

Few-Shot Object Detection via Variational Feature Aggregation

1 code implementation31 Jan 2023 Jiaming Han, Yuqiang Ren, Jian Ding, Ke Yan, Gui-Song Xia

As few-shot object detectors are often trained with abundant base samples and fine-tuned on few-shot novel examples, the learned models are usually biased to base classes and sensitive to the variance of novel examples.

Few-Shot Object Detection Meta-Learning +3

Detecting Building Changes with Off-Nadir Aerial Images

1 code implementation26 Jan 2023 Chao Pang, Jiang Wu, Jian Ding, Can Song, Gui-Song Xia

The tilted viewing nature of the off-nadir aerial images brings severe challenges to the building change detection (BCD) problem: the mismatch of the nearby buildings and the semantic ambiguity of the building facades.

Building change detection for remote sensing images Change Detection

Learning to See Through with Events

no code implementations5 Dec 2022 Lei Yu, Xiang Zhang, Wei Liao, Wen Yang, Gui-Song Xia

Although synthetic aperture imaging (SAI) can achieve the seeing-through effect by blurring out off-focus foreground occlusions while recovering in-focus occluded scenes from multi-view images, its performance is often deteriorated by dense occlusions and extreme lighting conditions.

NOPE-SAC: Neural One-Plane RANSAC for Sparse-View Planar 3D Reconstruction

1 code implementation30 Nov 2022 Bin Tan, Nan Xue, Tianfu Wu, Gui-Song Xia

This paper studies the challenging two-view 3D reconstruction in a rigorous sparse-view configuration, which is suffering from insufficient correspondences in the input image pairs for camera pose estimation.

3D Reconstruction Camera Pose Estimation +1

Level-S$^2$fM: Structure from Motion on Neural Level Set of Implicit Surfaces

1 code implementation CVPR 2023 Yuxi Xiao, Nan Xue, Tianfu Wu, Gui-Song Xia

This paper presents a neural incremental Structure-from-Motion (SfM) approach, Level-S$^2$fM, which estimates the camera poses and scene geometry from a set of uncalibrated images by learning coordinate MLPs for the implicit surfaces and the radiance fields from the established keypoint correspondences.

3D Reconstruction Camera Pose Estimation +2

Detecting Line Segments in Motion-blurred Images with Events

1 code implementation14 Nov 2022 Huai Yu, Hao Li, Wen Yang, Lei Yu, Gui-Song Xia

To robustly detect line segments over motion blurs, we propose to leverage the complementary information of images and events.

3D Reconstruction Line Segment Detection +1

Holistically-Attracted Wireframe Parsing: From Supervised to Self-Supervised Learning

1 code implementation24 Oct 2022 Nan Xue, Tianfu Wu, Song Bai, Fu-Dong Wang, Gui-Song Xia, Liangpei Zhang, Philip H. S. Torr

This article presents Holistically-Attracted Wireframe Parsing (HAWP), a method for geometric analysis of 2D images containing wireframes formed by line segments and junctions.

Self-Supervised Learning Wireframe Parsing

Anomaly Detection in Aerial Videos with Transformers

1 code implementation25 Sep 2022 Pu Jin, Lichao Mou, Gui-Song Xia, Xiao Xiang Zhu

In this paper, we create a new dataset, named DroneAnomaly, for anomaly detection in aerial videos.

Anomaly Detection

FuTH-Net: Fusing Temporal Relations and Holistic Features for Aerial Video Classification

no code implementations22 Sep 2022 Pu Jin, Lichao Mou, Yuansheng Hua, Gui-Song Xia, Xiao Xiang Zhu

Furthermore, the holistic features are refined by the multi-scale temporal relations in a novel fusion module for yielding more discriminative video representations.

