The ability to efficiently utilize crowdsourced visual data carries immense potential for the domains of large scale dynamic mapping and autonomous driving. However, state-of-the-art methods for crowdsourced 3D mapping assume prior knowledge of camera intrinsics. In this work, we propose a framework that estimates the 3D positions of semantically meaningful landmarks such as traffic signs without assuming known camera intrinsics, using only monocular color camera and GPS. We utilize multi-view geometry as well as deep learning based self-calibration, depth, and ego-motion estimation for traffic sign positioning, and show that combining their strengths is important for increasing the map coverage. To facilitate research on this task, we construct and make available a KITTI based 3D traffic sign ground truth positioning dataset. Using our proposed framework, we achieve an average single-journey relative and absolute positioning accuracy of 39cm and 1.26m respectively, on this dataset.
Advanced Research Lab, NavInfo Europe（NavInfo欧洲先进研究实验室）
Autonomous vehicles and driver assistance systems utilize maps of 3D semantic landmarks for improved decision making. However, scaling the mapping process as well as regularly updating such maps come with a huge cost. Crowdsourced mapping of these landmarks such as traffic sign positions provides an appealing alternative. The state-of-the-art approaches to crowdsourced mapping use ground truth camera parameters, which may not always be known or may change over time. In this work, we demonstrate an approach to computing 3D traffic sign positions without knowing the camera focal lengths, princip…
CSMapping: Scalable Crowdsourced Semantic Mapping and Topology Inference for Autonomous Driving
the Department of Electronic and Computer Engineering, the Hong Kong University of Science and Technology, Hong Kong, China（电子与计算机工程系，香港科技大学，香港，中国）；the Academy for Engineering and Technology, Fudan University, Shanghai, China（工程与技术学院，复旦大学，上海，中国）；Zhuoyu Technology Co., Ltd., Shenzhen, China（珠海优创科技有限公司，深圳，中国）
Qualcomm Technologies, Inc.（高通技术公司）；Qualcomm Austria Research Center GmbH（高通奥地利研究中心有限公司）
Autonomous vehicles rely on precise high definition (HD) 3d maps for navigation. This paper presents the mapping component of an end-to-end system for crowdsourcing precise 3d maps with semantically meaningful landmarks such as traffic signs (6 dof pose, shape and size) and traffic lanes (3d splines). The system uses consumer grade parts, and in particular, relies on a single front facing camera and a consumer grade GPS. Using real-time sign and lane triangulation on-device in the vehicle, with offline sign/lane clustering across multiple journeys and offline Bundle Adjustment across multiple …
Representation learning approaches require a massive amount of discriminative training data, which is unavailable in many scenarios, such as healthcare, smart city, education, etc. In practice, people refer to crowdsourcing to get annotated labels. However, due to issues like data privacy, budget limitation, shortage of domain-specific annotators, the number of crowdsourced labels is still very limited. Moreover, because of annotators' diverse expertise, crowdsourced labels are often inconsistent. Thus, directly applying existing supervised representation learning (SRL) algorithms may easily g…
Successful flood recovery and evacuation require access to reliable flood depth information. Most existing flood mapping tools do not provide real-time flood maps of inundated streets in and around residential areas. In this paper, a deep convolutional network is used to determine flood depth with high spatial resolution by analyzing crowdsourced images of submerged traffic signs. Testing the model on photos from a recent flood in the U.S. and Canada yields a mean absolute error of 6.978 in., which is on par with previous studies, thus demonstrating the applicability of this approach to low-co…
Lancaster University（兰卡斯特大学）；University of Bath（巴斯大学）；University of Oxford（牛津大学）
High-resolution satellite imagery available immediately after disaster events is crucial for response planning as it facilitates broad situational awareness of critical infrastructure status such as building damage, flooding, and obstructions to access routes. Damage mapping at this scale would require hundreds of expert person-hours. However, a combination of crowdsourcing and recent advances in deep learning reduces the effort needed to just a few hours in real time. Asking volunteers to place point marks, as opposed to shapes of actual damaged areas, significantly decreases the required ana…
University of Freiburg（弗莱堡大学）；Federal University of Rio Grande（里奥格兰德联邦大学）；University of Technology Nuremberg（纽伦堡工业大学）
Bird's-Eye-View (BEV) semantic maps have become an essential component of automated driving pipelines due to the rich representation they provide for decision-making tasks. However, existing approaches for generating these maps still follow a fully supervised training paradigm and hence rely on large amounts of annotated BEV data. In this work, we address this limitation by proposing the first self-supervised approach for generating a BEV semantic map using a single monocular image from the frontal view (FV). During training, we overcome the need for BEV ground truth annotations by leveraging …
