Marc Van Droogenbroeck

Renaud Vandeghen, Anthony Cioppa, Marc Van Droogenbroeck

Accurate player and ball detection has become increasingly important in recent years for sport analytics. As most state-of-the-art methods rely on training deep learning networks in a supervised fashion, they require huge amounts of annotated data, which are rarely available. In this paper, we present a novel generic semi-supervised method to train a network based on a labeled image dataset by leveraging a large unlabeled dataset of soccer broadcast videos. More precisely, we design a teacher-student approach in which the teacher produces surrogate annotations on the unlabeled data to be used later for training a student which has the same architecture as the teacher. Furthermore, we introduce three training loss parametrizations that allow the student to doubt the predictions of the teacher during training depending on the proposal confidence score. We show that including unlabeled data in the training process allows to substantially improve the performances of the detection network trained only on the labeled data. Finally, we provide a thorough performance study including different proportions of labeled and unlabeled data, and establish the first benchmark on the new SoccerNet-v3 detection task, with an mAP of 52.3%. Our code is available at https://github.com/rvandeghen/SST .

Anthony Cioppa, Silvio Giancola, Vladimir Somers et al. · pku

The SoccerNet 2023 challenges were the third annual video understanding challenges organized by the SoccerNet team. For this third edition, the challenges were composed of seven vision-based tasks split into three main themes. The first theme, broadcast video understanding, is composed of three high-level tasks related to describing events occurring in the video broadcasts: (1) action spotting, focusing on retrieving all timestamps related to global actions in soccer, (2) ball action spotting, focusing on retrieving all timestamps related to the soccer ball change of state, and (3) dense video captioning, focusing on describing the broadcast with natural language and anchored timestamps. The second theme, field understanding, relates to the single task of (4) camera calibration, focusing on retrieving the intrinsic and extrinsic camera parameters from images. The third and last theme, player understanding, is composed of three low-level tasks related to extracting information about the players: (5) re-identification, focusing on retrieving the same players across multiple views, (6) multiple object tracking, focusing on tracking players and the ball through unedited video streams, and (7) jersey number recognition, focusing on recognizing the jersey number of players from tracklets. Compared to the previous editions of the SoccerNet challenges, tasks (2-3-7) are novel, including new annotations and data, task (4) was enhanced with more data and annotations, and task (6) now focuses on end-to-end approaches. More information on the tasks, challenges, and leaderboards are available on https://www.soccer-net.org. Baselines and development kits can be found on https://github.com/SoccerNet.

Renaud Vandeghen, Gilles Louppe, Marc Van Droogenbroeck

Deep learning has emerged as an effective solution for solving the task of object detection in images but at the cost of requiring large labeled datasets. To mitigate this cost, semi-supervised object detection methods, which consist in leveraging abundant unlabeled data, have been proposed and have already shown impressive results. However, most of these methods require linking a pseudo-label to a ground-truth object by thresholding. In previous works, this threshold value is usually determined empirically, which is time consuming, and only done for a single data distribution. When the domain, and thus the data distribution, changes, a new and costly parameter search is necessary. In this work, we introduce our method Adaptive Self-Training for Object Detection (ASTOD), which is a simple yet effective teacher-student method. ASTOD determines without cost a threshold value based directly on the ground value of the score histogram. To improve the quality of the teacher predictions, we also propose a novel pseudo-labeling procedure. We use different views of the unlabeled images during the pseudo-labeling step to reduce the number of missed predictions and thus obtain better candidate labels. Our teacher and our student are trained separately, and our method can be used in an iterative fashion by replacing the teacher by the student. On the MS-COCO dataset, our method consistently performs favorably against state-of-the-art methods that do not require a threshold parameter, and shows competitive results with methods that require a parameter sweep search. Additional experiments with respect to a supervised baseline on the DIOR dataset containing satellite images lead to similar conclusions, and prove that it is possible to adapt the score threshold automatically in self-training, regardless of the data distribution. The code is available at https:// github.com/rvandeghen/ASTOD

Sébastien Piérard, Anthony Cioppa, Anaïs Halin et al.

Various tasks encountered in real-world surveillance can be addressed by determining posteriors (e.g. by Bayesian inference or machine learning), based on which critical decisions must be taken. However, the surveillance domain (acquisition device, operating conditions, etc.) is often unknown, which prevents any possibility of scene-specific optimization. In this paper, we define a probabilistic framework and present a formal proof of an algorithm for the unsupervised many-to-infinity domain adaptation of posteriors. Our proposed algorithm is applicable when the probability measure associated with the target domain is a convex combination of the probability measures of the source domains. It makes use of source models and a domain discriminator model trained off-line to compute posteriors adapted on the fly to the target domain. Finally, we show the effectiveness of our algorithm for the task of semantic segmentation in real-world surveillance. The code is publicly available at https://github.com/rvandeghen/MDA.

Anthony Cioppa, Silvio Giancola, Adrien Deliege et al.

Tracking objects in soccer videos is extremely important to gather both player and team statistics, whether it is to estimate the total distance run, the ball possession or the team formation. Video processing can help automating the extraction of those information, without the need of any invasive sensor, hence applicable to any team on any stadium. Yet, the availability of datasets to train learnable models and benchmarks to evaluate methods on a common testbed is very limited. In this work, we propose a novel dataset for multiple object tracking composed of 200 sequences of 30s each, representative of challenging soccer scenarios, and a complete 45-minutes half-time for long-term tracking. The dataset is fully annotated with bounding boxes and tracklet IDs, enabling the training of MOT baselines in the soccer domain and a full benchmarking of those methods on our segregated challenge sets. Our analysis shows that multiple player, referee and ball tracking in soccer videos is far from being solved, with several improvement required in case of fast motion or in scenarios of severe occlusion.

Silvio Giancola, Anthony Cioppa, Adrien Deliège et al.

The SoccerNet 2022 challenges were the second annual video understanding challenges organized by the SoccerNet team. In 2022, the challenges were composed of 6 vision-based tasks: (1) action spotting, focusing on retrieving action timestamps in long untrimmed videos, (2) replay grounding, focusing on retrieving the live moment of an action shown in a replay, (3) pitch localization, focusing on detecting line and goal part elements, (4) camera calibration, dedicated to retrieving the intrinsic and extrinsic camera parameters, (5) player re-identification, focusing on retrieving the same players across multiple views, and (6) multiple object tracking, focusing on tracking players and the ball through unedited video streams. Compared to last year's challenges, tasks (1-2) had their evaluation metrics redefined to consider tighter temporal accuracies, and tasks (3-6) were novel, including their underlying data and annotations. More information on the tasks, challenges and leaderboards are available on https://www.soccer-net.org. Baselines and development kits are available on https://github.com/SoccerNet.