Action Recognition Temporal Action Localization +1

Transformers in Remote Sensing: A Survey

no code implementations2 Sep 2022 Abdulaziz Amer Aleissaee, Amandeep Kumar, Rao Muhammad Anwer, Salman Khan, Hisham Cholakkal, Gui-Song Xia, Fahad Shahbaz Khan

Deep learning-based algorithms have seen a massive popularity in different areas of remote sensing image analysis over the past decade.

Enabling Country-Scale Land Cover Mapping with Meter-Resolution Satellite Imagery

1 code implementation1 Sep 2022 Xin-Yi Tong, Gui-Song Xia, Xiao Xiang Zhu

To validate the generalizability of our dataset and the proposed approach across different sensors and different geographical regions, we carry out land cover mapping on five megacities in China and six cities in other five Asian countries severally using: PlanetScope (3 m), Gaofen-1 (8 m), and Sentinel-2 (10 m) satellite images.

Land Cover Classification Pseudo Label +5

RFLA: Gaussian Receptive Field based Label Assignment for Tiny Object Detection

1 code implementation18 Aug 2022 Chang Xu, Jinwang Wang, Wen Yang, Huai Yu, Lei Yu, Gui-Song Xia

Then, instead of assigning samples with IoU or center sampling strategy, a new Receptive Field Distance (RFD) is proposed to directly measure the similarity between the Gaussian receptive field and ground truth.

Object object-detection +1

HoW-3D: Holistic 3D Wireframe Perception from a Single Image

1 code implementation15 Aug 2022 Wenchao Ma, Bin Tan, Nan Xue, Tianfu Wu, Xianwei Zheng, Gui-Song Xia

This paper studies the problem of holistic 3D wireframe perception (HoW-3D), a new task of perceiving both the visible 3D wireframes and the invisible ones from single-view 2D images.

Accurate Polygonal Mapping of Buildings in Satellite Imagery

1 code implementation1 Aug 2022 Bowen Xu, Jiakun Xu, Nan Xue, Gui-Song Xia

We addressed such an issue by exploiting the hierarchical supervision (of bottom-level vertices, mid-level line segments and the high-level regional masks) and proposed a novel interaction mechanism of feature embedding sourced from different levels of supervision signals to obtain reversible building masks for polygonal mapping of buildings.

OmniCity: Omnipotent City Understanding with Multi-level and Multi-view Images

no code implementations CVPR 2023 Weijia Li, Yawen Lai, Linning Xu, Yuanbo Xiangli, Jinhua Yu, Conghui He, Gui-Song Xia, Dahua Lin

More precisely, the OmniCity contains multi-view satellite images as well as street-level panorama and mono-view images, constituting over 100K pixel-wise annotated images that are well-aligned and collected from 25K geo-locations in New York City.

Instance Segmentation Segmentation +1

GLF-CR: SAR-Enhanced Cloud Removal with Global-Local Fusion

1 code implementation6 Jun 2022 Fang Xu, Yilei Shi, Patrick Ebel, Lei Yu, Gui-Song Xia, Wen Yang, Xiao Xiang Zhu

The challenge of the cloud removal task can be alleviated with the aid of Synthetic Aperture Radar (SAR) images that can penetrate cloud cover.

Cloud Removal

Learning to Extract Building Footprints from Off-Nadir Aerial Images

1 code implementation28 Apr 2022 Jinwang Wang, Lingxuan Meng, Weijia Li, Wen Yang, Lei Yu, Gui-Song Xia

In this paper, we propose an offset vector learning scheme, which turns the building footprint extraction problem in off-nadir images into an instance-level joint prediction problem of the building roof and its corresponding "roof to footprint" offset vector.

An Empirical Study of Remote Sensing Pretraining

2 code implementations6 Apr 2022 Di Wang, Jing Zhang, Bo Du, Gui-Song Xia, DaCheng Tao

To this end, we train different networks from scratch with the help of the largest RS scene recognition dataset up to now -- MillionAID, to obtain a series of RS pretrained backbones, including both convolutional neural networks (CNN) and vision transformers such as Swin and ViTAE, which have shown promising performance on computer vision tasks.

