Manual-Label Free 3D Detection via An Open-Source Simulator
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Beijing Aerospace Changfeng Co.Ltd.（北京航天长峰股份有限公司）；Artificial Intelligence Research, Chinese Academy of Sciences（中国科学院人工智能研究院）
Zhen Yang, Chi Zhang, Huiming Guo, Zhaoxiang Zhang
LiDAR based 3D object detectors typically need a large amount of detailed-labeled point cloud data for training, but these detailed labels are commonly expensive to acquire. In this paper, we propose a manual-label free 3D detection algorithm that leverages the CARLA simulator to generate a large amount of self-labeled training samples and introduces a novel Domain Adaptive VoxelNet (DA-VoxelNet) that can cross the distribution gap from the synthetic data to the real scenario. The self-labeled training samples are generated by a set of high quality 3D models embedded in a CARLA simulator and a proposed LiDAR-guided sampling algorithm. Then a DA-VoxelNet that integrates both a sample-level DA module and an anchor-level DA module is proposed to enable the detector trained by the synthetic data to adapt to real scenario. Experimental results show that the proposed unsupervised DA 3D detector on KITTI evaluation set can achieve 76.66% and 56.64% mAP on BEV mode and 3D mode respectively. The results reveal a promising perspective of training a LIDAR-based 3D detector without any hand-tagged label.
Training of convolutional neural networks for semantic segmentation requires accurate pixel-wise labeling which requires large amounts of human effort. The human-in-the-loop method reduces labeling effort; however, it requires human intervention for each image. This paper describes a general iterative training methodology for semantic segmentation, Automating-the-Loop. This aims to replicate the manual adjustments of the human-in-the-loop method with an automated process, hence, drastically reducing labeling effort. Using the application of detecting partially occluded apple tree segmentation,…
Graz University of Technology（格拉茨理工大学）；University of Bordeaux（波尔多大学）
We show that it is possible to learn semantic segmentation from very limited amounts of manual annotations, by enforcing geometric 3D constraints between multiple views. More exactly, image locations corresponding to the same physical 3D point should all have the same label. We show that introducing such constraints during learning is very effective, even when no manual label is available for a 3D point, and can be done simply by employing techniques from 'general' semi-supervised learning to the context of semantic segmentation. To demonstrate this idea, we use RGB-D image sequences of rigid …
Producing manual, pixel-accurate, image segmentation labels is tedious and time-consuming. This is often a rate-limiting factor when large amounts of labeled images are required, such as for training deep convolutional networks for instrument-background segmentation in surgical scenes. No large datasets comparable to industry standards in the computer vision community are available for this task. To circumvent this problem, we propose to automate the creation of a realistic training dataset by exploiting techniques stemming from special effects and harnessing them to target training performanc…
Learning an object detector or retrieval requires a large data set with manual annotations. Such data sets are expensive and time consuming to create and therefore difficult to obtain on a large scale. In this work, we propose to exploit the natural correlation in narrations and the visual presence of objects in video, to learn an object detector and retrieval without any manual labeling involved. We pose the problem as weakly supervised learning with noisy labels, and propose a novel object detection paradigm under these constraints. We handle the background rejection by using contrastive sam…
LMU München（慕尼黑大学）；Technische Universität München（慕尼黑工业大学）；Indian Institute of Technology, Kharagpur（印度理工学院卡哈拉格普尔分校）；IBM Almaden Research Center（IBM阿尔马登研究中心）；Johns Hopkins University（约翰斯·霍普金斯大学）
Training deep fully convolutional neural networks (F-CNNs) for semantic image segmentation requires access to abundant labeled data. While large datasets of unlabeled image data are available in medical applications, access to manually labeled data is very limited. We propose to automatically create auxiliary labels on initially unlabeled data with existing tools and to use them for pre-training. For the subsequent fine-tuning of the network with manually labeled data, we introduce error corrective boosting (ECB), which emphasizes parameter updates on classes with lower accuracy. Furthermore, …
The State Key Laboratory for Management and Control of Complex Systems, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所复杂系统管理与控制国家重点实验室）；Qingdao Academy of Intelligent Industries（青岛智能产业研究院）；Research Center for Computational Experiments and Parallel Systems Technology, National University of Defense Technology（国防科技大学计算实验与平行系统技术研究中心）
