Peter H. N. de With

Tim J. Schoonbeek, Tim Houben, Hans Onvlee et al.

Although action recognition for procedural tasks has received notable attention, it has a fundamental flaw in that no measure of success for actions is provided. This limits the applicability of such systems especially within the industrial domain, since the outcome of procedural actions is often significantly more important than the mere execution. To address this limitation, we define the novel task of procedure step recognition (PSR), focusing on recognizing the correct completion and order of procedural steps. Alongside the new task, we also present the multi-modal IndustReal dataset. Unlike currently available datasets, IndustReal contains procedural errors (such as omissions) as well as execution errors. A significant part of these errors are exclusively present in the validation and test sets, making IndustReal suitable to evaluate robustness of algorithms to new, unseen mistakes. Additionally, to encourage reproducibility and allow for scalable approaches trained on synthetic data, the 3D models of all parts are publicly available. Annotations and benchmark performance are provided for action recognition and assembly state detection, as well as the new PSR task. IndustReal, along with the code and model weights, is available at: https://github.com/TimSchoonbeek/IndustReal .

Tim J. M. Jaspers, Ronald L. P. D. de Jong, Yasmina Al Khalil et al.

Over the past decade, computer vision applications in minimally invasive surgery have rapidly increased. Despite this growth, the impact of surgical computer vision remains limited compared to other medical fields like pathology and radiology, primarily due to the scarcity of representative annotated data. Whereas transfer learning from large annotated datasets such as ImageNet has been conventionally the norm to achieve high-performing models, recent advancements in self-supervised learning (SSL) have demonstrated superior performance. In medical image analysis, in-domain SSL pretraining has already been shown to outperform ImageNet-based initialization. Although unlabeled data in the field of surgical computer vision is abundant, the diversity within this data is limited. This study investigates the role of dataset diversity in SSL for surgical computer vision, comparing procedure-specific datasets against a more heterogeneous general surgical dataset across three different downstream surgical applications. The obtained results show that using solely procedure-specific data can lead to substantial improvements of 13.8%, 9.5%, and 36.8% compared to ImageNet pretraining. However, extending this data with more heterogeneous surgical data further increases performance by an additional 5.0%, 5.2%, and 2.5%, suggesting that increasing diversity within SSL data is beneficial for model performance. The code and pretrained model weights are made publicly available at https://github.com/TimJaspers0801/SurgeNet.

Tim J. Schoonbeek, Goutham Balachandran, Hans Onvlee et al.

Assembly state recognition facilitates the execution of assembly procedures, offering feedback to enhance efficiency and minimize errors. However, recognizing assembly states poses challenges in scalability, since parts are frequently updated, and the robustness to execution errors remains underexplored. To address these challenges, this paper proposes an approach based on representation learning and the novel intermediate-state informed loss function modification (ISIL). ISIL leverages unlabeled transitions between states and demonstrates significant improvements in clustering and classification performance for all tested architectures and losses. Despite being trained exclusively on images without execution errors, thorough analysis on error states demonstrates that our approach accurately distinguishes between correct states and states with various types of execution errors. The integration of the proposed algorithm can offer meaningful assistance to workers and mitigate unexpected losses due to procedural mishaps in industrial settings. The code is available at: https://timschoonbeek.github.io/state_rec

Christiaan G. A. Viviers, Mark Ramaekers, Peter H. N. de With et al.

Pancreatic cancer is one of the global leading causes of cancer-related deaths. Despite the success of Deep Learning in computer-aided diagnosis and detection (CAD) methods, little attention has been paid to the detection of Pancreatic Cancer. We propose a method for detecting pancreatic tumor that utilizes clinically-relevant features in the surrounding anatomical structures, thereby better aiming to exploit the radiologist's knowledge compared to other, conventional deep learning approaches. To this end, we collect a new dataset consisting of 99 cases with pancreatic ductal adenocarcinoma (PDAC) and 97 control cases without any pancreatic tumor. Due to the growth pattern of pancreatic cancer, the tumor may not be always visible as a hypodense lesion, therefore experts refer to the visibility of secondary external features that may indicate the presence of the tumor. We propose a method based on a U-Net-like Deep CNN that exploits the following external secondary features: the pancreatic duct, common bile duct and the pancreas, along with a processed CT scan. Using these features, the model segments the pancreatic tumor if it is present. This segmentation for classification and localization approach achieves a performance of 99% sensitivity (one case missed) and 99% specificity, which realizes a 5% increase in sensitivity over the previous state-of-the-art method. The model additionally provides location information with reasonable accuracy and a shorter inference time compared to previous PDAC detection methods. These results offer a significant performance improvement and highlight the importance of incorporating the knowledge of the clinical expert when developing novel CAD methods.

Giacomo D'Amicantonio, Egor Bondarev, Peter H. N. De With

Over the past few decades, a significant rise of camera-based applications for traffic monitoring has occurred. Governments and local administrations are increasingly relying on the data collected from these cameras to enhance road safety and optimize traffic conditions. However, for effective data utilization, it is imperative to ensure accurate and automated calibration of the involved cameras. This paper proposes a novel approach to address this challenge by leveraging the topological structure of intersections. We propose a framework involving the generation of a set of synthetic intersection viewpoint images from a bird's-eye-view image, framed as a graph of virtual cameras to model these images. Using the capabilities of Graph Neural Networks, we effectively learn the relationships within this graph, thereby facilitating the estimation of a homography matrix. This estimation leverages the neighbourhood representation for any real-world camera and is enhanced by exploiting multiple images instead of a single match. In turn, the homography matrix allows the retrieval of extrinsic calibration parameters. As a result, the proposed framework demonstrates superior performance on both synthetic datasets and real-world cameras, setting a new state-of-the-art benchmark.