Mapping the landscape of histomorphological cancer phenotypes using self-supervised learning on unlabeled, unannotated pathology slides
University of Glasgow（格拉斯哥大学）；New York University School of Medicine（纽约大学医学院）；New York University Langone Health（纽约大学朗格尼医学中心）；Karolinska Institutet（卡罗林斯卡学院）；University College London Hospital（伦敦大学学院医院）
Deep learning is revolutionizing the mapping industry. Under lightweight human curation, computer has generated almost half of the roads in Thailand on OpenStreetMap (OSM) using high-resolution aerial imagery. Bing maps are displaying 125 million computer-generated building polygons in the U.S. While tremendously more efficient than manual mapping, one cannot map out everything from the air. Especially for roads, a small prediction gap by image occlusion renders the entire road useless for routing. Misconnections can be more dangerous. Therefore computer-based mapping often requires local veri…
Decoding the Disaster: Multi-Task Geospatial Reasoning with Vision-Language Models and Crowdsourced Imagery for Disaster Mapping
Shandong University of Science and Technology（山东科技大学）；Technical University of Munich（慕尼黑工业大学）；Wuhan University（武汉大学）；Tsinghua University（清华大学）；Helmholtz-Zentrum Dresden-Rossendorf（亥姆霍兹德累斯顿罗森多夫研究中心）；University of Iceland（冰岛大学）
Machine learning analysis of longitudinal neuroimaging data is typically based on supervised learning, which requires a large number of ground-truth labels to be informative. As ground-truth labels are often missing or expensive to obtain in neuroscience, we avoid them in our analysis by combing factor disentanglement with self-supervised learning to identify changes and consistencies across the multiple MRIs acquired of each individual over time. Specifically, we propose a new definition of disentanglement by formulating a multivariate mapping between factors (e.g., brain age) associated with…
Mines Paris - PSL University（巴黎国立高等矿业学校 - PSL大学）；LuciSun（LuciSun公司）；RTE France（法国输电网络公司）；BDPV（BDPV机构）
Photovoltaic (PV) energy generation plays a crucial role in the energy transition. Small-scale PV installations are deployed at an unprecedented pace, and their integration into the grid can be challenging since public authorities often lack quality data about them. Overhead imagery is increasingly used to improve the knowledge of residential PV installations with machine learning models capable of automatically mapping these installations. However, these models cannot be easily transferred from one region or data source to another due to differences in image acquisition. To address this issue…
University of Waterloo（滑铁卢大学）；Vector Institute（向量研究所）
In this paper, we present a new algorithm for semi-supervised representation learning. In this algorithm, we first find a vector representation for the labels of the data points based on their local positions in the space. Then, we map the data to lower-dimensional space using a linear transformation such that the dependency between the transformed data and the assigned labels is maximized. In fact, we try to find a mapping that is as discriminative as possible. The approach will use Hilber-Schmidt Independence Criterion (HSIC) as the dependence measure. We also present a kernelized version of…
KU Leuven（鲁汶大学）；Centre Tecnologic Telecomunicacions Catalunya（加泰罗尼亚电信技术中心）
Massive multiple input multiple output (MIMO) systems are typically designed under the assumption of linear power amplifiers (PAs). However, PAs are typically most energy-efficient when operating close to their saturation point, where they cause non-linear distortion. Moreover, when using conventional precoders, this distortion coherently combines at the user locations, limiting performance. As such, when designing an energy-efficient massive MIMO system, this distortion has to be managed. In this work, we propose the use of a neural network (NN) to learn the mapping between the channel matrix…
Affect modeling is viewed, traditionally, as the process of mapping measurable affect manifestations from multiple modalities of user input to affect labels. That mapping is usually inferred through end-to-end (manifestation-to-affect) machine learning processes. What if, instead, one trains general, subject-invariant representations that consider affect information and then uses such representations to model affect? In this paper we assume that affect labels form an integral part, and not just the training signal, of an affect representation and we explore how the recent paradigm of contrasti…
A Decade of PhotoMappers: A Longitudinal Study of Crowdsourced Disaster Photos Geolocalization with Vision-Language Models and Geospatial Reasoning
National University of Singapore（新加坡国立大学）；College of Geodesy and Geomatics, Shandong University of Science and Technology（山东科技大学测绘与空间信息学院）；University of the Bundeswehr Munich（慕尼黑联邦国防军大学）；Wuhan University（武汉大学）；University of Florida（佛罗里达大学）；Institute of Remote Sensing and GIS, Peking University（北京大学遥感与地理信息系统研究所）；Department of Architecture, National University of Singapore（新加坡国立大学建筑系）；Department of Real Estate, National University of Singapore（新加坡国立大学房地产系）