Hassan Mkhallati, Anthony Cioppa, Silvio Giancola et al.

Soccer is more than just a game - it is a passion that transcends borders and unites people worldwide. From the roar of the crowds to the excitement of the commentators, every moment of a soccer match is a thrill. Yet, with so many games happening simultaneously, fans cannot watch them all live. Notifications for main actions can help, but lack the engagement of live commentary, leaving fans feeling disconnected. To fulfill this need, we propose in this paper a novel task of dense video captioning focusing on the generation of textual commentaries anchored with single timestamps. To support this task, we additionally present a challenging dataset consisting of almost 37k timestamped commentaries across 715.9 hours of soccer broadcast videos. Additionally, we propose a first benchmark and baseline for this task, highlighting the difficulty of temporally anchoring commentaries yet showing the capacity to generate meaningful commentaries. By providing broadcasters with a tool to summarize the content of their video with the same level of engagement as a live game, our method could help satisfy the needs of the numerous fans who follow their team but cannot necessarily watch the live game. We believe our method has the potential to enhance the accessibility and understanding of soccer content for a wider audience, bringing the excitement of the game to more people.

Jan Held, Anthony Cioppa, Silvio Giancola et al.

The Video Assistant Referee (VAR) has revolutionized association football, enabling referees to review incidents on the pitch, make informed decisions, and ensure fairness. However, due to the lack of referees in many countries and the high cost of the VAR infrastructure, only professional leagues can benefit from it. In this paper, we propose a Video Assistant Referee System (VARS) that can automate soccer decision-making. VARS leverages the latest findings in multi-view video analysis, to provide real-time feedback to the referee, and help them make informed decisions that can impact the outcome of a game. To validate VARS, we introduce SoccerNet-MVFoul, a novel video dataset of soccer fouls from multiple camera views, annotated with extensive foul descriptions by a professional soccer referee, and we benchmark our VARS to automatically recognize the characteristics of these fouls. We believe that VARS has the potential to revolutionize soccer refereeing and take the game to new heights of fairness and accuracy across all levels of professional and amateur federations.

Renaud Vandeghen, Fida Mohammad Thoker, Marc Van Droogenbroeck et al.

Masked video modeling (MVM) has emerged as a simple and scalable self-supervised pretraining paradigm, but only encodes motion information implicitly, limiting the encoding of temporal dynamics in the learned representations. As a result, such models struggle on motion-centric tasks that require fine-grained motion awareness. To address this, we propose TrackMAE, a simple masked video modeling paradigm that explicitly uses motion information as a reconstruction signal. In TrackMAE, we use an off-the-shelf point tracker to sparsely track points in the input videos, generating motion trajectories. Furthermore, we exploit the extracted trajectories to improve random tube masking with a motion-aware masking strategy. We enhance video representations learned in both pixel and feature semantic reconstruction spaces by providing a complementary supervision signal in the form of motion targets. We evaluate on six datasets across diverse downstream settings and find that TrackMAE consistently outperforms state-of-the-art video self-supervised learning baselines, learning more discriminative and generalizable representations. Code available at https://github.com/rvandeghen/TrackMAE

Silvio Giancola, Anthony Cioppa, Julia Georgieva et al.

Association football is a complex and dynamic sport, with numerous actions occurring simultaneously in each game. Analyzing football videos is challenging and requires identifying subtle and diverse spatio-temporal patterns. Despite recent advances in computer vision, current algorithms still face significant challenges when learning from limited annotated data, lowering their performance in detecting these patterns. In this paper, we propose an active learning framework that selects the most informative video samples to be annotated next, thus drastically reducing the annotation effort and accelerating the training of action spotting models to reach the highest accuracy at a faster pace. Our approach leverages the notion of uncertainty sampling to select the most challenging video clips to train on next, hastening the learning process of the algorithm. We demonstrate that our proposed active learning framework effectively reduces the required training data for accurate action spotting in football videos. We achieve similar performances for action spotting with NetVLAD++ on SoccerNet-v2, using only one-third of the dataset, indicating significant capabilities for reducing annotation time and improving data efficiency. We further validate our approach on two new datasets that focus on temporally localizing actions of headers and passes, proving its effectiveness across different action semantics in football. We believe our active learning framework for action spotting would support further applications of action spotting algorithms and accelerate annotation campaigns in the sports domain.

Joachim Houyon, Anthony Cioppa, Yasir Ghunaim et al.

In recent years, online distillation has emerged as a powerful technique for adapting real-time deep neural networks on the fly using a slow, but accurate teacher model. However, a major challenge in online distillation is catastrophic forgetting when the domain shifts, which occurs when the student model is updated with data from the new domain and forgets previously learned knowledge. In this paper, we propose a solution to this issue by leveraging the power of continual learning methods to reduce the impact of domain shifts. Specifically, we integrate several state-of-the-art continual learning methods in the context of online distillation and demonstrate their effectiveness in reducing catastrophic forgetting. Furthermore, we provide a detailed analysis of our proposed solution in the case of cyclic domain shifts. Our experimental results demonstrate the efficacy of our approach in improving the robustness and accuracy of online distillation, with potential applications in domains such as video surveillance or autonomous driving. Overall, our work represents an important step forward in the field of online distillation and continual learning, with the potential to significantly impact real-world applications.

Anthony Cioppa, Silvio Giancola, Vladimir Somers et al.

The SoccerNet 2024 challenges represent the fourth annual video understanding challenges organized by the SoccerNet team. These challenges aim to advance research across multiple themes in football, including broadcast video understanding, field understanding, and player understanding. This year, the challenges encompass four vision-based tasks. (1) Ball Action Spotting, focusing on precisely localizing when and which soccer actions related to the ball occur, (2) Dense Video Captioning, focusing on describing the broadcast with natural language and anchored timestamps, (3) Multi-View Foul Recognition, a novel task focusing on analyzing multiple viewpoints of a potential foul incident to classify whether a foul occurred and assess its severity, (4) Game State Reconstruction, another novel task focusing on reconstructing the game state from broadcast videos onto a 2D top-view map of the field. Detailed information about the tasks, challenges, and leaderboards can be found at https://www.soccer-net.org, with baselines and development kits available at https://github.com/SoccerNet.