As a special type of object detection, pedestrian detection in generic scenes has made a significant progress trained with large amounts of labeled training data manually. While the models trained with generic dataset work bad when they are directly used in specific scenes. With special viewpoints, flow light and backgrounds, datasets from specific scenes are much different from the datasets from generic scenes. In order to make the generic scene pedestrian detectors work well in specific scenes, the labeled data from specific scenes are needed to adapt the models to the specific scenes. While…
This paper describes a novel method of training a semantic segmentation model for scene recognition of agricultural mobile robots exploiting publicly available datasets of outdoor scenes that are different from the target greenhouse environments. Semantic segmentation models require abundant labels given by tedious manual annotation. A method to work around it is unsupervised domain adaptation (UDA) that transfers knowledge from labeled source datasets to unlabeled target datasets. However, the effectiveness of existing methods is not well studied in adaptation between heterogeneous environmen…
The University of Tennessee Knoxville（田纳西大学诺克斯维尔分校）
Annotating images for semantic segmentation requires intense manual labor and is a time-consuming and expensive task especially for domains with a scarcity of experts, such as Forensic Anthropology. We leverage the evolving nature of images depicting the decay process in human decomposition data to design a simple yet effective pseudo-pixel-level label generation technique to reduce the amount of effort for manual annotation of such images. We first identify sequences of images with a minimum variation that are most suitable to share the same or similar annotation using an unsupervised approac…
Optical aerial images change detection is an important task in earth observation and has been extensively investigated in the past few decades. Generally, the supervised change detection methods with superior performance require a large amount of labeled training data which is obtained by manual annotation with high cost. In this paper, we present a novel unsupervised self-training algorithm (USTA) for optical aerial images change detection. The traditional method such as change vector analysis is used to generate the pseudo labels. We use these pseudo labels to train a well designed convoluti…
ThermoCycleNet: Stereo-based Thermogram Labeling for Model Transition to Cycling
Institute of Computer Science, Research Group Computational Geometry, Johannes Gutenberg University, Mainz, Germany（计算机科学研究所，计算几何研究组，吉森大学，马因茨，德国）；Institute of Sports Science, Department of Sports Medicine, Disease Prevention and Rehabilitation, Johannes Gutenberg University, Mainz, Germany（体育科学研究所，运动医学部门，疾病预防与康复，吉森大学，马因茨，德国）；Institute of Occupational, Social and Environmental Medicine, University Medical Center, Mainz, Germany（职业、社会和环境医学研究所，大学医学中心，马因茨，德国）
University of Cambridge（剑桥大学）；Imperial College London（帝国理工学院）
Manual segmentation is used as the gold-standard for evaluating neural networks on automated image segmentation tasks. Due to considerable heterogeneity in shapes, colours and textures, demarcating object boundaries is particularly difficult in biomedical images, resulting in significant inter and intra-rater variability. Approaches, such as soft labelling and distance penalty term, apply a global transformation to the ground truth, redefining the loss function with respect to uncertainty. However, global operations are computationally expensive, and neither approach accurately reflects the un…
A lack of generalizability is one key limitation of deep learning based segmentation. Typically, one manually labels new training images when segmenting organs in different imaging modalities or segmenting abnormal organs from distinct disease cohorts. The manual efforts can be alleviated if one is able to reuse manual labels from one modality (e.g., MRI) to train a segmentation network for a new modality (e.g., CT). Previously, two stage methods have been proposed to use cycle generative adversarial networks (CycleGAN) to synthesize training images for a target modality. Then, these efforts t…
Renmin University of China（中国人民大学）；Visionary Intelligence Ltd（远见智能有限公司）；Tongren Hospital（同仁医院）
For retinal image matching (RIM), we propose SuperRetina, the first end-to-end method with jointly trainable keypoint detector and descriptor. SuperRetina is trained in a novel semi-supervised manner. A small set of (nearly 100) images are incompletely labeled and used to supervise the network to detect keypoints on the vascular tree. To attack the incompleteness of manual labeling, we propose Progressive Keypoint Expansion to enrich the keypoint labels at each training epoch. By utilizing a keypoint-based improved triplet loss as its description loss, SuperRetina produces highly discriminativ…