We present the first utterly self-supervised network for dense correspondence mapping between non-isometric shapes. The task of alignment in non-Euclidean domains is one of the most fundamental and crucial problems in computer vision. As 3D scanners can generate highly complex and dense models, the mission of finding dense mappings between those models is vital. The novelty of our solution is based on a cyclic mapping between metric spaces, where the distance between a pair of points should remain invariant after the full cycle. As the same learnable rules that generate the point-wise descript…
Institute of Cognitive Science（认知科学研究所）；University of Osnabrück（奥斯纳布吕克大学）
Most artificial neural networks used for object detection and recognition are trained in a fully supervised setup. This is not only very resource consuming as it requires large data sets of labeled examples but also very different from how humans learn. We introduce a setup in which an artificial agent first learns in a simulated world through self-supervised exploration. Following this, the representations learned through interaction with the world can be used to associate semantic concepts such as different types of doors. To do this, we use a method we call fast concept mapping which uses c…
Scene understanding is an important capability for robots acting in unstructured environments. While most SLAM approaches provide a geometrical representation of the scene, a semantic map is necessary for more complex interactions with the surroundings. Current methods treat the semantic map as part of the geometry which limits scalability and accuracy. We propose to represent the semantic map as a geometrical mesh and a semantic texture coupled at independent resolution. The key idea is that in many environments the geometry can be greatly simplified without loosing fidelity, while semantic i…
Pests and diseases are relevant factors for production losses in agriculture and, therefore, promote a huge investment in the prevention and detection of its causative agents. In many countries, Integrated Pest Management is the most widely used process to prevent and mitigate the damages caused by pests and diseases in citrus crops. However, its results are credited by humans who visually inspect the orchards in order to identify the disease symptoms, insects and mite pests. In this context, we design a weakly supervised learning process guided by saliency maps to automatically select regions…
Artificial Intelligence eXploration Research Center, The University of Electro Communications（电气通信大学人工智能探索研究中心）
To minimize the annotation costs associated with the training of semantic segmentation models, researchers have extensively investigated weakly-supervised segmentation approaches. In the current weakly-supervised segmentation methods, the most widely adopted approach is based on visualization. However, the visualization results are not generally equal to semantic segmentation. Therefore, to perform accurate semantic segmentation under the weakly supervised condition, it is necessary to consider the mapping functions that convert the visualization results into semantic segmentation. For such ma…
OPPO US Research Center, InnoPeak Technology（OPPO美国研究中心，InnoPeak科技）
We present a robust and accurate depth refinement system, named GeoRefine, for geometrically-consistent dense mapping from monocular sequences. GeoRefine consists of three modules: a hybrid SLAM module using learning-based priors, an online depth refinement module leveraging self-supervision, and a global mapping module via TSDF fusion. The proposed system is online by design and achieves great robustness and accuracy via: (i) a robustified hybrid SLAM that incorporates learning-based optical flow and/or depth; (ii) self-supervised losses that leverage SLAM outputs and enforce long-term geomet…
This paper reviews the NTIRE 2020 challenge on video quality mapping (VQM), which addresses the issues of quality mapping from source video domain to target video domain. The challenge includes both a supervised track (track 1) and a weakly-supervised track (track 2) for two benchmark datasets. In particular, track 1 offers a new Internet video benchmark, requiring algorithms to learn the map from more compressed videos to less compressed videos in a supervised training manner. In track 2, algorithms are required to learn the quality mapping from one device to another when their quality varies…
University of Science and Technology of China（中国科学技术大学）；Microsoft Research Asia（微软亚洲研究院）
Recent image-to-image translation works have been transferred from supervised to unsupervised settings due to the expensive cost of capturing or labeling large amounts of paired data. However, current unsupervised methods using the cycle-consistency constraint may not find the desired mapping, especially for difficult translation tasks. On the other hand, a small number of paired data are usually accessible. We therefore introduce a general framework for semi-supervised image translation. Unlike previous works, our main idea is to learn the translation over the latent feature space instead of …