Carles Cantero, Olivier Absil, Carl-Henrik Dahlqvist et al.

Supervised deep learning was recently introduced in high-contrast imaging (HCI) through the SODINN algorithm, a convolutional neural network designed for exoplanet detection in angular differential imaging (ADI) datasets. The benchmarking of HCI algorithms within the Exoplanet Imaging Data Challenge (EIDC) showed that (i) SODINN can produce a high number of false positives in the final detection maps, and (ii) algorithms processing images in a more local manner perform better. This work aims to improve the SODINN detection performance by introducing new local processing approaches and adapting its learning process accordingly. We propose NA-SODINN, a new deep learning binary classifier based on a convolutional neural network (CNN) that better captures image noise correlations in ADI-processed frames by identifying noise regimes. Our new approach was tested against its predecessor, as well as two SODINN-based hybrid models and a more standard annular-PCA approach, through local receiving operating characteristics (ROC) analysis of ADI sequences from the VLT/SPHERE and Keck/NIRC-2 instruments. Results show that NA-SODINN enhances SODINN in both sensitivity and specificity, especially in the speckle-dominated noise regime. NA-SODINN is also benchmarked against the complete set of submitted detection algorithms in EIDC, in which we show that its final detection score matches or outperforms the most powerful detection algorithms.Throughout the supervised machine learning case, this study illustrates and reinforces the importance of adapting the task of detection to the local content of processed images.

Jan Held, Anthony Cioppa, Silvio Giancola et al.

Over the past decade, the technology used by referees in football has improved substantially, enhancing the fairness and accuracy of decisions. This progress has culminated in the implementation of the Video Assistant Referee (VAR), an innovation that enables backstage referees to review incidents on the pitch from multiple points of view. However, the VAR is currently limited to professional leagues due to its expensive infrastructure and the lack of referees worldwide. In this paper, we present the semi-automated Video Assistant Referee System (VARS) that leverages the latest findings in multi-view video analysis. VARS sets a new state-of-the-art on the SoccerNet-MVFoul dataset, a multi-view video dataset of football fouls. Our VARS achieves a new state-of-the-art on the SoccerNet-MVFoul dataset by recognizing the type of foul in 50% of instances and the appropriate sanction in 46% of cases. Finally, we conducted a comparative study to investigate human performance in classifying fouls and their corresponding severity and compared these findings to our VARS. The results of our study highlight the potential of our VARS to reach human performance and support football refereeing across all levels of professional and amateur federations.

Maxim Henry, Adrien Deliège, Sébastien Piérard et al.

Training high-capacity vision models from scratch requires substantial computational resources. To improve training efficiency of a wide target model, existing growth methods often assume the availability of narrower models, obscuring the true computational cost of the entire pipeline. We propose an efficient training protocol, RBDC, that builds wide models by coupling in a parameter-free block-diagonal way narrower, independently trained models in a recursive way. This allows a flexible allocation of the training budget available across all the models involved. Evaluated with vision transformers (DeiT) and convolutional networks (ResNet) on ImageNet, our RBDC training protocol shows a much better efficiency than models trained from scratch with the standard protocol, yielding 30% FLOPs reduction at similar test accuracies. It also achieves higher performances at same training FLOPs than training protocols from the model growth literature. Finally, we show that our models can serve as better backbones than their original counterparts for downstream object detection and instance segmentation tasks.

Xavier Bou, Nathan Correger, Alexandre Cloots et al.

Fatigue monitoring is central in association football due to its links with injury risk and tactical performance. However, objective fatigue-related indicators are commonly derived from subjective self-reported metrics, biomarkers derived from laboratory tests, or, more recently, intrusive sensors such as heart monitors or GPS tracking data. This paper studies whether monocular broadcast videos can provide spatio-temporal signals of sufficient quality to support fatigue-oriented analysis. Building on state-of-the-art Game State Reconstruction methods, we extract player trajectories in pitch coordinates and propose a novel kinematics processing algorithm to obtain temporally consistent speed and acceleration estimates from reconstructed tracks. We then construct acceleration--speed (A-S) profiles from these signals and analyze their behavior as fatigue-related performance indicators. We evaluate the full pipeline on the public SoccerNet-GSR benchmark, considering both 30-second clips and a complete 45-minute half to examine short-term reliability and longer-term temporal consistency. Our results indicate that monocular GSR can recover kinematic patterns that are compatible with A-S profiling while also revealing sensitivity to trajectory noise, calibration errors, and temporal discontinuities inherent to broadcast footage. These findings support monocular broadcast video as a low-cost basis for fatigue analysis and delineate the methodological challenges for future research.

Antoine Deckyvere, Anthony Cioppa, Silvio Giancola et al.

Slow-motion replays provide a thrilling perspective on pivotal moments within sports games, offering a fresh and captivating visual experience. However, capturing slow-motion footage typically demands high-tech, expensive cameras and infrastructures. Deep learning Video Frame Interpolation (VFI) techniques have emerged as a promising avenue, capable of generating high-speed footage from regular camera feeds. Moreover, the utilization of event-based cameras has recently gathered attention as they provide valuable motion information between frames, further enhancing the VFI performances. In this work, we present a first investigation of event-based VFI models for generating sports slow-motion videos. Particularly, we design and implement a bi-camera recording setup, including an RGB and an event-based camera to capture sports videos, to temporally align and spatially register both cameras. Our experimental validation demonstrates that TimeLens, an off-the-shelf event-based VFI model, can effectively generate slow-motion footage for sports videos. This first investigation underscores the practical utility of event-based cameras in producing sports slow-motion content and lays the groundwork for future research endeavors in this domain.

Yassine Benzakour, Bruno Cabado, Silvio Giancola et al.

Action spotting is crucial in sports analytics as it enables the precise identification and categorization of pivotal moments in sports matches, providing insights that are essential for performance analysis and tactical decision-making. The fragmentation of existing methodologies, however, impedes the progression of sports analytics, necessitating a unified codebase to support the development and deployment of action spotting for video analysis. In this work, we introduce OSL-ActionSpotting, a Python library that unifies different action spotting algorithms to streamline research and applications in sports video analytics. OSL-ActionSpotting encapsulates various state-of-the-art techniques into a singular, user-friendly framework, offering standardized processes for action spotting and analysis across multiple datasets. We successfully integrated three cornerstone action spotting methods into OSL-ActionSpotting, achieving performance metrics that match those of the original, disparate codebases. This unification within a single library preserves the effectiveness of each method and enhances usability and accessibility for researchers and practitioners in sports analytics. By bridging the gaps between various action spotting techniques, OSL-ActionSpotting significantly contributes to the field of sports video analysis, fostering enhanced analytical capabilities and collaborative research opportunities. The scalable and modularized design of the library ensures its long-term relevance and adaptability to future technological advancements in the domain.