M. M. Amaan Valiuddin, Christiaan G. A. Viviers, Ruud J. G. van Sloun et al.

Melanoma is a serious form of skin cancer with high mortality rate at later stages. Fortunately, when detected early, the prognosis of melanoma is promising and malignant melanoma incidence rates are relatively low. As a result, datasets are heavily imbalanced which complicates training current state-of-the-art supervised classification AI models. We propose to use generative models to learn the benign data distribution and detect Out-of-Distribution (OOD) malignant images through density estimation. Normalizing Flows (NFs) are ideal candidates for OOD detection due to their ability to compute exact likelihoods. Nevertheless, their inductive biases towards apparent graphical features rather than semantic context hamper accurate OOD detection. In this work, we aim at using these biases with domain-level knowledge of melanoma, to improve likelihood-based OOD detection of malignant images. Our encouraging results demonstrate potential for OOD detection of melanoma using NFs. We achieve a 9% increase in Area Under Curve of the Receiver Operating Characteristics by using wavelet-based NFs. This model requires significantly less parameters for inference making it more applicable on edge devices. The proposed methodology can aid medical experts with diagnosis of skin-cancer patients and continuously increase survival rates. Furthermore, this research paves the way for other areas in oncology with similar data imbalance issues.

Christiaan G. A. Viviers, Joel de Bruijn, Lena Filatova et al.

Deep learning-based pose estimation algorithms can successfully estimate the pose of objects in an image, especially in the field of color images. 6D Object pose estimation based on deep learning models for X-ray images often use custom architectures that employ extensive CAD models and simulated data for training purposes. Recent RGB-based methods opt to solve pose estimation problems using small datasets, making them more attractive for the X-ray domain where medical data is scarcely available. We refine an existing RGB-based model (SingleShotPose) to estimate the 6D pose of a marked cube from grayscale X-ray images by creating a generic solution trained on only real X-ray data and adjusted for X-ray acquisition geometry. The model regresses 2D control points and calculates the pose through 2D/3D correspondences using Perspective-n-Point(PnP), allowing a single trained model to be used across all supporting cone-beam-based X-ray geometries. Since modern X-ray systems continuously adjust acquisition parameters during a procedure, it is essential for such a pose estimation network to consider these parameters in order to be deployed successfully and find a real use case. With a 5-cm/5-degree accuracy of 93% and an average 3D rotation error of 2.2 degrees, the results of the proposed approach are comparable with state-of-the-art alternatives, while requiring significantly less real training examples and being applicable in real-time applications.

Luis A. Zavala-Mondragón, Peter H. N. de With, Fons van der Sommen

Encoding-decoding CNNs play a central role in data-driven noise reduction and can be found within numerous deep-learning algorithms. However, the development of these CNN architectures is often done in ad-hoc fashion and theoretical underpinnings for important design choices is generally lacking. Up to this moment there are different existing relevant works that strive to explain the internal operation of these CNNs. Still, these ideas are either scattered and/or may require significant expertise to be accessible for a bigger audience. In order to open up this exciting field, this article builds intuition on the theory of deep convolutional framelets and explains diverse ED CNN architectures in a unified theoretical framework. By connecting basic principles from signal processing to the field of deep learning, this self-contained material offers significant guidance for designing robust and efficient novel CNN architectures.

Giacomo D'Amicantonio, Egor Bondarau, Peter H. N. De With

Surveillance videos and images are used for a broad set of applications, ranging from traffic analysis to crime detection. Extrinsic camera calibration data is important for most analysis applications. However, security cameras are susceptible to environmental conditions and small camera movements, resulting in a need for an automated re-calibration method that can account for these varying conditions. In this paper, we present an automated camera-calibration process leveraging a dictionary-based approach that does not require prior knowledge on any camera settings. The method consists of a custom implementation of a Spatial Transformer Network (STN) and a novel topological loss function. Experiments reveal that the proposed method improves the IoU metric by up to 12% w.r.t. a state-of-the-art model across five synthetic datasets and the World Cup 2014 dataset.

M. M. Amaan Valiuddin, Christiaan G. A. Viviers, Ruud J. G. van Sloun et al.

Data uncertainties, such as sensor noise, occlusions or limitations in the acquisition method can introduce irreducible ambiguities in images, which result in varying, yet plausible, semantic hypotheses. In Machine Learning, this ambiguity is commonly referred to as aleatoric uncertainty. In image segmentation, latent density models can be utilized to address this problem. The most popular approach is the Probabilistic U-Net (PU-Net), which uses latent Normal densities to optimize the conditional data log-likelihood Evidence Lower Bound. In this work, we demonstrate that the PU-Net latent space is severely sparse and heavily under-utilized. To address this, we introduce mutual information maximization and entropy-regularized Sinkhorn Divergence in the latent space to promote homogeneity across all latent dimensions, effectively improving gradient-descent updates and latent space informativeness. Our results show that by applying this on public datasets of various clinical segmentation problems, our proposed methodology receives up to 11% performance gains compared against preceding latent variable models for probabilistic segmentation on the Hungarian-Matched Intersection over Union. The results indicate that encouraging a homogeneous latent space significantly improves latent density modeling for medical image segmentation.