The raw-RGB colors of a camera sensor vary due to the spectral sensitivity differences across different sensor makes and models. This paper focuses on the task of mapping between different sensor raw-RGB color spaces. Prior work addressed this problem using a pairwise calibration to achieve accurate color mapping. Although being accurate, this approach is less practical as it requires: (1) capturing pair of images by both camera devices with a color calibration object placed in each new scene; (2) accurate image alignment or manual annotation of the color calibration object. This paper aims to…
From Time-series Generation, Model Selection to Transfer Learning: A Comparative Review of Pixel-wise Approaches for Large-scale Crop Mapping
College of Forest Resources and Environmental Science, Michigan Technological University（密歇根理工大学森林资源与环境科学学院）；Warnell School of Forestry and Natural Resources, University of Georgia（佐治亚大学沃内尔林业与自然资源学院）；Annis Water Resources Institute, Grand Valley State University（大峡谷州立大学安尼斯水资源研究所）；BioSense Institute（生物感知研究所）；Department of Agricultural, Food, and Resource Economics, Michigan State University（密歇根州立大学农业、食品与资源经济学系）
University of Minnesota（明尼苏达大学）；University of Pittsburgh（匹兹堡大学）
Collecting large annotated datasets in Remote Sensing is often expensive and thus can become a major obstacle for training advanced machine learning models. Common techniques of addressing this issue, based on the underlying idea of pre-training the Deep Neural Networks (DNN) on freely available large datasets, cannot be used for Remote Sensing due to the unavailability of such large-scale labeled datasets and the heterogeneity of data sources caused by the varying spatial and spectral resolution of different sensors. Self-supervised learning is an alternative approach that learns feature repr…
Technical University of Munich（慕尼黑工业大学）；German Aerospace Center (DLR)（德国航空航天中心（DLR））
Fully automatic large-scale land cover mapping belongs to the core challenges addressed by the remote sensing community. Usually, the basis of this task is formed by (supervised) machine learning models. However, in spite of recent growth in the availability of satellite observations, accurate training data remains comparably scarce. On the other hand, numerous global land cover products exist and can be accessed often free-of-charge. Unfortunately, these maps are typically of a much lower resolution than modern day satellite imagery. Besides, they always come with a significant amount of nois…
Google Research India（谷歌印度研究院）；Google LLC（谷歌有限责任公司）
Self- and semi-supervised machine learning techniques leverage unlabeled data for improving downstream task performance. These methods are especially valuable for remote sensing tasks where producing labeled ground truth datasets can be prohibitively expensive but there is easy access to a wealth of unlabeled imagery. We perform a rigorous evaluation of SimCLR, a self-supervised method, and FixMatch, a semi-supervised method, on three remote sensing tasks: riverbed segmentation, land cover mapping, and flood mapping. We quantify performance improvements on these remote sensing segmentation tas…
The Chinese University of Hong Kong（香港中文大学）；SenseTime Research（商汤科技研究院）；Zhejiang University（浙江大学）
The correct ego-motion estimation basically relies on the understanding of correspondences between adjacent LiDAR scans. However, given the complex scenarios and the low-resolution LiDAR, finding reliable structures for identifying correspondences can be challenging. In this paper, we delve into structure reliability for accurate self-supervised ego-motion estimation and aim to alleviate the influence of unreliable structures in training, inference and mapping phases. We improve the self-supervised LiDAR odometry substantially from three aspects: 1) A two-stage odometry estimation network is d…
Geographically-Weighted Weakly Supervised Bayesian High-Resolution Transformer for 200m Resolution Pan-Arctic Sea Ice Concentration Mapping and Uncertainty Estimation using Sentinel-1, RCM, and AMSR2 Data
Department of Geomatics Engineering, Schulich School of Engineering, University of Calgary（地质工程系，Schulich 工程学院，卡尔加里大学）
We propose a new grayscale image denoiser, dubbed as Neural Affine Image Denoiser (Neural AIDE), which utilizes neural network in a novel way. Unlike other neural network based image denoising methods, which typically apply simple supervised learning to learn a mapping from a noisy patch to a clean patch, we formulate to train a neural network to learn an \emph{affine} mapping that gets applied to a noisy pixel, based on its context. Our formulation enables both supervised training of the network from the labeled training dataset and adaptive fine-tuning of the network parameters using the giv…
Fudan University（复旦大学）；Shanghai University of Finance and Economics（上海财经大学）；Deakin University（迪肯大学）