Vladimir Somers, Victor Joos, Anthony Cioppa et al.

Tracking and identifying athletes on the pitch holds a central role in collecting essential insights from the game, such as estimating the total distance covered by players or understanding team tactics. This tracking and identification process is crucial for reconstructing the game state, defined by the athletes' positions and identities on a 2D top-view of the pitch, (i.e. a minimap). However, reconstructing the game state from videos captured by a single camera is challenging. It requires understanding the position of the athletes and the viewpoint of the camera to localize and identify players within the field. In this work, we formalize the task of Game State Reconstruction and introduce SoccerNet-GSR, a novel Game State Reconstruction dataset focusing on football videos. SoccerNet-GSR is composed of 200 video sequences of 30 seconds, annotated with 9.37 million line points for pitch localization and camera calibration, as well as over 2.36 million athlete positions on the pitch with their respective role, team, and jersey number. Furthermore, we introduce GS-HOTA, a novel metric to evaluate game state reconstruction methods. Finally, we propose and release an end-to-end baseline for game state reconstruction, bootstrapping the research on this task. Our experiments show that GSR is a challenging novel task, which opens the field for future research. Our dataset and codebase are publicly available at https://github.com/SoccerNet/sn-gamestate.

Alexandre Eymaël, Renaud Vandeghen, Anthony Cioppa et al.

Self-supervised pre-training of image encoders is omnipresent in the literature, particularly following the introduction of Masked autoencoders (MAE). Current efforts attempt to learn object-centric representations from motion in videos. In particular, SiamMAE recently introduced a Siamese network, training a shared-weight encoder from two frames of a video with a high asymmetric masking ratio (95%). In this work, we propose CropMAE, an alternative approach to the Siamese pre-training introduced by SiamMAE. Our method specifically differs by exclusively considering pairs of cropped images sourced from the same image but cropped differently, deviating from the conventional pairs of frames extracted from a video. CropMAE therefore alleviates the need for video datasets, while maintaining competitive performances and drastically reducing pre-training and learning time. Furthermore, we demonstrate that CropMAE learns similar object-centric representations without explicit motion, showing that current self-supervised learning methods do not learn such representations from explicit object motion, but rather thanks to the implicit image transformations that occur between the two views. Finally, CropMAE achieves the highest masking ratio to date (98.5%), enabling the reconstruction of images using only two visible patches. Our code is available at https://github.com/alexandre-eymael/CropMAE.

Victor Rong, Jan Held, Victor Chu et al.

Though Gaussian splatting has achieved impressive results in novel view synthesis, it requires millions of primitives to model highly textured scenes, even when the geometry of the scene is simple. We propose a representation that goes beyond point-based rendering and decouples geometry and appearance in order to achieve a compact representation. We use surfels for geometry and a combination of a global neural field and per-primitive colours for appearance. The neural field textures a fixed number of primitives for each pixel, ensuring that the added compute is low. Our representation matches the perceptual quality of 3D Gaussian splatting while using $9.7\times$ fewer primitives and $5.5\times$ less memory on outdoor scenes and using $31\times$ fewer primitives and $3.7\times$ less memory on indoor scenes. Our representation also renders twice as fast as existing textured primitives while improving upon their visual quality.

Floriane Magera, Thomas Hoyoux, Olivier Barnich et al.

Camera calibration and localization, sometimes simply named camera calibration, enables many applications in the context of soccer broadcasting, for instance regarding the interpretation and analysis of the game, or the insertion of augmented reality graphics for storytelling or refereeing purposes. To contribute to such applications, the research community has typically focused on single-view calibration methods, leveraging the near-omnipresence of soccer field markings in wide-angle broadcast views, but leaving all temporal aspects, if considered at all, to general-purpose tracking or filtering techniques. Only a few contributions have been made to leverage any domain-specific knowledge for this tracking task, and, as a result, there lacks a truly performant and off-the-shelf camera tracking system tailored for soccer broadcasting, specifically for elevated tripod-mounted cameras around the stadium. In this work, we present such a system capable of addressing the task of soccer broadcast camera tracking efficiently, robustly, and accurately, outperforming by far the most precise methods of the state-of-the-art. By combining the available open-source soccer field detectors with carefully designed camera and tripod models, our tracking system, BroadTrack, halves the mean reprojection error rate and gains more than 15% in terms of Jaccard index for camera calibration on the SoccerNet dataset. Furthermore, as the SoccerNet dataset videos are relatively short (30 seconds), we also present qualitative results on a 20-minute broadcast clip to showcase the robustness and the soundness of our system.

Mohamad Dalal, Artur Xarles, Anthony Cioppa et al.

Artificial intelligence has revolutionized the way we analyze sports videos, whether to understand the actions of games in long untrimmed videos or to anticipate the player's motion in future frames. Despite these efforts, little attention has been given to anticipating game actions before they occur. In this work, we introduce the task of action anticipation for football broadcast videos, which consists in predicting future actions in unobserved future frames, within a five- or ten-second anticipation window. To benchmark this task, we release a new dataset, namely the SoccerNet Ball Action Anticipation dataset, based on SoccerNet Ball Action Spotting. Additionally, we propose a Football Action ANticipation TRAnsformer (FAANTRA), a baseline method that adapts FUTR, a state-of-the-art action anticipation model, to predict ball-related actions. To evaluate action anticipation, we introduce new metrics, including mAP@$δ$, which evaluates the temporal precision of predicted future actions, as well as mAP@$\infty$, which evaluates their occurrence within the anticipation window. We also conduct extensive ablation studies to examine the impact of various task settings, input configurations, and model architectures. Experimental results highlight both the feasibility and challenges of action anticipation in football videos, providing valuable insights into the design of predictive models for sports analytics. By forecasting actions before they unfold, our work will enable applications in automated broadcasting, tactical analysis, and player decision-making. Our dataset and code are publicly available at https://github.com/MohamadDalal/FAANTRA.

