We propose to use a model-based generative loss for training hand pose estimators on depth images based on a volumetric hand model. This additional loss allows training of a hand pose estimator that accurately infers the entire set of 21 hand keypoints while only using supervision for 6 easy-to-annotate keypoints (fingertips and wrist). We show that our partially-supervised method achieves results that are comparable to those of fully-supervised methods which enforce articulation consistency. Moreover, for the first time we demonstrate that such an approach can be used to train on datasets that have erroneous annotations, i.e. "ground truth" with notable measurement errors, while obtaining predictions that explain the depth images better than the given "ground truth".
Bilateral postural symmetry plays a key role as a potential risk marker for autism spectrum disorder (ASD) and as a symptom of congenital muscular torticollis (CMT) in infants, but current methods of assessing symmetry require laborious clinical expert assessments. In this paper, we develop a computer vision based infant symmetry assessment system, leveraging 3D human pose estimation for infants. Evaluation and calibration of our system against ground truth assessments is complicated by our findings from a survey of human ratings of angle and symmetry, that such ratings exhibit low inter-rater…
A significant weakness of most current deep Convolutional Neural Networks is the need to train them using vast amounts of manu- ally labelled data. In this work we propose a unsupervised framework to learn a deep convolutional neural network for single view depth predic- tion, without requiring a pre-training stage or annotated ground truth depths. We achieve this by training the network in a manner analogous to an autoencoder. At training time we consider a pair of images, source and target, with small, known camera motion between the two such as a stereo pair. We train the convolutional enco…
Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）；Carl Zeiss AG（卡尔蔡司公司）；University of Applied Sciences Berlin（柏林应用科学大学）
Pixel-wise segmentation is one of the most data and annotation hungry tasks in our field. Providing representative and accurate annotations is often mission-critical especially for challenging medical applications. In this paper, we propose a semi-weakly supervised segmentation algorithm to overcome this barrier. Our approach is based on a new formulation of deep supervision and student-teacher model and allows for easy integration of different supervision signals. In contrast to previous work, we show that care has to be taken how deep supervision is integrated in lower layers and we present …
Existing instance segmentation models learn task-specific information using manual mask annotations from base (training) categories. These mask annotations require tremendous human effort, limiting the scalability to annotate novel (new) categories. To alleviate this problem, Open-Vocabulary (OV) methods leverage large-scale image-caption pairs and vision-language models to learn novel categories. In summary, an OV method learns task-specific information using strong supervision from base annotations and novel category information using weak supervision from image-captions pairs. This differen…
Mapillary Research（Mapillary研究中心）；Graz University of Technology（格拉茨理工大学）；Computer Vision Center, UAB（巴塞罗那自治大学计算机视觉中心）
In this work we contribute a novel pipeline to automatically generate training data, and to improve over state-of-the-art multi-object tracking and segmentation (MOTS) methods. Our proposed track mining algorithm turns raw street-level videos into high-fidelity MOTS training data, is scalable and overcomes the need of expensive and time-consuming manual annotation approaches. We leverage state-of-the-art instance segmentation results in combination with optical flow predictions, also trained on automatically harvested training data. Our second major contribution is MOTSNet - a deep learning, t…
Hohai University（河海大学）；Nanjing University of Science and Technology（南京理工大学）
Since the labelling for the positive images/videos is ambiguous in weakly supervised segment annotation, negative mining based methods that only use the intra-class information emerge. In these methods, negative instances are utilized to penalize unknown instances to rank their likelihood of being an object, which can be considered as a voting in terms of similarity. However, these methods 1) ignore the information contained in positive bags, 2) only rank the likelihood but cannot generate an explicit decision function. In this paper, we propose a voting scheme involving not only the definite …