Vanishing points (VPs) play a vital role in various computer vision tasks, especially for recognizing the 3D scenes from an image. In the real-world scenario of automobile applications, it is costly to manually obtain the external camera parameters when the camera is attached to the vehicle or the attachment is accidentally perturbed. In this paper we introduce a simple but effective end-to-end vanishing point detection. By automatically calculating intersection of the extrapolated lane marker annotations, we obtain geometrically consistent VP labels and mitigate human annotation errors caused…
Recent deep neural networks (DNNs) can easily overfit to biased training data with noisy labels. Label correction strategy is commonly used to alleviate this issue by designing a method to identity suspected noisy labels and then correct them. Current approaches to correcting corrupted labels usually need certain pre-defined label correction rules or manually preset hyper-parameters. These fixed settings make it hard to apply in practice since the accurate label correction usually related with the concrete problem, training data and the temporal information hidden in dynamic iterations of trai…
Daimler AG（戴姆勒股份公司）；Karlsruhe Institute of Technology (KIT)（卡尔斯鲁厄理工学院）；Forschungszentrum Informatik (FZI)（信息技术研究中心）
Mobile robots and autonomous vehicles rely on multi-modal sensor setups to perceive and understand their surroundings. Aside from cameras, LiDAR sensors represent a central component of state-of-the-art perception systems. In addition to accurate spatial perception, a comprehensive semantic understanding of the environment is essential for efficient and safe operation. In this paper we present a novel deep neural network architecture called LiLaNet for point-wise, multi-class semantic labeling of semi-dense LiDAR data. The network utilizes virtual image projections of the 3D point clouds for e…
We present the development and evaluation of a hand tracking algorithm based on single depth images captured from an overhead perspective for use in the COACH prompting system. We train a random decision forest body part classifier using approximately 5,000 manually labeled, unbalanced, partially labeled training images. The classifier represents a random subset of pixels in each depth image with a learned probability density function across all trained body parts. A local mode-find approach is used to search for clusters present in the underlying feature space sampled by the classified pixels…
Automatic Labels are as Effective as Manual Labels in Biomedical Images Classification with Deep Learning
Information Systems Institute, University of Applied Sciences Western Switzerland (HES-SO Valais)（瑞士西部应用科学与艺术大学信息系统研究所）；University of Padua（帕多瓦大学）；University of Applied Sciences and Arts Dortmund（多特蒙德应用科学与艺术大学）；AGH University of Kraków（克拉科夫AGH科技大学）；SURFsara；Ruggi University Hospital（鲁吉大学医院）；Gravina Hospital Caltagirone ASP（卡尔塔吉罗内格拉维纳医院）；Ontotext；Bulgarian Academy of Sciences（保加利亚科学院）；Radboud University Medical Center（拉德堡德大学医学中心）；University of Geneva（日内瓦大学）
Combining CNN with CRF for modeling dependencies between pixel labels is a popular research direction. This task is far from trivial, especially if end-to-end training is desired. In this paper, we propose a novel simple approach to CNN+CRF combination. In particular, we propose to simulate a CRF regularizer with a trainable module that has standard CNN architecture. We call this module a CRF Simulator. We can automatically generate an unlimited amount of ground truth for training such CRF Simulator without any user interaction, provided we have an efficient algorithm for optimization of the a…
Nanjing University of Science and Technology（南京理工大学）
Supervised-learning based person re-identification (re-id) require a large amount of manual labeled data, which is not applicable in practical re-id deployment. In this work, we propose a Support Pair Active Learning (SPAL) framework to lower the manual labeling cost for large-scale person reidentification. The support pairs can provide the most informative relationships and support the discriminative feature learning. Specifically, we firstly design a dual uncertainty selection strategy to iteratively discover support pairs and require human annotations. Afterwards, we introduce a constrained…
Toyota Research Institute（丰田研究院）；Intel Labs（英特尔实验室）
Deep Learning for Computer Vision depends mainly on the source of supervision.Photo-realistic simulators can generate large-scale automatically labeled syntheticdata, but introduce a domain gap negatively impacting performance. We propose anew unsupervised domain adaptation algorithm, called SPIGAN, relying on Sim-ulator Privileged Information (PI) and Generative Adversarial Networks (GAN).We use internal data from the simulator as PI during the training of a target tasknetwork. We experimentally evaluate our approach on semantic segmentation. Wetrain the networks on real-world Cityscapes and …