Michaël Fonder, Marc Van Droogenbroeck

When used by autonomous vehicles for trajectory planning or obstacle avoidance, depth estimation methods need to be reliable. Therefore, estimating the quality of the depth outputs is critical. In this paper, we show how M4Depth, a state-of-the-art depth estimation method designed for unmanned aerial vehicle (UAV) applications, can be enhanced to perform joint depth and uncertainty estimation. For that, we present a solution to convert the uncertainty estimates related to parallax generated by M4Depth into uncertainty estimates related to depth, and show that it outperforms the standard probabilistic approach. Our experiments on various public datasets demonstrate that our method performs consistently, even in zero-shot transfer. Besides, our method offers a compelling value when compared to existing multi-view depth estimation methods as it performs similarly on a multi-view depth estimation benchmark despite being 2.5 times faster and causal, as opposed to other methods. The code of our method is publicly available at https://github.com/michael-fonder/M4DepthU .

Michaël Fonder, Damien Ernst, Marc Van Droogenbroeck

Estimating the distance to objects is crucial for autonomous vehicles when using depth sensors is not possible. In this case, the distance has to be estimated from on-board mounted RGB cameras, which is a complex task especially in environments such as natural outdoor landscapes. In this paper, we present a new method named M4Depth for depth estimation. First, we establish a bijective relationship between depth and the visual disparity of two consecutive frames and show how to exploit it to perform motion-invariant pixel-wise depth estimation. Then, we detail M4Depth which is based on a pyramidal convolutional neural network architecture where each level refines an input disparity map estimate by using two customized cost volumes. We use these cost volumes to leverage the visual spatio-temporal constraints imposed by motion and to make the network robust for varied scenes. We benchmarked our approach both in test and generalization modes on public datasets featuring synthetic camera trajectories recorded in a wide variety of outdoor scenes. Results show that our network outperforms the state of the art on these datasets, while also performing well on a standard depth estimation benchmark. The code of our method is publicly available at https://github.com/michael-fonder/M4Depth.

Adrien Deliège, Anthony Cioppa, Silvio Giancola et al.

Understanding broadcast videos is a challenging task in computer vision, as it requires generic reasoning capabilities to appreciate the content offered by the video editing. In this work, we propose SoccerNet-v2, a novel large-scale corpus of manual annotations for the SoccerNet video dataset, along with open challenges to encourage more research in soccer understanding and broadcast production. Specifically, we release around 300k annotations within SoccerNet's 500 untrimmed broadcast soccer videos. We extend current tasks in the realm of soccer to include action spotting, camera shot segmentation with boundary detection, and we define a novel replay grounding task. For each task, we provide and discuss benchmark results, reproducible with our open-source adapted implementations of the most relevant works in the field. SoccerNet-v2 is presented to the broader research community to help push computer vision closer to automatic solutions for more general video understanding and production purposes.

Anthony Cioppa, Marc Van Droogenbroeck, Marc Braham

Semantic background subtraction SBS has been shown to improve the performance of most background subtraction algorithms by combining them with semantic information, derived from a semantic segmentation network. However, SBS requires high-quality semantic segmentation masks for all frames, which are slow to compute. In addition, most state-of-the-art background subtraction algorithms are not real-time, which makes them unsuitable for real-world applications. In this paper, we present a novel background subtraction algorithm called Real-Time Semantic Background Subtraction (denoted RT-SBS) which extends SBS for real-time constrained applications while keeping similar performances. RT-SBS effectively combines a real-time background subtraction algorithm with high-quality semantic information which can be provided at a slower pace, independently for each pixel. We show that RT-SBS coupled with ViBe sets a new state of the art for real-time background subtraction algorithms and even competes with the non real-time state-of-the-art ones. Note that we provide python CPU and GPU implementations of RT-SBS at https://github.com/cioppaanthony/rt-sbs.

Jan Held, Hani Itani, Anthony Cioppa et al.

The rapid advancement of artificial intelligence has led to significant improvements in automated decision-making. However, the increased performance of models often comes at the cost of explainability and transparency of their decision-making processes. In this paper, we investigate the capabilities of large language models to explain decisions, using football refereeing as a testing ground, given its decision complexity and subjectivity. We introduce the Explainable Video Assistant Referee System, X-VARS, a multi-modal large language model designed for understanding football videos from the point of view of a referee. X-VARS can perform a multitude of tasks, including video description, question answering, action recognition, and conducting meaningful conversations based on video content and in accordance with the Laws of the Game for football referees. We validate X-VARS on our novel dataset, SoccerNet-XFoul, which consists of more than 22k video-question-answer triplets annotated by over 70 experienced football referees. Our experiments and human study illustrate the impressive capabilities of X-VARS in interpreting complex football clips. Furthermore, we highlight the potential of X-VARS to reach human performance and support football referees in the future.

Jan Held, Renaud Vandeghen, Abdullah Hamdi et al.

Recent advances in radiance field reconstruction, such as 3D Gaussian Splatting (3DGS), have achieved high-quality novel view synthesis and fast rendering by representing scenes with compositions of Gaussian primitives. However, 3D Gaussians present several limitations for scene reconstruction. Accurately capturing hard edges is challenging without significantly increasing the number of Gaussians, creating a large memory footprint. Moreover, they struggle to represent flat surfaces, as they are diffused in space. Without hand-crafted regularizers, they tend to disperse irregularly around the actual surface. To circumvent these issues, we introduce a novel method, named 3D Convex Splatting (3DCS), which leverages 3D smooth convexes as primitives for modeling geometrically-meaningful radiance fields from multi-view images. Smooth convex shapes offer greater flexibility than Gaussians, allowing for a better representation of 3D scenes with hard edges and dense volumes using fewer primitives. Powered by our efficient CUDA-based rasterizer, 3DCS achieves superior performance over 3DGS on benchmarks such as Mip-NeRF360, Tanks and Temples, and Deep Blending. Specifically, our method attains an improvement of up to 0.81 in PSNR and 0.026 in LPIPS compared to 3DGS while maintaining high rendering speeds and reducing the number of required primitives. Our results highlight the potential of 3D Convex Splatting to become the new standard for high-quality scene reconstruction and novel view synthesis. Project page: convexsplatting.github.io.

Floriane Magera, Thomas Hoyoux, Olivier Barnich et al.