Aerial Scene Classification Building change detection for remote sensing images +5

Revisiting Document Image Dewarping by Grid Regularization

no code implementations CVPR 2022 Xiangwei Jiang, Rujiao Long, Nan Xue, Zhibo Yang, Cong Yao, Gui-Song Xia

This paper addresses the problem of document image dewarping, which aims at eliminating the geometric distortion in document images for document digitization.

Local Distortion Optical Flow Estimation

Partial Wasserstein Adversarial Network for Non-rigid Point Set Registration

no code implementations ICLR 2022 Zi-Ming Wang, Nan Xue, Ling Lei, Gui-Song Xia

To handle large point sets, we propose a scalable PDM algorithm by utilizing the efficient partial Wasserstein-1 (PW) discrepancy.

Aerial Scene Parsing: From Tile-level Scene Classification to Pixel-wise Semantic Labeling

no code implementations6 Jan 2022 Yang Long, Gui-Song Xia, Liangpei Zhang, Gong Cheng, Deren Li

Finally, we perform ASP by unifying the tile-level scene classification and object-based image analysis to achieve pixel-wise semantic labeling.

Aerial Scene Classification Benchmarking +4

Hidden Path Selection Network for Semantic Segmentation of Remote Sensing Images

no code implementations9 Dec 2021 Kunping Yang, Xin-Yi Tong, Gui-Song Xia, Weiming Shen, Liangpei Zhang

Targeting at depicting land covers with pixel-wise semantic categories, semantic segmentation in remote sensing images needs to portray diverse distributions over vast geographical locations, which is difficult to be achieved by the homogeneous pixel-wise forward paths in the architectures of existing deep models.

Semantic Segmentation

Motion Deblurring with Real Events

no code implementations ICCV 2021 Fang Xu, Lei Yu, Bishan Wang, Wen Yang, Gui-Song Xia, Xu Jia, Zhendong Qiao, Jianzhuang Liu

In this paper, we propose an end-to-end learning framework for event-based motion deblurring in a self-supervised manner, where real-world events are exploited to alleviate the performance degradation caused by data inconsistency.


Parsing Table Structures in the Wild

2 code implementations ICCV 2021 Rujiao Long, Wen Wang, Nan Xue, Feiyu Gao, Zhibo Yang, Yongpan Wang, Gui-Song Xia

In contrast to existing studies that mainly focus on parsing well-aligned tabular images with simple layouts from scanned PDF documents, we aim to establish a practical table structure parsing system for real-world scenarios where tabular input images are taken or scanned with severe deformation, bending or occlusions.

Object Detection

PlaneTR: Structure-Guided Transformers for 3D Plane Recovery

no code implementations ICCV 2021 Bin Tan, Nan Xue, Song Bai, Tianfu Wu, Gui-Song Xia

This paper presents a neural network built upon Transformers, namely PlaneTR, to simultaneously detect and reconstruct planes from a single image.


ReDet: A Rotation-equivariant Detector for Aerial Object Detection

4 code implementations CVPR 2021 Jiaming Han, Jian Ding, Nan Xue, Gui-Song Xia

More precisely, we incorporate rotation-equivariant networks into the detector to extract rotation-equivariant features, which can accurately predict the orientation and lead to a huge reduction of model size.

Ranked #19 on Object Detection In Aerial Images on DOTA (using extra training data)

Object object-detection +1

Deep Graph Matching under Quadratic Constraint

1 code implementation CVPR 2021 Quankai Gao, Fudong Wang, Nan Xue, Jin-Gang Yu, Gui-Song Xia

Recently, deep learning based methods have demonstrated promising results on the graph matching problem, by relying on the descriptive capability of deep features extracted on graph nodes.