PAII Inc.（PAII公司）；Virginia Polytechnic Institute and State University（弗吉尼亚理工学院暨州立大学）；Ping An Insurance (Group) Company of China, Ltd.（中国平安保险（集团）股份有限公司）
Large-scale datasets with high-quality labels are desired for training accurate deep learning models. However, due to the annotation cost, datasets in medical imaging are often either partially-labeled or small. For example, DeepLesion is such a large-scale CT image dataset with lesions of various types, but it also has many unlabeled lesions (missing annotations). When training a lesion detector on a partially-labeled dataset, the missing annotations will generate incorrect negative signals and degrade the performance. Besides DeepLesion, there are several small single-type datasets, such as …
NVIDIA（英伟达）；University of Toronto（多伦多大学）；Vector Institute（矢量研究所）
Autonomous driving relies on a huge volume of real-world data to be labeled to high precision. Alternative solutions seek to exploit driving simulators that can generate large amounts of labeled data with a plethora of content variations. However, the domain gap between the synthetic and real data remains, raising the following important question: What are the best ways to utilize a self-driving simulator for perception tasks? In this work, we build on top of recent advances in domain-adaptation theory, and from this perspective, propose ways to minimize the reality gap. We primarily focus on …
Simultaneous Automatic Picking and Manual Picking Refinement for First-Break
School of Mathematics and Statistics, Xi’an Jiaotong University（西安交通大学数学与统计学院）；Geophysical Technology Research Center of Bureau of Geophysical Prospecting（东方地球物理公司物探技术研究中心）；School of Artificial Intelligence, Wenzhou Polytechnic（温州职业技术学院人工智能学院）
National Institutes of Health Clinical Center（美国国立卫生研究院临床中心）
Accurately predicting and detecting interstitial lung disease (ILD) patterns given any computed tomography (CT) slice without any pre-processing prerequisites, such as manually delineated regions of interest (ROIs), is a clinically desirable, yet challenging goal. The majority of existing work relies on manually-provided ILD ROIs to extract sampled 2D image patches from CT slices and, from there, performs patch-based ILD categorization. Acquiring manual ROIs is labor intensive and serves as a bottleneck towards fully-automated CT imaging ILD screening over large-scale populations. Furthermore,…
University of Science and Technology of China（中国科学技术大学）；Texas A&M University（得克萨斯农工大学）
Few-shot classification aims to learn a model that can generalize well to new tasks when only a few labeled samples are available. To make use of unlabeled data that are more abundantly available in real applications, Ren et al. \shortcite{ren2018meta} propose a semi-supervised few-shot classification method that assigns an appropriate label to each unlabeled sample by a manually defined metric. However, the manually defined metric fails to capture the intrinsic property in data. In this paper, we propose a \textbf{S}elf-\textbf{A}daptive \textbf{L}abel \textbf{A}ugmentation approach, called \…
While mislabeled or ambiguously-labeled samples in the training set could negatively affect the performance of deep models, diagnosing the dataset and identifying mislabeled samples helps to improve the generalization power. Training dynamics, i.e., the traces left by iterations of optimization algorithms, have recently been proved to be effective to localize mislabeled samples with hand-crafted features. In this paper, beyond manually designed features, we introduce a novel learning-based solution, leveraging a noise detector, instanced by an LSTM network, which learns to predict whether a sa…
Manual Labelling Artificially Inflates Deep Learning-Based Segmentation Performance on RGB Images of Closed Canopy: Validation Using TLS
University of Cambridge（剑桥大学）；Queen Mary University of London（伦敦玛丽女王大学）；Digital Environment Research Institute, Queen Mary University of London（伦敦玛丽女王大学数字环境研究所）
University of Maryland（马里兰大学）；Worcester Polytechnic Institute（伍斯特理工学院）
In the era of deep learning, data is the critical determining factor in the performance of neural network models. Generating large datasets suffers from various difficulties such as scalability, cost efficiency and photorealism. To avoid expensive and strenuous dataset collection and annotations, researchers have inclined towards computer-generated datasets. Although, a lack of photorealism and a limited amount of computer-aided data, has bounded the accuracy of network predictions. To this end, we present WorldGen -- an open source framework to autonomously generate countless structured and u…