Camera calibration is a crucial component in the realm of sports analytics, as it serves as the foundation to extract 3D information out of the broadcast images. Despite the significance of camera calibration research in sports analytics, progress is impeded by outdated benchmarking criteria. Indeed, the annotation data and evaluation metrics provided by most currently available benchmarks strongly favor and incite the development of sports field registration methods, i.e. methods estimating homographies that map the sports field plane to the image plane. However, such homography-based methods are doomed to overlook the broader capabilities of camera calibration in bridging the 3D world to the image. In particular, real-world non-planar sports field elements (such as goals, corner flags, baskets, ...) and image distortion caused by broadcast camera lenses are out of the scope of sports field registration methods. To overcome these limitations, we designed a new benchmarking protocol, named ProCC, based on two principles: (1) the protocol should be agnostic to the camera model chosen for a camera calibration method, and (2) the protocol should fairly evaluate camera calibration methods using the reprojection of arbitrary yet accurately known 3D objects. Indirectly, we also provide insights into the metric used in SoccerNet-calibration, which solely relies on image annotation data of viewed 3D objects as ground truth, thus implementing our protocol. With experiments on the World Cup 2014, CARWC, and SoccerNet datasets, we show that our benchmarking protocol provides fairer evaluations of camera calibration methods. By defining our requirements for proper benchmarking, we hope to pave the way for a new stage in camera calibration for sports applications with high accuracy standards.

Jan Held, Renaud Vandeghen, Adrien Deliege et al.

The field of computer graphics was revolutionized by models such as Neural Radiance Fields and 3D Gaussian Splatting, displacing triangles as the dominant representation for photogrammetry. In this paper, we argue for a triangle comeback. We develop a differentiable renderer that directly optimizes triangles via end-to-end gradients. We achieve this by rendering each triangle as differentiable splats, combining the efficiency of triangles with the adaptive density of representations based on independent primitives. Compared to popular 2D and 3D Gaussian Splatting methods, our approach achieves higher visual fidelity, faster convergence, and increased rendering throughput. On the Mip-NeRF360 dataset, our method outperforms concurrent non-volumetric primitives in visual fidelity and achieves higher perceptual quality than the state-of-the-art Zip-NeRF on indoor scenes. Triangles are simple, compatible with standard graphics stacks and GPU hardware, and highly efficient: for the \textit{Garden} scene, we achieve over 2,400 FPS at 1280x720 resolution using an off-the-shelf mesh renderer. These results highlight the efficiency and effectiveness of triangle-based representations for high-quality novel view synthesis. Triangles bring us closer to mesh-based optimization by combining classical computer graphics with modern differentiable rendering frameworks. The project page is https://trianglesplatting.github.io/

Anaïs Halin, Sébastien Piérard, Anthony Cioppa et al.

Properly understanding the performances of classifiers is essential in various scenarios. However, the literature often relies only on one or two standard scores to compare classifiers, which fails to capture the nuances of application-specific requirements. The Tile is a recently introduced visualization tool organizing an infinity of ranking scores into a 2D map. Thanks to the Tile, it is now possible to compare classifiers efficiently, displaying all possible application-specific preferences instead of having to rely on a pair of scores. This hitchhiker's guide to understanding the performances of two-class classifiers presents four scenarios showcasing different user profiles: a theoretical analyst, a method designer, a benchmarker, and an application developer. We introduce several interpretative flavors adapted to the user's needs by mapping different values on the Tile. We illustrate this guide by ranking and analyzing the performances of 74 state-of-the-art semantic segmentation models through the perspective of the four scenarios. Through these user profiles, we demonstrate that the Tile effectively captures the behavior of classifiers in a single visualization, while accommodating an infinite number of ranking scores. Code for mapping the different Tile flavors is available in supplementary material.

Sébastien Piérard, Anaïs Halin, Anthony Cioppa et al.

Ranking entities such as algorithms, devices, methods, or models based on their performances, while accounting for application-specific preferences, is a challenge. To address this challenge, we establish the foundations of a universal theory for performance-based ranking. First, we introduce a rigorous framework built on top of both the probability and order theories. Our new framework encompasses the elements necessary to (1) manipulate performances as mathematical objects, (2) express which performances are worse than or equivalent to others, (3) model tasks through a variable called satisfaction, (4) consider properties of the evaluation, (5) define scores, and (6) specify application-specific preferences through a variable called importance. On top of this framework, we propose the first axiomatic definition of performance orderings and performance-based rankings. Then, we introduce a universal parametric family of scores, called ranking scores, that can be used to establish rankings satisfying our axioms, while considering application-specific preferences. Finally, we show, in the case of two-class classification, that the family of ranking scores encompasses well-known performance scores, including the accuracy, the true positive rate (recall, sensitivity), the true negative rate (specificity), the positive predictive value (precision), and F1. However, we also show that some other scores commonly used to compare classifiers are unsuitable to derive performance orderings satisfying the axioms.

Sébastien Piérard, Anaïs Halin, Anthony Cioppa et al.

In the computer vision and machine learning communities, as well as in many other research domains, rigorous evaluation of any new method, including classifiers, is essential. One key component of the evaluation process is the ability to compare and rank methods. However, ranking classifiers and accurately comparing their performances, especially when taking application-specific preferences into account, remains challenging. For instance, commonly used evaluation tools like Receiver Operating Characteristic (ROC) and Precision/Recall (PR) spaces display performances based on two scores. Hence, they are inherently limited in their ability to compare classifiers across a broader range of scores and lack the capability to establish a clear ranking among classifiers. In this paper, we present a novel versatile tool, named the Tile, that organizes an infinity of ranking scores in a single 2D map for two-class classifiers, including common evaluation scores such as the accuracy, the true positive rate, the positive predictive value, Jaccard's coefficient, and all F-beta scores. Furthermore, we study the properties of the underlying ranking scores, such as the influence of the priors or the correspondences with the ROC space, and depict how to characterize any other score by comparing them to the Tile. Overall, we demonstrate that the Tile is a powerful tool that effectively captures all the rankings in a single visualization and allows interpreting them.

Benoît Gérin, Anaïs Halin, Anthony Cioppa et al.

In the era of the Internet of Things (IoT), objects connect through a dynamic network, empowered by technologies like 5G, enabling real-time data sharing. However, smart objects, notably autonomous vehicles, face challenges in critical local computations due to limited resources. Lightweight AI models offer a solution but struggle with diverse data distributions. To address this limitation, we propose a novel Multi-Stream Cellular Test-Time Adaptation (MSC-TTA) setup where models adapt on the fly to a dynamic environment divided into cells. Then, we propose a real-time adaptive student-teacher method that leverages the multiple streams available in each cell to quickly adapt to changing data distributions. We validate our methodology in the context of autonomous vehicles navigating across cells defined based on location and weather conditions. To facilitate future benchmarking, we release a new multi-stream large-scale synthetic semantic segmentation dataset, called DADE, and show that our multi-stream approach outperforms a single-stream baseline. We believe that our work will open research opportunities in the IoT and 5G eras, offering solutions for real-time model adaptation.