Descriptive Graph Matching

Event-based Synthetic Aperture Imaging with a Hybrid Network

1 code implementation CVPR 2021 Xiang Zhang, Wei Liao, Lei Yu, Wen Yang, Gui-Song Xia

Synthetic aperture imaging (SAI) is able to achieve the see through effect by blurring out the off-focus foreground occlusions and reconstructing the in-focus occluded targets from multi-view images.

Decoder Style Transfer

Bidirectional Multi-scale Attention Networks for Semantic Segmentation of Oblique UAV Imagery

1 code implementation5 Feb 2021 Ye Lyu, George Vosselman, Gui-Song Xia, Michael Ying Yang

Semantic segmentation for aerial platforms has been one of the fundamental scene understanding task for the earth observation.

Earth Observation Scene Understanding +2

Tiny Object Detection in Aerial Images

1 code implementation International Conference on Pattern Recognition (ICPR) 2021 Jinwang Wang, Wen Yang, Haowen Guo, Ruixiang Zhang, Gui-Song Xia

To build a benchmark for tiny object detection in aerial images, we evaluate the state-of-the-art object detectors on our AI-TOD dataset.

Object object-detection +1

3D Building Reconstruction From Monocular Remote Sensing Images

no code implementations ICCV 2021 Weijia Li, Lingxuan Meng, Jinwang Wang, Conghui He, Gui-Song Xia, Dahua Lin

3D building reconstruction from monocular remote sensing imagery is an important research problem and an economic solution to large-scale city modeling, compared with reconstruction from LiDAR data and multi-view imagery.

3D Reconstruction Model Optimization

Unmixing Convolutional Features for Crisp Edge Detection

1 code implementation19 Nov 2020 Linxi Huan, Nan Xue, Xianwei Zheng, wei he, Jianya Gong, Gui-Song Xia

This paper presents a context-aware tracing strategy (CATS) for crisp edge detection with deep edge detectors, based on an observation that the localization ambiguity of deep edge detectors is mainly caused by the mixing phenomenon of convolutional neural networks: feature mixing in edge classification and side mixing during fusing side predictions.

Edge Classification Edge Detection

Semantic Change Detection with Asymmetric Siamese Networks

1 code implementation12 Oct 2020 Kunping Yang, Gui-Song Xia, Zicheng Liu, Bo Du, Wen Yang, Marcello Pelillo, Liangpei Zhang

Given two multi-temporal aerial images, semantic change detection aims to locate the land-cover variations and identify their change types with pixel-wise boundaries.

Change Detection Management

Mixed Noise Removal with Pareto Prior

no code implementations27 Aug 2020 Zhou Liu, Lei Yu, Gui-Song Xia, Hong Sun

To address this problem, we exploit the Pareto distribution as the priori of the weighting matrix, based on which an accurate and robust weight estimator is proposed for mixed noise removal.


Align Deep Features for Oriented Object Detection

3 code implementations21 Aug 2020 Jiaming Han, Jian Ding, Jie Li, Gui-Song Xia

However most of existing methods rely on heuristically defined anchors with different scales, angles and aspect ratios and usually suffer from severe misalignment between anchor boxes and axis-aligned convolutional features, which leads to the common inconsistency between the classification score and localization accuracy.

Ranked #23 on Object Detection In Aerial Images on DOTA (using extra training data)

Object object-detection +2

Event Enhanced High-Quality Image Recovery

1 code implementation ECCV 2020 Bishan Wang, Jingwei He, Lei Yu, Gui-Song Xia, Wen Yang

To recover high-quality intensity images, one should address both denoising and super-resolution problems for event cameras.

Denoising Sparse Learning +2

Implicit Euler ODE Networks for Single-Image Dehazing

no code implementations13 Jul 2020 Jiawei Shen, Zhuoyan Li, Lei Yu, Gui-Song Xia, Wen Yang

Deep convolutional neural networks (CNN) have been applied for image dehazing tasks, where the residual network (ResNet) is often adopted as the basic component to avoid the vanishing gradient problem.