Universal lesion detection in computed tomography (CT) images is an important yet challenging task due to the large variations in lesion type, size, shape, and appearance. Considering that data in clinical routine (such as the DeepLesion dataset) are usually annotated with a long and a short diameter according to the standard of Response Evaluation Criteria in Solid Tumors (RECIST) diameters, we propose RECIST-Net, a new approach to lesion detection in which the four extreme points and center point of the RECIST diameters are detected. By detecting a lesion as keypoints, we provide a more conc…
As natural images usually contain multiple objects, multi-label image classification is more applicable "in the wild" than single-label classification. However, exhaustively annotating images with every object of interest is costly and time-consuming. We aim to train multi-label classifiers from single-label annotations only. We show that adding a consistency loss, ensuring that the predictions of the network are consistent over consecutive training epochs, is a simple yet effective method to train multi-label classifiers in a weakly supervised setting. We further extend this approach spatiall…
UC Berkeley（加州大学伯克利分校）；Nanyang Tech. Univ.（南洋理工大学）；UC Santa Barbara（加州大学圣塔芭芭拉分校）；Princeton University（普林斯顿大学）；Univ. KwaZulu-Natal（夸祖鲁-纳塔尔大学）
Camera trapping is increasingly used to monitor wildlife, but this technology typically requires extensive data annotation. Recently, deep learning has significantly advanced automatic wildlife recognition. However, current methods are hampered by a dependence on large static data sets when wildlife data is intrinsically dynamic and involves long-tailed distributions. These two drawbacks can be overcome through a hybrid combination of machine learning and humans in the loop. Our proposed iterative human and automated identification approach is capable of learning from wildlife imagery data wit…
Lomonosov Moscow State University（罗蒙诺索夫莫斯科国立大学）；Microsoft Research Cambridge（微软研究院剑桥实验室）
Structured-output learning is a challenging problem; particularly so because of the difficulty in obtaining large datasets of fully labelled instances for training. In this paper we try to overcome this difficulty by presenting a multi-utility learning framework for structured prediction that can learn from training instances with different forms of supervision. We propose a unified technique for inferring the loss functions most suitable for quantifying the consistency of solutions with the given weak annotation. We demonstrate the effectiveness of our framework on the challenging semantic im…
Bridging the Gap between Text, Audio, Image, and Any Sequence: A Novel Approach using Gloss-based Annotation
Victoria University（维多利亚大学）；Chengdu University of Information Technology（成都信息工程大学）；Shanghai Jiao Tong University（上海交通大学）；Nanyang Technological University（南洋理工大学）
Few-shot segmentation aims to segment images containing objects from previously unseen classes using only a few annotated samples. Most current methods focus on using object information extracted, with the aid of human annotations, from support images to identify the same objects in new query images. However, background information can also be useful to distinguish objects from their surroundings. Hence, some previous methods also extract background information from the support images. In this paper, we argue that such information is of limited utility, as the background in different images ca…
School of Computer Science, the University of Adelaide, Australia（澳大利亚阿德莱德大学计算机学院）；Monash University, Australia（澳大利亚莫纳什大学）
Deployment of deep learning models in robotics as sensory information extractors can be a daunting task to handle, even using generic GPU cards. Here, we address three of its most prominent hurdles, namely, i) the adaptation of a single model to perform multiple tasks at once (in this work, we consider depth estimation and semantic segmentation crucial for acquiring geometric and semantic understanding of the scene), while ii) doing it in real-time, and iii) using asymmetric datasets with uneven numbers of annotations per each modality. To overcome the first two issues, we adapt a recently pro…
Sunnybrook Research Institute（桑尼布鲁克研究所）；University of Toronto（多伦多大学）