Tim J. M. Jaspers, Francisco Caetano, Cris H. B. Claessens et al.

Computer-aided detection (CADe) of early neoplasia in Barrett's esophagus is a low-prevalence surveillance problem in which clinically relevant findings are rare. Although many CADe systems report strong performance on balanced or enriched datasets, their behavior under realistic prevalence remains insufficiently characterized. The RARE25 challenge addresses this gap by introducing a large-scale, prevalence-aware benchmark for neoplasia detection. It includes a public training set and a hidden test set reflecting real-world incidence. Methods were evaluated using operating-point-specific metrics emphasizing high sensitivity and accounting for prevalence. Eleven teams from seven countries submitted approaches using diverse architectures, pretraining, ensembling, and calibration strategies. While several methods achieved strong discriminative performance, positive predictive values remained low, highlighting the difficulty of low-prevalence detection and the risk of overestimating clinical utility when prevalence is ignored. All methods relied on fully supervised classification despite the dominance of normal findings, indicating a lack of prevalence-agnostic approaches such as anomaly detection or one-class learning. By releasing a public dataset and a reproducible evaluation framework, RARE25 aims to support the development of CADe systems robust to prevalence shift and suitable for clinical surveillance workflows.

Dan Lehman, Tim J. Schoonbeek, Shao-Hsuan Hung et al.

Recognizing errors in assembly and maintenance procedures is valuable for industrial applications, since it can increase worker efficiency and prevent unplanned down-time. Although assembly state recognition is gaining attention, none of the current works investigate assembly error localization. Therefore, we propose StateDiffNet, which localizes assembly errors based on detecting the differences between a (correct) intended assembly state and a test image from a similar viewpoint. StateDiffNet is trained on synthetically generated image pairs, providing full control over the type of meaningful change that should be detected. The proposed approach is the first to correctly localize assembly errors taken from real ego-centric video data for both states and error types that are never presented during training. Furthermore, the deployment of change detection to this industrial application provides valuable insights and considerations into the mechanisms of state-of-the-art change detection algorithms. The code and data generation pipeline are publicly available at: https://timschoonbeek.github.io/error_seg.

Christiaan G. A. Viviers, Lena Filatova, Maurice Termeer et al.

Accurate 6-DoF pose estimation of surgical instruments during minimally invasive surgeries can substantially improve treatment strategies and eventual surgical outcome. Existing deep learning methods have achieved accurate results, but they require custom approaches for each object and laborious setup and training environments often stretching to extensive simulations, whilst lacking real-time computation. We propose a general-purpose approach of data acquisition for 6-DoF pose estimation tasks in X-ray systems, a novel and general purpose YOLOv5-6D pose architecture for accurate and fast object pose estimation and a complete method for surgical screw pose estimation under acquisition geometry consideration from a monocular cone-beam X-ray image. The proposed YOLOv5-6D pose model achieves competitive results on public benchmarks whilst being considerably faster at 42 FPS on GPU. In addition, the method generalizes across varying X-ray acquisition geometry and semantic image complexity to enable accurate pose estimation over different domains. Finally, the proposed approach is tested for bone-screw pose estimation for computer-aided guidance during spine surgeries. The model achieves a 92.41% by the 0.1 ADD-S metric, demonstrating a promising approach for enhancing surgical precision and patient outcomes. The code for YOLOv5-6D is publicly available at https://github.com/cviviers/YOLOv5-6D-Pose

Tim J. M. Jaspers, Ronald L. P. D. de Jong, Yiping Li et al.

Foundation models have revolutionized computer vision by achieving vastly superior performance across diverse tasks through large-scale pretraining on extensive datasets. However, their application in surgical computer vision has been limited. This study addresses this gap by introducing SurgeNetXL, a novel surgical foundation model that sets a new benchmark in surgical computer vision. Trained on the largest reported surgical dataset to date, comprising over 4.7 million video frames, SurgeNetXL achieves consistent top-tier performance across six datasets spanning four surgical procedures and three tasks, including semantic segmentation, phase recognition, and critical view of safety (CVS) classification. Compared with the best-performing surgical foundation models, SurgeNetXL shows mean improvements of 2.4, 9.0, and 12.6 percent for semantic segmentation, phase recognition, and CVS classification, respectively. Additionally, SurgeNetXL outperforms the best-performing ImageNet-based variants by 14.4, 4.0, and 1.6 percent in the respective tasks. In addition to advancing model performance, this study provides key insights into scaling pretraining datasets, extending training durations, and optimizing model architectures specifically for surgical computer vision. These findings pave the way for improved generalizability and robustness in data-scarce scenarios, offering a comprehensive framework for future research in this domain. All models and a subset of the SurgeNetXL dataset, including over 2 million video frames, are publicly available at: https://github.com/TimJaspers0801/SurgeNet.

Erkut Akdag, Zeqi Zhu, Egor Bondarev et al.