Image Dehazing Single Image Dehazing

On Creating Benchmark Dataset for Aerial Image Interpretation: Reviews, Guidances and Million-AID

1 code implementation22 Jun 2020 Yang Long, Gui-Song Xia, Shengyang Li, Wen Yang, Michael Ying Yang, Xiao Xiang Zhu, Liangpei Zhang, Deren Li

After reviewing existing benchmark datasets in the research community of RS image interpretation, this article discusses the problem of how to efficiently prepare a suitable benchmark dataset for RS image interpretation.

General Classification Image Classification +1

Remote Sensing Image Scene Classification Meets Deep Learning: Challenges, Methods, Benchmarks, and Opportunities

no code implementations3 May 2020 Gong Cheng, Xingxing Xie, Junwei Han, Lei Guo, Gui-Song Xia

Considering the rapid evolution of this field, this paper provides a systematic survey of deep learning methods for remote sensing image scene classification by covering more than 160 papers.

Classification General Classification +2

FGN: Fully Guided Network for Few-Shot Instance Segmentation

no code implementations CVPR 2020 Zhibo Fan, Jin-Gang Yu, Zhihao Liang, Jiarong Ou, Changxin Gao, Gui-Song Xia, Yuanqing Li

Few-shot instance segmentation (FSIS) conjoins the few-shot learning paradigm with general instance segmentation, which provides a possible way of tackling instance segmentation in the lack of abundant labeled data for training.

Few-Shot Learning Instance Segmentation +2

Zero-Assignment Constraint for Graph Matching with Outliers

1 code implementation CVPR 2020 Fu-Dong Wang, Nan Xue, Jin-Gang Yu, Gui-Song Xia

Graph matching (GM), as a longstanding problem in computer vision and pattern recognition, still suffers from numerous cluttered outliers in practical applications.

Graph Matching valid

Fisheye Distortion Rectification from Deep Straight Lines

no code implementations25 Mar 2020 Zhu-Cun Xue, Nan Xue, Gui-Song Xia

This paper presents a novel line-aware rectification network (LaRecNet) to address the problem of fisheye distortion rectification based on the classical observation that straight lines in 3D space should be still straight in image planes.


Semantic Change Pattern Analysis

no code implementations7 Mar 2020 Wensheng Cheng, Yan Zhang, Xu Lei, Wen Yang, Gui-Song Xia

Change detection is an important problem in vision field, especially for aerial images.

Change Detection

Holistically-Attracted Wireframe Parsing

1 code implementation CVPR 2020 Nan Xue, Tianfu Wu, Song Bai, Fu-Dong Wang, Gui-Song Xia, Liangpei Zhang, Philip H. S. Torr

For computing line segment proposals, a novel exact dual representation is proposed which exploits a parsimonious geometric reparameterization for line segments and forms a holistic 4-dimensional attraction field map for an input image.

Line Segment Detection Wireframe Parsing

Plug & Play Convolutional Regression Tracker for Video Object Detection

2 code implementations2 Mar 2020 Ye Lyu, Michael Ying Yang, George Vosselman, Gui-Song Xia

As the tracker reuses the features from the detector, it is a very light-weighted increment to the detection network.

Object object-detection +2

Matching Neuromorphic Events and Color Images via Adversarial Learning

no code implementations2 Mar 2020 Fang Xu, ShiJie Lin, Wen Yang, Lei Yu, Dengxin Dai, Gui-Song Xia

The event camera has appealing properties: high dynamic range, low latency, low power consumption and low memory usage, and thus provides complementariness to conventional frame-based cameras.

Image Retrieval Retrieval

An Urban Water Extraction Method Combining Deep Learning and Google Earth Engine

no code implementations23 Dec 2019 Yudie Wang, Zhiwei Li, Chao Zeng, Gui-Song Xia, Huanfeng Shen

In this paper, we proposed a new method to combine Google Earth Engine (GEE) with multiscale convolutional neural network (MSCNN) to extract urban water from Landsat images, which is summarized as offline training and online prediction (OTOP).