Training a neural network with a large labeled dataset is still a dominant paradigm in computational histopathology. However, obtaining such exhaustive manual annotations is often expensive, laborious, and prone to inter and Intra-observer variability. While recent self-supervised and semi-supervised methods can alleviate this need by learn-ing unsupervised feature representations, they still struggle to generalize well to downstream tasks when the number of labeled instances is small. In this work, we overcome this challenge by leveraging both task-agnostic and task-specific unlabeled data ba…
Face parsing, which is to assign a semantic label to each pixel in face images, has recently attracted increasing interest due to its huge application potentials. Although many face related fields (e.g., face recognition and face detection) have been well studied for many years, the existing datasets for face parsing are still severely limited in terms of the scale and quality, e.g., the widely used Helen dataset only contains 2,330 images. This is mainly because pixel-level annotation is a high cost and time-consuming work, especially for the facial parts without clear boundaries. The lack of…
Mitigating annotation shift in cancer classification using single image generative models
Universitat de Barcelona（巴塞罗那大学）；Helmholtz Center Munich（慕尼黑亥姆霍兹中心）；Technical University of Munich（慕尼黑工业大学）；Institució Catalana de Recerca i Estudis Avançats (ICREA)（加泰罗尼亚高级研究学院）；Computer Vision Center（计算机视觉中心）
SceneGlue: Scene-Aware Transformer for Feature Matching without Scene-Level Annotation
School of Automation, Southeast University（东南大学自动化学院）；Shenzhen Research Institute of Southeast University（东南大学深圳研究院）；School of Computer Science and Engineering, Southeast University（东南大学计算机科学与工程学院）；School of Computer Science and Technology, Tongji University（同济大学计算机科学与技术学院）；Graduate School of Information, Production and Systems, Waseda University（早稻田大学信息、生产与系统研究生学校）
Robotics Institute, Carnegie Mellon University（卡内基梅隆大学机器人研究所）
In this paper, we propose a self-supervised learningmethod for multi-object pose estimation. 3D object under-standing from 2D image is a challenging task that infers ad-ditional dimension from reduced-dimensional information.In particular, the estimation of the 3D localization or orien-tation of an object requires precise reasoning, unlike othersimple clustering tasks such as object classification. There-fore, the scale of the training dataset becomes more cru-cial. However, it is challenging to obtain large amount of3D dataset since achieving 3D annotation is expensive andtime-consuming. If t…
Renmin University of China（中国人民大学）；University of Surrey（萨里大学）
Zero-shot learning (ZSL) aims to recognize a set of unseen classes without any training images. The standard approach to ZSL requires a set of training images annotated with seen class labels and a semantic descriptor for seen/unseen classes (attribute vector is the most widely used). Class label/attribute annotation is expensive; it thus severely limits the scalability of ZSL. In this paper, we define a new ZSL setting where only a few annotated images are collected from each seen class. This is clearly more challenging yet more realistic than the conventional ZSL setting. To overcome the res…
Technical University of Munich（慕尼黑工业大学）；Tsinghua University（清华大学）；Google（谷歌）
6D object pose estimation is a fundamental problem in computer vision. Convolutional Neural Networks (CNNs) have recently proven to be capable of predicting reliable 6D pose estimates even from monocular images. Nonetheless, CNNs are identified as being extremely data-driven, and acquiring adequate annotations is oftentimes very time-consuming and labor intensive. To overcome this shortcoming, we propose the idea of monocular 6D pose estimation by means of self-supervised learning, removing the need for real annotations. After training our proposed network fully supervised with synthetic RGB d…
Eindhoven University of Technology（埃因霍温理工大学）；Shandong University of Science and Technology（山东科技大学）；Philips Research（飞利浦研究院）
Accurate and efficient catheter segmentation in 3D ultrasound (US) is essential for cardiac intervention. Currently, the state-of-the-art segmentation algorithms are based on convolutional neural networks (CNNs), which achieved remarkable performances in a standard Cartesian volumetric data. Nevertheless, these approaches suffer the challenges of low efficiency and GPU unfriendly image size. Therefore, such difficulties and expensive hardware requirements become a bottleneck to build accurate and efficient segmentation models for real clinical application. In this paper, we propose a novel Fru…