Classification and localization of driving actions over time is important for advanced driver-assistance systems and naturalistic driving studies. Temporal localization is challenging because it requires robustness, reliability, and accuracy. In this study, we aim to improve the temporal localization and classification accuracy performance by adapting video action recognition and 2D human-pose estimation networks to one model. Therefore, we design a transformer-based fusion architecture to effectively combine 2D-pose features and spatio-temporal features. The model uses 2D-pose features as the positional embedding of the transformer architecture and spatio-temporal features as the main input to the encoder of the transformer. The proposed solution is generic and independent of the camera numbers and positions, giving frame-based class probabilities as output. Finally, the post-processing step combines information from different camera views to obtain final predictions and eliminate false positives. The model performs well on the A2 test set of the 2023 NVIDIA AI City Challenge for naturalistic driving action recognition, achieving the overlap score of the organizer-defined distracted driver behaviour metric of 0.5079.

Giacomo D'Amicantonio, Egor Bondarau, Peter H. N. de With

Deep learning-based approaches have achieved significant improvements on public video anomaly datasets, but often do not perform well in real-world applications. This paper addresses two issues: the lack of labeled data and the difficulty of explaining the predictions of a neural network. To this end, we present a framework called uTRAND, that shifts the problem of anomalous trajectory prediction from the pixel space to a semantic-topological domain. The framework detects and tracks all types of traffic agents in bird's-eye-view videos of traffic cameras mounted at an intersection. By conceptualizing the intersection as a patch-based graph, it is shown that the framework learns and models the normal behaviour of traffic agents without costly manual labeling. Furthermore, uTRAND allows to formulate simple rules to classify anomalous trajectories in a way suited for human interpretation. We show that uTRAND outperforms other state-of-the-art approaches on a dataset of anomalous trajectories collected in a real-world setting, while producing explainable detection results.

Tunc Alkanat, Erkut Akdag, Egor Bondarev et al.

Temporal localization of driving actions plays a crucial role in advanced driver-assistance systems and naturalistic driving studies. However, this is a challenging task due to strict requirements for robustness, reliability and accurate localization. In this work, we focus on improving the overall performance by efficiently utilizing video action recognition networks and adapting these to the problem of action localization. To this end, we first develop a density-guided label smoothing technique based on label probability distributions to facilitate better learning from boundary video-segments that typically include multiple labels. Second, we design a post-processing step to efficiently fuse information from video-segments and multiple camera views into scene-level predictions, which facilitates elimination of false positives. Our methodology yields a competitive performance on the A2 test set of the naturalistic driving action recognition track of the 2022 NVIDIA AI City Challenge with an F1 score of 0.271.

Ivo P. C. Kersten, Erkut Akdag, Egor Bondarev et al.

Anomalous behavior detection is a challenging research area within computer vision. Progress in this area enables automated detection of dangerous behavior using surveillance camera feeds. A dangerous behavior that is often overlooked in other research is the throwing action in traffic flow, which is one of the unique requirements of our Smart City project to enhance public safety. This paper proposes a solution for throwing action detection in surveillance videos using deep learning. At present, datasets for throwing actions are not publicly available. To address the use-case of our Smart City project, we first generate the novel public 'Throwing Action' dataset, consisting of 271 videos of throwing actions performed by traffic participants, such as pedestrians, bicyclists, and car drivers, and 130 normal videos without throwing actions. Second, we compare the performance of different feature extractors for our anomaly detection method on the UCF-Crime and Throwing-Action datasets. The explored feature extractors are the Convolutional 3D (C3D) network, the Inflated 3D ConvNet (I3D) network, and the Multi-Fiber Network (MFNet). Finally, the performance of the anomaly detection algorithm is improved by applying the Adam optimizer instead of Adadelta, and proposing a mean normal loss function that covers the multitude of normal situations in traffic. Both aspects yield better anomaly detection performance. Besides this, the proposed mean normal loss function lowers the false alarm rate on the combined dataset. The experimental results reach an area under the ROC curve of 86.10 for the Throwing-Action dataset, and 80.13 on the combined dataset, respectively.

Erkut Akdag, Egor Bondarev, Peter H. N. De With

Anomaly detection in video surveillance has recently gained interest from the research community. Temporal duration of anomalies vary within video streams, leading to complications in learning the temporal dynamics of specific events. This paper presents a temporal-granularity method for an anomaly detection model (TeG) in real-world surveillance, combining spatio-temporal features at different time-scales. The TeG model employs multi-head cross-attention blocks and multi-head self-attention blocks for this purpose. Additionally, we extend the UCF-Crime dataset with new anomaly types relevant to Smart City research project. The TeG model is deployed and validated in a city surveillance system, achieving successful real-time results in industrial settings.

Francisco Caetano, Christiaan Viviers, Peter H. N. De With et al.

Flow Matching has emerged as a powerful framework for learning continuous transformations between distributions, enabling high-fidelity generative modeling. This work introduces Symmetrical Flow Matching (SymmFlow), a new formulation that unifies semantic segmentation, classification, and image generation within a single model. Using a symmetric learning objective, SymmFlow models forward and reverse transformations jointly, ensuring bi-directional consistency, while preserving sufficient entropy for generative diversity. A new training objective is introduced to explicitly retain semantic information across flows, featuring efficient sampling while preserving semantic structure, allowing for one-step segmentation and classification without iterative refinement. Unlike previous approaches that impose strict one-to-one mapping between masks and images, SymmFlow generalizes to flexible conditioning, supporting both pixel-level and image-level class labels. Experimental results on various benchmarks demonstrate that SymmFlow achieves state-of-the-art performance on semantic image synthesis, obtaining FID scores of 11.9 on CelebAMask-HQ and 7.0 on COCO-Stuff with only 25 inference steps. Additionally, it delivers competitive results on semantic segmentation and shows promising capabilities in classification tasks.