Floriane Magera, Thomas Hoyoux, Martin Castin et al.

Single-frame sports field registration often serves as the foundation for extracting 3D information from broadcast videos, enabling applications related to sports analytics, refereeing, or fan engagement. As sports fields have rigorous specifications in terms of shape and dimensions of their line, circle and point components, sports field markings are commonly used as calibration targets for this task. However, because of the sparse and uneven distribution of field markings, close-up camera views around central areas of the field often depict only line and circle markings. On these views, sports field registration is challenging for the vast majority of existing methods, as they focus on leveraging line field markings and their intersections. It is indeed a challenge to include circle correspondences in a set of linear equations. In this work, we propose a novel method to derive a set of points and lines from circle correspondences, enabling the exploitation of circle correspondences for both sports field registration and image annotation. In our experiments, we illustrate the benefits of our bottom-up geometric method against top-performing detectors and show that our method successfully complements them, enabling sports field registration in difficult scenarios.

Anaïs Halin, Sébastien Piérard, Renaud Vandeghen et al.

Characterizing domains is essential for models analyzing dynamic environments, as it allows them to adapt to evolving conditions or to hand the task over to backup systems when facing conditions outside their operational domain. Existing solutions typically characterize a domain by solving a regression or classification problem, which limits their applicability as they only provide a limited summarized description of the domain. In this paper, we present a novel approach to domain characterization by characterizing domains as probability distributions. Particularly, we develop a method to predict the likelihood of different weather conditions from images captured by vehicle-mounted cameras by estimating distributions of physical parameters using normalizing flows. To validate our proposed approach, we conduct experiments within the context of autonomous vehicles, focusing on predicting the distribution of weather parameters to characterize the operational domain. This domain is characterized by physical parameters (absolute characterization) and arbitrarily predefined domains (relative characterization). Finally, we evaluate whether a system can safely operate in a target domain by comparing it to multiple source domains where safety has already been established. This approach holds significant potential, as accurate weather prediction and effective domain adaptation are crucial for autonomous systems to adjust to dynamic environmental conditions.

Sébastien Piérard, Adrien Deliège, Marc Van Droogenbroeck

Ranking methods or models based on their performance is of prime importance but is tricky because performance is fundamentally multidimensional. In the case of classification, precision and recall are scores with probabilistic interpretations that are both important to consider and complementary. The rankings induced by these two scores are often in partial contradiction. In practice, therefore, it is extremely useful to establish a compromise between the two views to obtain a single, global ranking. Over the last fifty years or so,it has been proposed to take a weighted harmonic mean, known as the F-score, F-measure, or $F_β$. Generally speaking, by averaging basic scores, we obtain a score that is intermediate in terms of values. However, there is no guarantee that these scores lead to meaningful rankings and no guarantee that the rankings are good tradeoffs between these base scores. Given the ubiquity of $F_β$ scores in the literature, some clarification is in order. Concretely: (1) We establish that $F_β$-induced rankings are meaningful and define a shortest path between precision- and recall-induced rankings. (2) We frame the problem of finding a tradeoff between two scores as an optimization problem expressed with Kendall rank correlations. We show that $F_1$ and its skew-insensitive version are far from being optimal in that regard. (3) We provide theoretical tools and a closed-form expression to find the optimal value for $β$ for any distribution or set of performances, and we illustrate their use on six case studies.

Jan Held, Renaud Vandeghen, Sanghyun Son et al.

Reconstructing 3D scenes and synthesizing novel views has seen rapid progress in recent years. Neural Radiance Fields demonstrated that continuous volumetric radiance fields can achieve high-quality image synthesis, but their long training and rendering times limit practicality. 3D Gaussian Splatting (3DGS) addressed these issues by representing scenes with millions of Gaussians, enabling real-time rendering and fast optimization. However, Gaussian primitives are not natively compatible with the mesh-based pipelines used in VR headsets, and real-time graphics applications. Existing solutions attempt to convert Gaussians into meshes through post-processing or two-stage pipelines, which increases complexity and degrades visual quality. In this work, we introduce Triangle Splatting+, which directly optimizes triangles, the fundamental primitive of computer graphics, within a differentiable splatting framework. We formulate triangle parametrization to enable connectivity through shared vertices, and we design a training strategy that enforces opaque triangles. The final output is immediately usable in standard graphics engines without post-processing. Experiments on the Mip-NeRF360 and Tanks & Temples datasets show that Triangle Splatting+achieves state-of-the-art performance in mesh-based novel view synthesis. Our method surpasses prior splatting approaches in visual fidelity while remaining efficient and fast to training. Moreover, the resulting semi-connected meshes support downstream applications such as physics-based simulation or interactive walkthroughs. The project page is https://trianglesplatting2.github.io/trianglesplatting2/.

Sébastien Piérard, Adrien Deliège, Anaïs Halin et al.

Frequently, multiple entities (methods, algorithms, procedures, solutions, etc.) can be developed for a common task and applied across various domains that differ in the distribution of scenarios encountered. For example, in computer vision, the input data provided to image analysis methods depend on the type of sensor used, its location, and the scene content. However, a crucial difficulty remains: can we predict which entities will perform best in a new domain based on assessments on known domains, without having to carry out new and costly evaluations? This paper presents an original methodology to address this question, in a leave-one-domain-out fashion, for various application-specific preferences. We illustrate its use with 30 strategies to predict the rankings of 40 entities (unsupervised background subtraction methods) on 53 domains (videos).

Sébastien Piérard, Marc Braham, Marc Van Droogenbroeck

Background subtraction (BGS) is a common choice for performing motion detection in video. Hundreds of BGS algorithms are released every year, but combining them to detect motion remains largely unexplored. We found that combination strategies allow to capitalize on this massive amount of available BGS algorithms, and offer significant space for performance improvement. In this paper, we explore sets of performances achievable by 6 strategies combining, pixelwise, the outputs of 26 unsupervised BGS algorithms, on the CDnet 2014 dataset, both in the ROC space and in terms of the F1 score. The chosen strategies are representative for a large panel of strategies, including both deterministic and non-deterministic ones, voting and learning. In our experiments, we compare our results with the state-of-the-art combinations IUTIS-5 and CNN-SFC, and report six conclusions, among which the existence of an important gap between the performances of the individual algorithms and the best performances achievable by combining them.

Adrien Deliège, Maxime Istasse, Ashwani Kumar et al.