Carnegie Mellon University（卡内基梅隆大学）；University of Central Florida（中佛罗里达大学）；NVIDIA Inc.（英伟达公司）；Qatar University（卡塔尔大学）；University of Warwick（华威大学）
With multiple crowd gatherings of millions of people every year in events ranging from pilgrimages to protests, concerts to marathons, and festivals to funerals; visual crowd analysis is emerging as a new frontier in computer vision. In particular, counting in highly dense crowds is a challenging problem with far-reaching applicability in crowd safety and management, as well as gauging political significance of protests and demonstrations. In this paper, we propose a novel approach that simultaneously solves the problems of counting, density map estimation and localization of people in a given…
Xiamen University（厦门大学）；Chinese PLA General Hospital（中国人民解放军总医院）；Deepwise AI Laboratory（深度智耀人工智能实验室）
Standard segmentation of medical images based on full-supervised convolutional networks demands accurate dense annotations. Such learning framework is built on laborious manual annotation with restrict demands for expertise, leading to insufficient high-quality labels. To overcome such limitation and exploit massive weakly labeled data, we relaxed the rigid labeling requirement and developed a semi-supervised learning framework based on a teacher-student fashion for organ and lesion segmentation with partial dense-labeled supervision and supplementary loose bounding-box supervision which are e…
Cell detection is the task of detecting the approximate positions of cell centroids from microscopy images. Recently, convolutional neural network-based approaches have achieved promising performance. However, these methods require a certain amount of annotation for each imaging condition. This annotation is a time-consuming and labor-intensive task. To overcome this problem, we propose a semi-supervised cell-detection method that effectively uses a time-lapse sequence with one labeled image and the other images unlabeled. First, we train a cell-detection network with a one-labeled image and e…
National University of Sciences and Technology (NUST)（巴基斯坦国立科技大学（NUST））；Riphah International University（里法国际大学）
Unavailability of large training datasets is a bottleneck that needs to be overcome to realize the true potential of deep learning in histopathology applications. Although slide digitization via whole slide imaging scanners has increased the speed of data acquisition, labeling of virtual slides requires a substantial time investment from pathologists. Eye gaze annotations have the potential to speed up the slide labeling process. This work explores the viability and timing comparisons of eye gaze labeling compared to conventional manual labeling for training object detectors. Challenges associ…
Modern 3D human pose estimation techniques rely on deep networks, which require large amounts of training data. While weakly-supervised methods require less supervision, by utilizing 2D poses or multi-view imagery without annotations, they still need a sufficiently large set of samples with 3D annotations for learning to succeed. In this paper, we propose to overcome this problem by learning a geometry-aware body representation from multi-view images without annotations. To this end, we use an encoder-decoder that predicts an image from one viewpoint given an image from another viewpoint. Beca…
University of Electronic Science and Technology of China（电子科技大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；West China Hospital, Sichuan University（四川大学华西医院）
The success of Convolutional Neural Networks (CNNs) in 3D medical image segmentation relies on massive fully annotated 3D volumes for training that are time-consuming and labor-intensive to acquire. In this paper, we propose to annotate a segmentation target with only seven points in 3D medical images, and design a two-stage weakly supervised learning framework PA-Seg. In the first stage, we employ geodesic distance transform to expand the seed points to provide more supervision signal. To further deal with unannotated image regions during training, we propose two contextual regularization str…
University of Electronic Science and Technology of China（电子科技大学）；SenseTime Research（商汤科技研究院）