Francisco Caetano, Christiaan Viviers, Lena Filatova et al.

Ensuring the quality and integrity of medical images is crucial for maintaining diagnostic accuracy in deep learning-based Computer-Aided Diagnosis and Computer-Aided Detection (CAD) systems. Covariate shifts are subtle variations in the data distribution caused by different imaging devices or settings and can severely degrade model performance, similar to the effects of adversarial attacks. Therefore, it is vital to have a lightweight and fast method to assess the quality of these images prior to using CAD models. AdverX-Ray addresses this need by serving as an image-quality assessment layer, designed to detect covariate shifts effectively. This Adversarial Variational Autoencoder prioritizes the discriminator's role, using the suboptimal outputs of the generator as negative samples to fine-tune the discriminator's ability to identify high-frequency artifacts. Images generated by adversarial networks often exhibit severe high-frequency artifacts, guiding the discriminator to focus excessively on these components. This makes the discriminator ideal for this approach. Trained on patches from X-ray images of specific machine models, AdverX-Ray can evaluate whether a scan matches the training distribution, or if a scan from the same machine is captured under different settings. Extensive comparisons with various OOD detection methods show that AdverX-Ray significantly outperforms existing techniques, achieving a 96.2% average AUROC using only 64 random patches from an X-ray. Its lightweight and fast architecture makes it suitable for real-time applications, enhancing the reliability of medical imaging systems. The code and pretrained models are publicly available.

Tim J. Schoonbeek, Shao-Hsuan Hung, Dan Lehman et al.

Procedure step recognition (PSR) aims to identify all correctly completed steps and their sequential order in videos of procedural tasks. The existing state-of-the-art models rely solely on detecting assembly object states in individual video frames. By neglecting temporal features, model robustness and accuracy are limited, especially when objects are partially occluded. To overcome these limitations, we propose Spatio-Temporal Occlusion-Resilient Modeling for Procedure Step Recognition (STORM-PSR), a dual-stream framework for PSR that leverages both spatial and temporal features. The assembly state detection stream operates effectively with unobstructed views of the object, while the spatio-temporal stream captures both spatial and temporal features to recognize step completions even under partial occlusion. This stream includes a spatial encoder, pre-trained using a novel weakly supervised approach to capture meaningful spatial representations, and a transformer-based temporal encoder that learns how these spatial features relate over time. STORM-PSR is evaluated on the MECCANO and IndustReal datasets, reducing the average delay between actual and predicted assembly step completions by 11.2% and 26.1%, respectively, compared to prior methods. We demonstrate that this reduction in delay is driven by the spatio-temporal stream, which does not rely on unobstructed views of the object to infer completed steps. The code for STORM-PSR, along with the newly annotated MECCANO labels, is made publicly available at https://timschoonbeek.github.io/stormpsr .

Francisco Caetano, Christiaan Viviers, Luis A. Zavala-Mondragón et al.

Out-of-distribution (OOD) detection holds significant importance across many applications. While semantic and domain-shift OOD problems are well-studied, this work focuses on covariate shifts - subtle variations in the data distribution that can degrade machine learning performance. We hypothesize that detecting these subtle shifts can improve our understanding of in-distribution boundaries, ultimately improving OOD detection. In adversarial discriminators trained with Batch Normalization (BN), real and adversarial samples form distinct domains with unique batch statistics - a property we exploit for OOD detection. We introduce DisCoPatch, an unsupervised Adversarial Variational Autoencoder (VAE) framework that harnesses this mechanism. During inference, batches consist of patches from the same image, ensuring a consistent data distribution that allows the model to rely on batch statistics. DisCoPatch uses the VAE's suboptimal outputs (generated and reconstructed) as negative samples to train the discriminator, thereby improving its ability to delineate the boundary between in-distribution samples and covariate shifts. By tightening this boundary, DisCoPatch achieves state-of-the-art results in public OOD detection benchmarks. The proposed model not only excels in detecting covariate shifts, achieving 95.5% AUROC on ImageNet-1K(-C) but also outperforms all prior methods on public Near-OOD (95.0%) benchmarks. With a compact model size of 25MB, it achieves high OOD detection performance at notably lower latency than existing methods, making it an efficient and practical solution for real-world OOD detection applications. The code is publicly available.

Christiaan G. A. Viviers, Amaan M. M. Valiuddin, Peter H. N. de With et al.

Uncertainty quantification in medical images has become an essential addition to segmentation models for practical application in the real world. Although there are valuable developments in accurate uncertainty quantification methods using 2D images and slices of 3D volumes, in clinical practice, the complete 3D volumes (such as CT and MRI scans) are used to evaluate and plan the medical procedure. As a result, the existing 2D methods miss the rich 3D spatial information when resolving the uncertainty. A popular approach for quantifying the ambiguity in the data is to learn a distribution over the possible hypotheses. In recent work, this ambiguity has been modeled to be strictly Gaussian. Normalizing Flows (NFs) are capable of modelling more complex distributions and thus, better fit the embedding space of the data. To this end, we have developed a 3D probabilistic segmentation framework augmented with NFs, to enable capturing the distributions of various complexity. To test the proposed approach, we evaluate the model on the LIDC-IDRI dataset for lung nodule segmentation and quantify the aleatoric uncertainty introduced by the multi-annotator setting and inherent ambiguity in the CT data. Following this approach, we are the first to present a 3D Squared Generalized Energy Distance (GED) of 0.401 and a high 0.468 Hungarian-matched 3D IoU. The obtained results reveal the value in capturing the 3D uncertainty, using a flexible posterior distribution augmented with a Normalizing Flow. Finally, we present the aleatoric uncertainty in a visual manner with the aim to provide clinicians with additional insight into data ambiguity and facilitating more informed decision-making.