Change Detection Management

Learning Regional Attraction for Line Segment Detection

no code implementations18 Dec 2019 Nan Xue, Song Bai, Fu-Dong Wang, Gui-Song Xia, Tianfu Wu, Liangpei Zhang, Philip H. S. Torr

Given a line segment map, the proposed regional attraction first establishes the relationship between line segments and regions in the image lattice.

Line Segment Detection

Conditional Generative ConvNets for Exemplar-based Texture Synthesis

1 code implementation17 Dec 2019 Zi-Ming Wang, Meng-Han Li, Gui-Song Xia

Given a texture exemplar, the cgCNN model defines a conditional distribution using deep statistics of a ConvNet, and synthesize new textures by sampling from the conditional distribution.

Texture Synthesis

Gliding vertex on the horizontal bounding box for multi-oriented object detection

1 code implementation21 Nov 2019 Yongchao Xu, Mingtao Fu, Qimeng Wang, Yukang Wang, Kai Chen, Gui-Song Xia, Xiang Bai

Yet, the widely adopted horizontal bounding box representation is not appropriate for ubiquitous oriented objects such as objects in aerial images and scene texts.

Ranked #43 on Object Detection In Aerial Images on DOTA (using extra training data)

Object object-detection +5

LIP: Learning Instance Propagation for Video Object Segmentation

no code implementations30 Sep 2019 Ye Lyu, George Vosselman, Gui-Song Xia, Michael Ying Yang

In recent years, the task of segmenting foreground objects from background in a video, i. e. video object segmentation (VOS), has received considerable attention.

Data Augmentation Instance Segmentation +5

iSAID: A Large-scale Dataset for Instance Segmentation in Aerial Images

3 code implementations30 May 2019 Syed Waqas Zamir, Aditya Arora, Akshita Gupta, Salman Khan, Guolei Sun, Fahad Shahbaz Khan, Fan Zhu, Ling Shao, Gui-Song Xia, Xiang Bai

Compared to existing small-scale aerial image based instance segmentation datasets, iSAID contains 15$\times$ the number of object categories and 5$\times$ the number of instances.

Instance Segmentation Object +4

Learning to Calibrate Straight Lines for Fisheye Image Rectification

no code implementations CVPR 2019 Zhu-Cun Xue, Nan Xue, Gui-Song Xia, Weiming Shen

This paper presents a new deep-learning based method to simultaneously calibrate the intrinsic parameters of fisheye lens and rectify the distorted images.

A Functional Representation for Graph Matching

1 code implementation16 Jan 2019 Fu-Dong Wang, Gui-Song Xia, Nan Xue, Yi-Peng Zhang, Marcello Pelillo

In this paper, we present a functional representation for graph matching (FRGM) that aims to provide more geometric insights on the problem and reduce the space and time complexities of corresponding algorithms.

Graph Matching

Mini-Unmanned Aerial Vehicle-Based Remote Sensing: Techniques, Applications, and Prospects

no code implementations19 Dec 2018 Tian-Zhu Xiang, Gui-Song Xia, Liangpei Zhang

We hope this paper will provide remote-sensing researchers an overall picture of recent UAV-based remote sensing developments and help guide the further research on this topic.

Learning RoI Transformer for Detecting Oriented Objects in Aerial Images

1 code implementation1 Dec 2018 Jian Ding, Nan Xue, Yang Long, Gui-Song Xia, Qikai Lu

Especially when detecting densely packed objects in aerial images, methods relying on horizontal proposals for common object detection often introduce mismatches between the Region of Interests (RoIs) and objects.