Learning video concept detectors automatically from the big but noisy web data with no additional manual annotations is a novel but challenging area in the multimedia and the machine learning community. A considerable amount of videos on the web are associated with rich but noisy contextual information, such as the title, which provides weak annotations or labels about the video content. To leverage the big noisy web labels, this paper proposes a novel method called WEbly-Labeled Learning (WELL), which is established on the state-of-the-art machine learning algorithm inspired by the learning p…
High-resolution segmentations of the hypothalamus and its subregions for training of segmentation models
Massachusetts General Hospital（麻省总医院）；Harvard Medical School（哈佛医学院）；Universidade Estadual de Campinas（坎皮纳斯州立大学）；Dementia Research Centre（痴呆研究中心）；UCL Queen Square Institute of Neurology（伦敦大学学院女王广场神经学研究所）；University College London（伦敦大学学院）；Centre for Cognitive and Clinical Neuroscience（认知与临床神经科学中心）；Brunel University London（布鲁内尔伦敦大学）；Centre for Medical Image Computing（医学影像计算中心）；Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology（麻省理工学院计算机科学与人工智能实验室）
School of Earth and Planetary Sciences（地球与行星科学学院）；Curtin University（科廷大学）；Oil and Gas Innovation Centre（油气创新中心）
With the increased size and complexity of seismic surveys, manual labeling of seismic facies has become a significant challenge. Application of automatic methods for seismic facies interpretation could significantly reduce the manual labor and subjectivity of a particular interpreter present in conventional methods. A recently emerged group of methods is based on deep neural networks. These approaches are data-driven and require large labeled datasets for network training. We apply a deep convolutional autoencoder for unsupervised seismic facies classification, which does not require manually …
More efficient manual review of automatically transcribed tabular data
UiT The Arctic University of Norway（挪威北极大学）；Norwegian Historical Data Centre（挪威历史数据中心）；Department of Health and Care Sciences（健康与护理科学学院）；Department of Computer Science（计算机科学学院）
National Center for Tumor Diseases（国家肿瘤疾病中心）；University College London（伦敦大学学院）；Mannheim University of Applied Sciences（曼海姆应用科学大学）；German Cancer Research Center（德国癌症研究中心）
In the medical domain, the lack of large training data sets and benchmarks is often a limiting factor for training deep neural networks. In contrast to expensive manual labeling, computer simulations can generate large and fully labeled data sets with a minimum of manual effort. However, models that are trained on simulated data usually do not translate well to real scenarios. To bridge the domain gap between simulated and real laparoscopic images, we exploit recent advances in unpaired image-to-image translation. We extent an image-to-image translation method to generate a diverse multitude o…
Microsoft AI and Research（微软人工智能与研究院）；JD AI Research（京东人工智能研究院）；Facebook（脸书）
In this paper, we study the problem of learning image classification models with label noise. Existing approaches depending on human supervision are generally not scalable as manually identifying correct or incorrect labels is time-consuming, whereas approaches not relying on human supervision are scalable but less effective. To reduce the amount of human supervision for label noise cleaning, we introduce CleanNet, a joint neural embedding network, which only requires a fraction of the classes being manually verified to provide the knowledge of label noise that can be transferred to other clas…
Dept. of Electrical and Computer Engineering, Rice University（莱斯大学电气与计算机工程系）；Dept. of Electrical and Computer Engineering, Technical University of Munich（慕尼黑工业大学电气与计算机工程系）
Image classification problems are typically addressed by first collecting examples with candidate labels, second cleaning the candidate labels manually, and third training a deep neural network on the clean examples. The manual labeling step is often the most expensive one as it requires workers to label millions of images. In this paper we propose to work without any explicitly labeled data by i) directly training the deep neural network on the noisy candidate labels, and ii) early stopping the training to avoid overfitting. With this procedure we exploit an intriguing property of standard ov…
Over the last couple of years, deep learning and especially convolutional neural networks have become one of the work horses of computer vision. One limiting factor for the applicability of supervised deep learning to more areas is the need for large, manually labeled datasets. In this paper we propose an easy to implement method we call guided labeling, which automatically determines which samples from an unlabeled dataset should be labeled. We show that using this procedure, the amount of samples that need to be labeled is reduced considerably in comparison to labeling images arbitrarily.