Hongxu Yang, Caifeng Shan, R. Arthur Bouwman et al.

Medical instrument segmentation in 3D ultrasound is essential for image-guided intervention. However, to train a successful deep neural network for instrument segmentation, a large number of labeled images are required, which is expensive and time-consuming to obtain. In this article, we propose a semi-supervised learning (SSL) framework for instrument segmentation in 3D US, which requires much less annotation effort than the existing methods. To achieve the SSL learning, a Dual-UNet is proposed to segment the instrument. The Dual-UNet leverages unlabeled data using a novel hybrid loss function, consisting of uncertainty and contextual constraints. Specifically, the uncertainty constraints leverage the uncertainty estimation of the predictions of the UNet, and therefore improve the unlabeled information for SSL training. In addition, contextual constraints exploit the contextual information of the training images, which are used as the complementary information for voxel-wise uncertainty estimation. Extensive experiments on multiple ex-vivo and in-vivo datasets show that our proposed method achieves Dice score of about 68.6%-69.1% and the inference time of about 1 sec. per volume. These results are better than the state-of-the-art SSL methods and the inference time is comparable to the supervised approaches.

Sander R. Klomp, Matthew van Rijn, Rob G. J. Wijnhoven et al.

Since the introduction of the GDPR and CCPA legislation, both public and private facial image datasets are increasingly scrutinized. Several datasets have been taken offline completely and some have been anonymized. However, it is unclear how anonymization impacts face detection performance. To our knowledge, this paper presents the first empirical study on the effect of image anonymization on supervised training of face detectors. We compare conventional face anonymizers with three state-of-the-art Generative Adversarial Network-based (GAN) methods, by training an off-the-shelf face detector on anonymized data. Our experiments investigate the suitability of anonymization methods for maintaining face detector performance, the effect of detectors overtraining on anonymization artefacts, dataset size for training an anonymizer, and the effect of training time of anonymization GANs. A final experiment investigates the correlation between common GAN evaluation metrics and the performance of a trained face detector. Although all tested anonymization methods lower the performance of trained face detectors, faces anonymized using GANs cause far smaller performance degradation than conventional methods. As the most important finding, the best-performing GAN, DeepPrivacy, removes identifiable faces for a face detector trained on anonymized data, resulting in a modest decrease from 91.0 to 88.3 mAP. In the last few years, there have been rapid improvements in realism of GAN-generated faces. We expect that further progression in GAN research will allow the use of Deep Fake technology for privacy-preserving Safe Fakes, without any performance degradation for training face detectors.

Hongxu Yang, Caifeng Shan, Alexander F. Kolen et al.

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 Frustum ultrasound based catheter segmentation method. Specifically, Frustum ultrasound is a polar coordinate based image, which includes same information of standard Cartesian image but has much smaller size, which overcomes the bottleneck of efficiency than conventional Cartesian images. Nevertheless, the irregular and deformed Frustum images lead to more efforts for accurate voxel-level annotation. To address this limitation, a weakly supervised learning framework is proposed, which only needs 3D bounding box annotations overlaying the region-of-interest to training the CNNs. Although the bounding box annotation includes noise and inaccurate annotation to mislead to model, it is addressed by the proposed pseudo label generated scheme. The labels of training voxels are generated by incorporating class activation maps with line filtering, which is iteratively updated during the training. Our experimental results show the proposed method achieved the state-of-the-art performance with an efficiency of 0.25 second per volume. More crucially, the Frustum image segmentation provides a much faster and cheaper solution for segmentation in 3D US image, which meet the demands of clinical applications.

Hongxu Yang, Caifeng Shan, Alexander F. Kolen et al.

Medical instrument detection is essential for computer-assisted interventions since it would facilitate the surgeons to find the instrument efficiently with a better interpretation, which leads to a better outcome. This article reviews medical instrument detection methods in the ultrasound-guided intervention. First, we present a comprehensive review of instrument detection methodologies, which include traditional non-data-driven methods and data-driven methods. The non-data-driven methods were extensively studied prior to the era of machine learning, i.e. data-driven approaches. We discuss the main clinical applications of medical instrument detection in ultrasound, including anesthesia, biopsy, prostate brachytherapy, and cardiac catheterization, which were validated on clinical datasets. Finally, we selected several principal publications to summarize the key issues and potential research directions for the computer-assisted intervention community.

Hongxu Yang, Caifeng Shan, Alexander F. Kolen et al.