Ranked #49 on Object Detection In Aerial Images on DOTA (using extra training data)

General Classification Object +4

GeoSay: A Geometric Saliency for Extracting Buildings in Remote Sensing Images

no code implementations7 Nov 2018 Gui-Song Xia, Jin Huang, Nan Xue, Qikai Lu, Xiaoxiang Zhu

More precisely, given an image, the geometric saliency is derived from a mid-level geometric representations based on meaningful junctions that can locally describe geometrical structures of images.

Extracting Buildings In Remote Sensing Images

UAVid: A Semantic Segmentation Dataset for UAV Imagery

3 code implementations24 Oct 2018 Ye Lyu, George Vosselman, Gui-Song Xia, Alper Yilmaz, Michael Ying Yang

There already exist several semantic segmentation datasets for comparison among semantic segmentation methods in complex urban scenes, such as the Cityscapes and CamVid datasets, where the side views of the objects are captured with a camera mounted on the driving car.

4k Autonomous Driving +4

Texture Mixing by Interpolating Deep Statistics via Gaussian Models

no code implementations29 Jul 2018 Zi-Ming Wang, Gui-Song Xia, Yi-Peng Zhang

More precisely, we first reveal that the statistics used in existing deep models can be unified using a stationary Gaussian scheme.

Style Transfer Texture Synthesis

Adaptively Transforming Graph Matching

no code implementations ECCV 2018 Fu-Dong Wang, Nan Xue, Yi-Peng Zhang, Xiang Bai, Gui-Song Xia

Due to an efficient Frank-Wolfe method-based optimization strategy, we can handle graphs with hundreds and thousands of nodes within an acceptable amount of time.

Domain Adaptation Graph Matching

Land-Cover Classification with High-Resolution Remote Sensing Images Using Transferable Deep Models

no code implementations16 Jul 2018 Xin-Yi Tong, Gui-Song Xia, Qikai Lu, Huanfeng Shen, Shengyang Li, Shucheng You, Liangpei Zhang

The main idea is to rely on deep neural networks for presenting the contextual information contained in different types of land-covers and propose a pseudo-labeling and sample selection scheme for improving the transferability of deep models.

Classification Domain Adaptation +6

Large-scale Land Cover Classification in GaoFen-2 Satellite Imagery

no code implementations4 Jun 2018 Xin-Yi Tong, Qikai Lu, Gui-Song Xia, Liangpei Zhang

Many significant applications need land cover information of remote sensing images that are acquired from different areas and times, such as change detection and disaster monitoring.

Change Detection Classification +2

Recent advances and opportunities in scene classification of aerial images with deep models

no code implementations4 Jun 2018 Fan Hu, Gui-Song Xia, Wen Yang, Liangpei Zhang

Scene classification is a fundamental task in interpretation of remote sensing images, and has become an active research topic in remote sensing community due to its important role in a wide range of applications.

Classification Diversity +2

Accurate Building Detection in VHR Remote Sensing Images using Geometric Saliency

no code implementations4 Jun 2018 Jin Huang, Gui-Song Xia, Fan Hu, Liangpei Zhang

This paper aims to address the problem of detecting buildings from remote sensing images with very high resolution (VHR).

AID++: An Updated Version of AID on Scene Classification

no code implementations3 Jun 2018 Pu Jin, Gui-Song Xia, Fan Hu, Qikai Lu, Liangpei Zhang

Aerial image scene classification is a fundamental problem for understanding high-resolution remote sensing images and has become an active research task in the field of remote sensing due to its important role in a wide range of applications.

Aerial Scene Classification Classification +3

Learning the Synthesizability of Dynamic Texture Samples

no code implementations3 Feb 2018 Feng Yang, Gui-Song Xia, Dengxin Dai, Liangpei Zhang

In this paper, we investigate the synthesizability of dynamic texture samples: {\em given a dynamic texture sample, how synthesizable it is by using EDTS, and which EDTS method is the most suitable to synthesize it?}

regression Texture Synthesis

Deep learning in remote sensing: a review

1 code implementation11 Oct 2017 Xiao Xiang Zhu, Devis Tuia, Lichao Mou, Gui-Song Xia, Liangpei Zhang, Feng Xu, Friedrich Fraundorfer

In this article, we analyze the challenges of using deep learning for remote sensing data analysis, review the recent advances, and provide resources to make deep learning in remote sensing ridiculously simple to start with.