In the framework of convolutional neural networks, downsampling is often performed with an average-pooling, where all the activations are treated equally, or with a max-pooling operation that only retains an element with maximum activation while discarding the others. Both of these operations are restrictive and have previously been shown to be sub-optimal. To address this issue, a novel pooling scheme, named\emph{ ordinal pooling}, is introduced in this work. Ordinal pooling rearranges all the elements of a pooling region in a sequence and assigns a different weight to each element based upon its order in the sequence. These weights are used to compute the pooling operation as a weighted sum of the rearranged elements of the pooling region. They are learned via a standard gradient-based training, allowing to learn a behavior anywhere in the spectrum of average-pooling to max-pooling in a differentiable manner. Our experiments suggest that it is advantageous for the networks to perform different types of pooling operations within a pooling layer and that a hybrid behavior between average- and max-pooling is often beneficial. More importantly, they also demonstrate that ordinal pooling leads to consistent improvements in the accuracy over average- or max-pooling operations while speeding up the training and alleviating the issue of the choice of the pooling operations and activation functions to be used in the networks. In particular, ordinal pooling mainly helps on lightweight or quantized deep learning architectures, as typically considered e.g. for embedded applications.

Adrien Deliège, Anthony Cioppa, Marc Van Droogenbroeck

Supervised image classification problems rely on training data assumed to have been correctly annotated; this assumption underpins most works in the field of deep learning. In consequence, during its training, a network is forced to match the label provided by the annotator and is not given the flexibility to choose an alternative to inconsistencies that it might be able to detect. Therefore, erroneously labeled training images may end up ``correctly'' classified in classes which they do not actually belong to. This may reduce the performances of the network and thus incite to build more complex networks without even checking the quality of the training data. In this work, we question the reliability of the annotated datasets. For that purpose, we introduce the notion of ghost loss, which can be seen as a regular loss that is zeroed out for some predicted values in a deterministic way and that allows the network to choose an alternative to the given label without being penalized. After a proof of concept experiment, we use the ghost loss principle to detect confusing images and erroneously labeled images in well-known training datasets (MNIST, Fashion-MNIST, SVHN, CIFAR10) and we provide a new tool, called sanity matrix, for summarizing these confusions.

Anthony Cioppa, Adrien Deliège, Floriane Magera et al.

Soccer broadcast video understanding has been drawing a lot of attention in recent years within data scientists and industrial companies. This is mainly due to the lucrative potential unlocked by effective deep learning techniques developed in the field of computer vision. In this work, we focus on the topic of camera calibration and on its current limitations for the scientific community. More precisely, we tackle the absence of a large-scale calibration dataset and of a public calibration network trained on such a dataset. Specifically, we distill a powerful commercial calibration tool in a recent neural network architecture on the large-scale SoccerNet dataset, composed of untrimmed broadcast videos of 500 soccer games. We further release our distilled network, and leverage it to provide 3 ways of representing the calibration results along with player localization. Finally, we exploit those representations within the current best architecture for the action spotting task of SoccerNet-v2, and achieve new state-of-the-art performances.

Anthony Cioppa, Adrien Deliège, Noor Ul Huda et al.

Monitoring the occupancy of public sports facilities is essential to assess their use and to motivate their construction in new places. In the case of a football field, the area to cover is large, thus several regular cameras should be used, which makes the setup expensive and complex. As an alternative, we developed a system that detects players from a unique cheap and wide-angle fisheye camera assisted by a single narrow-angle thermal camera. In this work, we train a network in a knowledge distillation approach in which the student and the teacher have different modalities and a different view of the same scene. In particular, we design a custom data augmentation combined with a motion detection algorithm to handle the training in the region of the fisheye camera not covered by the thermal one. We show that our solution is effective in detecting players on the whole field filmed by the fisheye camera. We evaluate it quantitatively and qualitatively in the case of an online distillation, where the student detects players in real time while being continuously adapted to the latest video conditions.

Anthony Cioppa, Adrien Deliège, Silvio Giancola et al.

In video understanding, action spotting consists in temporally localizing human-induced events annotated with single timestamps. In this paper, we propose a novel loss function that specifically considers the temporal context naturally present around each action, rather than focusing on the single annotated frame to spot. We benchmark our loss on a large dataset of soccer videos, SoccerNet, and achieve an improvement of 12.8% over the baseline. We show the generalization capability of our loss for generic activity proposals and detection on ActivityNet, by spotting the beginning and the end of each activity. Furthermore, we provide an extended ablation study and display challenging cases for action spotting in soccer videos. Finally, we qualitatively illustrate how our loss induces a precise temporal understanding of actions and show how such semantic knowledge can be used for automatic highlights generation.

A. Deliege, A. Cioppa, M. Van Droogenbroeck

Neural networks designed for the task of classification have become a commodity in recent years. Many works target the development of more effective networks, which results in a complexification of their architectures with more layers, multiple sub-networks, or even the combination of multiple classifiers, but this often comes at the expense of producing uninterpretable black boxes. In this paper, we redesign a simple capsule network to enable it to synthesize class-representative samples, called prototypes, by replacing the last layer with a novel Hit-or-Miss layer. This layer contains activated vectors, called capsules, that we train to hit or miss a fixed target capsule by tailoring a specific centripetal loss function. This possibility allows to develop a data augmentation step combining information from the data space and the feature space, resulting in a hybrid data augmentation process. We show that our network, named HitNet, is able to reach better performances than those reproduced with the initial CapsNet on several datasets, while allowing to visualize the nature of the features extracted as deformations of the prototypes, which provides a direct insight into the feature representation learned by the network .

Adrien Deliège, Anthony Cioppa, Marc Van Droogenbroeck

Neural networks designed for the task of classification have become a commodity in recent years. Many works target the development of better networks, which results in a complexification of their architectures with more layers, multiple sub-networks, or even the combination of multiple classifiers. In this paper, we show how to redesign a simple network to reach excellent performances, which are better than the results reproduced with CapsNet on several datasets, by replacing a layer with a Hit-or-Miss layer. This layer contains activated vectors, called capsules, that we train to hit or miss a central capsule by tailoring a specific centripetal loss function. We also show how our network, named HitNet, is capable of synthesizing a representative sample of the images of a given class by including a reconstruction network. This possibility allows to develop a data augmentation step combining information from the data space and the feature space, resulting in a hybrid data augmentation process. In addition, we introduce the possibility for HitNet, to adopt an alternative to the true target when needed by using the new concept of ghost capsules, which is used here to detect potentially mislabeled images in the training data.