Catheter segmentation in 3D ultrasound is important for computer-assisted cardiac intervention. However, a large amount of labeled images are required to train a successful deep convolutional neural network (CNN) to segment the catheter, which is expensive and time-consuming. In this paper, we propose a novel catheter segmentation approach, which requests fewer annotations than the supervised learning method, but nevertheless achieves better performance. Our scheme considers a deep Q learning as the pre-localization step, which avoids voxel-level annotation and which can efficiently localize the target catheter. With the detected catheter, patch-based Dual-UNet is applied to segment the catheter in 3D volumetric data. To train the Dual-UNet with limited labeled images and leverage information of unlabeled images, we propose a novel semi-supervised scheme, which exploits unlabeled images based on hybrid constraints from predictions. Experiments show the proposed scheme achieves a higher performance than state-of-the-art semi-supervised methods, while it demonstrates that our method is able to learn from large-scale unlabeled images.

Clint Sebastian, Raffaele Imbriaco, Egor Bondarev et al.

Vehicle re-identification plays a crucial role in the management of transportation infrastructure and traffic flow. However, this is a challenging task due to the large view-point variations in appearance, environmental and instance-related factors. Modern systems deploy CNNs to produce unique representations from the images of each vehicle instance. Most work focuses on leveraging new losses and network architectures to improve the descriptiveness of these representations. In contrast, our work concentrates on re-ranking and embedding expansion techniques. We propose an efficient approach for combining the outputs of multiple models at various scales while exploiting tracklet and neighbor information, called dual embedding expansion (DEx). Additionally, a comparative study of several common image retrieval techniques is presented in the context of vehicle re-ID. Our system yields competitive performance in the 2020 NVIDIA AI City Challenge with promising results. We demonstrate that DEx when combined with other re-ranking techniques, can produce an even larger gain without any additional attribute labels or manual supervision.

Clint Sebastian, Raffaele Imbriaco, Egor Bondarev et al.

Building extraction from aerial images has several applications in problems such as urban planning, change detection, and disaster management. With the increasing availability of data, Convolutional Neural Networks (CNNs) for semantic segmentation of remote sensing imagery has improved significantly in recent years. However, convolutions operate in local neighborhoods and fail to capture non-local features that are essential in semantic understanding of aerial images. In this work, we propose to improve building segmentation of different sizes by capturing long-range dependencies using contextual pyramid attention (CPA). The pathways process the input at multiple scales efficiently and combine them in a weighted manner, similar to an ensemble model. The proposed method obtains state-of-the-art performance on the Inria Aerial Image Labelling Dataset with minimal computation costs. Our method improves 1.8 points over current state-of-the-art methods and 12.6 points higher than existing baselines on the Intersection over Union (IoU) metric without any post-processing. Code and models will be made publicly available.

Clint Sebastian, Raffaele Imbriaco, Egor Bondarev et al.

Automatic building extraction from aerial imagery has several applications in urban planning, disaster management, and change detection. In recent years, several works have adopted deep convolutional neural networks (CNNs) for building extraction, since they produce rich features that are invariant against lighting conditions, shadows, etc. Although several advances have been made, building extraction from aerial imagery still presents multiple challenges. Most of the deep learning segmentation methods optimize the per-pixel loss with respect to the ground truth without knowledge of the context. This often leads to imperfect outputs that may lead to missing or unrefined regions. In this work, we propose a novel loss function combining both adversarial and cross-entropy losses that learn to understand both local and global contexts for semantic segmentation. The newly proposed loss function deployed on the DeepLab v3+ network obtains state-of-the-art results on the Massachusetts buildings dataset. The loss function improves the structure and refines the edges of buildings without requiring any of the commonly used post-processing methods, such as Conditional Random Fields. We also perform ablation studies to understand the impact of the adversarial loss. Finally, the proposed method achieves a relaxed F1 score of 95.59% on the Massachusetts buildings dataset compared to the previous best F1 of 94.88%.

Marco Mamprin, Jo M. Zelis, Pim A. L. Tonino et al.

Current prognostic risk scores in cardiac surgery are based on statistics and do not yet benefit from machine learning. Statistical predictors are not robust enough to correctly identify patients who would benefit from Transcatheter Aortic Valve Implantation (TAVI). This research aims to create a machine learning model to predict one-year mortality of a patient after TAVI. We adopt a modern gradient boosting on decision trees algorithm, specifically designed for categorical features. In combination with a recent technique for model interpretations, we developed a feature analysis and selection stage, enabling to identify the most important features for the prediction. We base our prediction model on the most relevant features, after interpreting and discussing the feature analysis results with clinical experts. We validated our model on 270 TAVI cases, reaching an AUC of 0.83. Our approach outperforms several widespread prognostic risk scores, such as logistic EuroSCORE II, the STS risk score and the TAVI2-score, which are broadly adopted by cardiologists worldwide.

Ries Uittenbogaard, Clint Sebastian, Julien Vijverberg et al.

The current paradigm in privacy protection in street-view images is to detect and blur sensitive information. In this paper, we propose a framework that is an alternative to blurring, which automatically removes and inpaints moving objects (e.g. pedestrians, vehicles) in street-view imagery. We propose a novel moving object segmentation algorithm exploiting consistencies in depth across multiple street-view images that are later combined with the results of a segmentation network. The detected moving objects are removed and inpainted with information from other views, to obtain a realistic output image such that the moving object is not visible anymore. We evaluate our results on a dataset of 1000 images to obtain a peak noise-to-signal ratio (PSNR) and L1 loss of 27.2 dB and 2.5%, respectively. To ensure the subjective quality, To assess overall quality, we also report the results of a survey conducted on 35 professionals, asked to visually inspect the images whether object removal and inpainting had taken place. The inpainting dataset will be made publicly available for scientific benchmarking purposes at https://research.cyclomedia.com

Raffaele Imbriaco, Clint Sebastian, Egor Bondarev et al.