Despite that deep learning has achieved state-of-the-art performance for medical image segmentation, its success relies on a large set of manually annotated images for training that are expensive to acquire. In this paper, we propose an annotation-efficient learning framework for segmentation tasks that avoids annotations of training images, where we use an improved Cycle-Consistent Generative Adversarial Network (GAN) to learn from a set of unpaired medical images and auxiliary masks obtained either from a shape model or public datasets. We first use the GAN to generate pseudo labels for our …
Supervised learning has proved effective for medical image analysis. However, it can utilize only the small labeled portion of data; it fails to leverage the large amounts of unlabeled data that is often available in medical image datasets. Supervised models are further handicapped by domain shifts, when the labeled dataset, despite being large enough, fails to cover different protocols or ethnicities. In this paper, we introduce \emph{extreme consistency}, which overcomes the above limitations, by maximally leveraging unlabeled data from the same or a different domain in a teacher-student sem…
Central Electronics Engineering Research Institute, CSIR Madras Complex（CSIR马德拉斯综合体中央电子工程研究所）；University of Bridgeport（桥港大学）
Image segmentation and classification are the two main fundamental steps in pattern recognition. To perform medical image segmentation or classification with deep learning models, it requires training on large image dataset with annotation. The dermoscopy images (ISIC archive) considered for this work does not have ground truth information for lesion segmentation. Performing manual labelling on this dataset is time-consuming. To overcome this issue, self-learning annotation scheme was proposed in the two-stage deep learning algorithm. The two-stage deep learning algorithm consists of U-Net seg…
European Laboratory for Non-Linear Spectroscopy (LENS), University of Florence（佛罗伦萨大学欧洲非线性光谱实验室）；Bioretics SrL（Bioretics SrL公司）；National Institute of Optics, National Research Council (INO-CNR)（国家研究委员会国家光学研究所）；Department of Physics（物理系）
Semantic segmentation of neuronal structures in 3D high-resolution fluorescence microscopy imaging of the human brain cortex can take advantage of bidimensional CNNs, which yield good results in neuron localization but lead to inaccurate surface reconstruction. 3D CNNs, on the other hand, would require manually annotated volumetric data on a large scale and hence considerable human effort. Semi-supervised alternative strategies which make use only of sparse annotations suffer from longer training times and achieved models tend to have increased capacity compared to 2D CNNs, needing more ground…
University of Freiburg（弗赖堡大学）；University of Technology Nuremberg（纽伦堡工业大学）
Robustly classifying ground infrastructure such as roads and street crossings is an essential task for mobile robots operating alongside pedestrians. While many semantic segmentation datasets are available for autonomous vehicles, models trained on such datasets exhibit a large domain gap when deployed on robots operating in pedestrian spaces. Manually annotating images recorded from pedestrian viewpoints is both expensive and time-consuming. To overcome this challenge, we propose TrackletMapper, a framework for annotating ground surface types such as sidewalks, roads, and street crossings fro…
Wetland mapping from sparse annotations with satellite image time series and temporal-aware segment anything model
Department of Geography, The University of Hong Kong, Hong Kong, China（香港大学地理系）；Pengcheng Laboratory, Shenzhen, China（深圳鹏城实验室）；Department of Electronics and Information Engineering, Harbin Institute of Technology (Shenzhen), Shenzhen, China（哈尔滨工业大学（深圳）电子与信息工程学院）；Key Laboratory for Geo-Environmental Monitoring of Great Bay Area, Ministry of Natural Resources, Guangdong Key Laboratory of Urban Informatics, Shenzhen Key Laboratory of Spatial Smart Sensing and Services, Shenzhen University, Shenzhen, China（粤港澳大湾区地理环境监测重点实验室，自然资源部，广东省城市信息学重点实验室，深圳空间智能感知与服务重点实验室，深圳大学）
Point2RBox-v3: Self-Bootstrapping from Point Annotations via Integrated Pseudo-Label Refinement and Utilization
Shanghai Jiao Tong University（上海交通大学）；South China University of Technology（华南理工大学）；Nankai University（南开大学）；The Chinese University of Hong Kong（香港中文大学）；Nanjing University of Aeronautics and Astronautics（南京航空航天大学）；East China Normal University（华东师范大学）；Ohio State University（俄亥俄州立大学）
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 …