Weakly Supervised Object Localization (WSOL) aims to localize objects with image-level supervision. Existing works mainly rely on Class Activation Mapping (CAM) derived from a classification model. However, CAM-based methods usually focus on the most discriminative parts of an object (i.e., incomplete localization problem). In this paper, we empirically prove that this problem is associated with the mixup of the activation values between less discriminative foreground regions and the background. To address it, we propose Class RE-Activation Mapping (CREAM), a novel clustering-based approach to…
Delft University of Technology（代尔夫特理工大学）；University of Copenhagen（哥本哈根大学）
The original problem of supervised classification considers the task of automatically assigning objects to their respective classes on the basis of numerical measurements derived from these objects. Classifiers are the tools that implement the actual functional mapping from these measurements---also called features or inputs---to the so-called class label---or output. The fields of pattern recognition and machine learning study ways of constructing such classifiers. The main idea behind supervised methods is that of learning from examples: given a number of example input-output relations, to w…
The Chinese University of Hong Kong（香港中文大学）；Philip Healthcare（飞利浦医疗）；Illuminatio Medical Technology Limited（Illuminatio医疗科技有限公司）
$T_{1ρ}$ mapping is a promising quantitative MRI technique for the non-invasive assessment of tissue properties. Learning-based approaches can map $T_{1ρ}$ from a reduced number of $T_{1ρ}$ weighted images, but requires significant amounts of high quality training data. Moreover, existing methods do not provide the confidence level of the $T_{1ρ}$ estimation. To address these problems, we proposed a self-supervised learning neural network that learns a $T_{1ρ}$ mapping using the relaxation constraint in the learning process. Epistemic uncertainty and aleatoric uncertainty are modelled for the …
Deep Self-Supervised Disturbance Mapping with the OPERA Sentinel-1 Radiometric Terrain Corrected SAR Backscatter Product
University of California - Los Angeles（加利福尼亚大学洛杉矶分校）；Jet Propulsion Laboratory, California Institute of Technology（加州理工学院喷气推进实验室）；Joint Institute for Regional Earth System Science and Engineering, University of California - Los Angeles（加利福尼亚大学洛杉矶分校区域地球系统科学与工程联合研究所）
本文基于 OPERA RTC-S1 数据训练无需标签的自监督 vision transformer，通过逐像素基线分布偏差检测地表扰动，并在三地灾害事件中取得优于现有方法的结果。
Weakly Supervised Framework Considering Multi-temporal Information for Large-scale Cropland Mapping with Satellite Imagery
School of Geosciences and Info-Physics, Central South University（中南大学地球科学与信息物理学院）；The 27th Research Institute, China Electronic Technology Group Corporation（中国电子科技集团公司第二十七研究所）
Nowadays, modern Earth Observation systems continuously collect massive amounts of satellite information. The unprecedented possibility to acquire high resolution Satellite Image Time Series (SITS) data (series of images with high revisit time period on the same geographical area) is opening new opportunities to monitor the different aspects of the Earth Surface but, at the same time, it is raising up new challenges in term of suitable methods to analyze and exploit such huge amount of rich and complex image data. One of the main task associated to SITS data analysis is related to land cover m…
Land cover maps are a vital input variable to many types of environmental research and management. While they can be produced automatically by machine learning techniques, these techniques require substantial training data to achieve high levels of accuracy, which are not always available. One technique researchers use when labelled training data are scarce is domain adaptation (DA) -- where data from an alternate region, known as the source domain, are used to train a classifier and this model is adapted to map the study region, or target domain. The scenario we address in this paper is known…
University of Bath（巴斯大学）；GE Healthcare（通用电气医疗集团）；Technical University of Munich（慕尼黑工业大学）；Technische Hochschule Ingolstadt（英戈尔施塔特应用技术大学）
Current state-of-the-art reconstruction for quantitative tissue maps from fast, compressive, Magnetic Resonance Fingerprinting (MRF), use supervised deep learning, with the drawback of requiring high-fidelity ground truth tissue map training data which is limited. This paper proposes NonLinear Equivariant Imaging (NLEI), a self-supervised learning approach to eliminate the need for ground truth for deep MRF image reconstruction. NLEI extends the recent Equivariant Imaging framework to nonlinear inverse problems such as MRF. Only fast, compressed-sampled MRF scans are used for training. NLEI le…
Rutgers, The State University of New Jersey（罗格斯大学，新泽西州立大学）；NEC Laboratories America Inc.（NEC美国实验室公司）
Urban flooding is becoming a common and devastating hazard to cause life loss and economic damage. Monitoring and understanding urban flooding in the local scale is a challenging task due to the complicated urban landscape, intricate hydraulic process, and the lack of high-quality and resolution data. The emerging smart city technology such as monitoring cameras provides an unprecedented opportunity to address the data issue. However, estimating the water accumulation on the land surface based on the monitoring footage is unreliable using the traditional segmentation technique because the boun…