Exploiting Deep Features for Remote Sensing Image Retrieval: A Systematic Investigation

no code implementations23 Jul 2017 Xin-Yi Tong, Gui-Song Xia, Fan Hu, Yanfei Zhong, Mihai Datcu, Liangpei Zhang

Over the past two decades, a large amount of research on this task has been carried out, which mainly focuses on the following three core issues: feature extraction, similarity metric and relevance feedback.

Image Retrieval Retrieval

Anisotropic-Scale Junction Detection and Matching for Indoor Images

no code implementations16 Mar 2017 Nan Xue, Gui-Song Xia, Xiang Bai, Liangpei Zhang, Weiming Shen

This paper presents a novel approach to junction detection and characterization that exploits the locally anisotropic geometries of a junction and estimates the scales of these geometries using an \emph{a contrario} model.

Junction Detection

Image Stitching by Line-guided Local Warping with Global Similarity Constraint

no code implementations25 Feb 2017 Tian-Zhu Xiang, Gui-Song Xia, Xiang Bai, Liangpei Zhang

On one hand, the line features are integrated into a local warping model through a designed weight function.

Image Stitching

Texture Characterization by Using Shape Co-occurrence Patterns

no code implementations10 Feb 2017 Gui-Song Xia, Gang Liu, Xiang Bai, Liangpei Zhang

In contrast with existing works, the proposed method not only inherits the strong ability to depict geometrical aspects of textures and the high robustness to variations of imaging conditions from the shape-based method, but also provides a flexible way to consider shape relationships and to compute high-order statistics on the tree.

Descriptive Texture Classification

Multi-feature combined cloud and cloud shadow detection in GaoFen-1 wide field of view imagery

no code implementations17 Jun 2016 Zhiwei Li, Huanfeng Shen, Huifang Li, Gui-Song Xia, Paolo Gamba, Liangpei Zhang

In this paper, an automatic multi-feature combined (MFC) method is proposed for cloud and cloud shadow detection in GF-1 WFV imagery.

Cloud Detection Earth Observation +1

Image stitching with perspective-preserving warping

no code implementations17 May 2016 Tian-Zhu Xiang, Gui-Song Xia, Liangpei Zhang

Image stitching algorithms often adopt the global transformation, such as homography, and work well for planar scenes or parallax free camera motions.

Image Stitching

Texture Synthesis Through Convolutional Neural Networks and Spectrum Constraints

2 code implementations4 May 2016 Gang Liu, Yann Gousseau, Gui-Song Xia

This paper presents a significant improvement for the synthesis of texture images using convolutional neural networks (CNNs), making use of constraints on the Fourier spectrum of the results.

Texture Synthesis

Dense v.s. Sparse: A Comparative Study of Sampling Analysis in Scene Classification of High-Resolution Remote Sensing Imagery

no code implementations4 Feb 2015 Jingwen Hu, Gui-Song Xia, Fan Hu, Liangpei Zhang

The experimental results on two commonly used datasets show that dense sampling has the best performance among all the strategies but with high spatial and computational complexity, random sampling gives better or comparable results than other sparse sampling methods, like the sophisticated multi-scale key-point operators and the saliency-based methods which are intensively studied and commonly used recently.

Classification General Classification +2

Meaningful Objects Segmentation from SAR Images via A Multi-Scale Non-Local Active Contour Model

no code implementations17 Jan 2015 Gui-Song Xia, Gang Liu, Wen Yang

The segmentation of synthetic aperture radar (SAR) images is a longstanding yet challenging task, not only because of the presence of speckle, but also due to the variations of surface backscattering properties in the images.

Image Segmentation Segmentation +1

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