Remote Sensing Image Retrieval remains a challenging topic due to the special nature of Remote Sensing Imagery. Such images contain various different semantic objects, which clearly complicates the retrieval task. In this paper, we present an image retrieval pipeline that uses attentive, local convolutional features and aggregates them using the Vector of Locally Aggregated Descriptors (VLAD) to produce a global descriptor. We study various system parameters such as the multiplicative and additive attention mechanisms and descriptor dimensionality. We propose a query expansion method that requires no external inputs. Experiments demonstrate that even without training, the local convolutional features and global representation outperform other systems. After system tuning, we can achieve state-of-the-art or competitive results. Furthermore, we observe that our query expansion method increases overall system performance by about 3%, using only the top-three retrieved images. Finally, we show how dimensionality reduction produces compact descriptors with increased retrieval performance and fast retrieval computation times, e.g. 50% faster than the current systems.

Clint Sebastian, Bas Boom, Egor Bondarev et al.

Recently, privacy has a growing importance in several domains, especially in street-view images. The conventional way to achieve this is to automatically detect and blur sensitive information from these images. However, the processing cost of blurring increases with the ever-growing resolution of images. We propose a system that is cost-effective even after increasing the resolution by a factor of 2.5. The new system utilizes depth data obtained from LiDAR to significantly reduce the search space for detection, thereby reducing the processing cost. Besides this, we test several detectors after reducing the detection space and provide an alternative solution based on state-of-the-art deep learning detectors to the existing HoG-SVM-Deep system that is faster and has a higher performance.

Hongxu Yang, Caifeng Shan, Alexander F. Kolen et al.

Fast and accurate catheter detection in cardiac catheterization using harmless 3D ultrasound (US) can improve the efficiency and outcome of the intervention. However, the low image quality of US requires extra training for sonographers to localize the catheter. In this paper, we propose a catheter detection method based on a pre-trained VGG network, which exploits 3D information through re-organized cross-sections to segment the catheter by a shared fully convolutional network (FCN), which is called a Direction-Fused FCN (DF-FCN). Based on the segmented image of DF-FCN, the catheter can be localized by model fitting. Our experiments show that the proposed method can successfully detect an ablation catheter in a challenging ex-vivo 3D US dataset, which was collected on the porcine heart. Extensive analysis shows that the proposed method achieves a Dice score of 57.7%, which offers at least an 11.8 % improvement when compared to state-of-the-art instrument detection methods. Due to the improved segmentation performance by the DF-FCN, the catheter can be localized with an error of only 1.4 mm.

Clint Sebastian, Bas Boom, Thijs van Lankveld et al.

Detection of buildings and other objects from aerial images has various applications in urban planning and map making. Automated building detection from aerial imagery is a challenging task, as it is prone to varying lighting conditions, shadows and occlusions. Convolutional Neural Networks (CNNs) are robust against some of these variations, although they fail to distinguish easy and difficult examples. We train a detection algorithm from RGB-D images to obtain a segmented mask by using the CNN architecture DenseNet.First, we improve the performance of the model by applying a statistical re-sampling technique called Bootstrapping and demonstrate that more informative examples are retained. Second, the proposed method outperforms the non-bootstrapped version by utilizing only one-sixth of the original training data and it obtains a precision-recall break-even of 95.10% on our aerial imagery dataset.

Clint Sebastian, Ries Uittenbogaard, Julien Vijverberg et al.

Object detection and classification of traffic signs in street-view imagery is an essential element for asset management, map making and autonomous driving. However, some traffic signs occur rarely and consequently, they are difficult to recognize automatically. To improve the detection and classification rates, we propose to generate images of traffic signs, which are then used to train a detector/classifier. In this research, we present an end-to-end framework that generates a realistic image of a traffic sign from a given image of a traffic sign and a pictogram of the target class. We propose a residual attention mechanism with dense concatenation called Dense Residual Attention, that preserves the background information while transferring the object information. We also propose to utilize multi-scale discriminators, so that the smaller scales of the output guide the higher resolution output. We have performed detection and classification tests across a large number of traffic sign classes, by training the detector using the combination of real and generated data. The newly trained model reduces the number of false positives by 1.2 - 1.5% at 99% recall in the detection tests and an absolute improvement of 4.65% (top-1 accuracy) in the classification tests.

Willem P. Sanberg, Gijs Dubbelman, Peter H. N. de With

Recently, vision-based Advanced Driver Assist Systems have gained broad interest. In this work, we investigate free-space detection, for which we propose to employ a Fully Convolutional Network (FCN). We show that this FCN can be trained in a self-supervised manner and achieve similar results compared to training on manually annotated data, thereby reducing the need for large manually annotated training sets. To this end, our self-supervised training relies on a stereo-vision disparity system, to automatically generate (weak) training labels for the color-based FCN. Additionally, our self-supervised training facilitates online training of the FCN instead of offline. Consequently, given that the applied FCN is relatively small, the free-space analysis becomes highly adaptive to any traffic scene that the vehicle encounters. We have validated our algorithm using publicly available data and on a new challenging benchmark dataset that is released with this paper. Experiments show that the online training boosts performance with 5% when compared to offline training, both for Fmax and AP.