We propose a lightweight compressed-domain tracking model that operates directly on video streams, without requiring full RGB video decoding.Using motion vectors and transform coefficients from compressed data, our deep model propagates object bounding boxes across frames, achieving a computational speed-up of order up to 3.7× with only a slight 4% [email protected] drop vs RGB baseline on MOTS15/17/20 datasets.These results highlight codec-domain motion modeling efficiency for realtime analytics in large monitoring systems.Our implementation is publicly available at : https://github.com/Fr4cti0n/See_without_decoding* This research is

In complex and dynamic environments such as road scenes, autonomous driving systems must make fully informed decisions despite being trained on a limited set of known object classes. This challenge, known as Open-Set Object Detection (OSOD), requires perception systems to detect unknown objects while maintaining reliable detection of critical known classes. Most open-set detectors rely on an objectness score as a first step to distinguish foreground objects from the background. Since this score determines which regions are further processed, its relevance has a direct and significant impact on the overall detection performance. However, our study on road scenes shows that previous attempts to improve this objectness score for unknown object detection degrade known-class detection. This trade-off is paramount for autonomous driving, where reliability on known objects is critical. Thus, this paper aims to develop an objectness score that preserves known-class detection performance while improving unknown object detection in road scenes. We first introduce a unified formulation of previous objectness scores and then propose a training procedure that excludes unlabeled unknowns from the loss calculation. To achieve this, we categorize detected boxes into four types and assign tailored losses. This results in the Driving Oriented Objectness (DROO) score, which is learned through our proposed training procedure. Additionally, we propose an evaluation protocol that isolates the impact of objectness scoring. Our results on CODA dataset, which features challenging corner-case unknowns in road scenes, demonstrate that the approach enhances unknown detection while maintaining accuracy on known classes.

Universal Domain Adaptation (UniDA) aims to transfer knowledge from a labeled source domain to an unlabeled target domain, even when their classes are not fully shared. Few dedicated UniDA methods exist for Time Series (TS), which remains a challenging case. In general, UniDA approaches align common class samples and detect unknown target samples from emerging classes. Such detection often results from thresholding a discriminability metric. The threshold value is typically either a fine-tuned hyperparameter or a fixed value, which limits the ability of the model to adapt to new data. Furthermore, discriminability metrics exhibit overconfidence for unknown samples, leading to misclassifications. This paper introduces UniJDOT, an optimal-transport-based method that accounts for the unknown target samples in the transport cost. Our method also proposes a joint decision space to improve the discriminability of the detection module. In addition, we use an auto-thresholding algorithm to reduce the dependence on fixed or fine-tuned thresholds. Finally, we rely on a Fourier transform-based layer inspired by the Fourier Neural Operator for better TS representation. Experiments on TS benchmarks demonstrate the discriminability, robustness, and state-of-the-art performance of UniJDOT.

Autonomous Vehicles (AVs) are expected to take safe and efficient decisions. Hence, AVs need to be robust to real-world situations and especially to cope with open world setting i.e. the ability to handle novelties such as unseen objects. Classical object detection models are trained to recognize a predefined set of classes but struggle to generalize well to novel classes at inference stage. Open-Set Object Detection (OSOD) aims to address the challenge of correctly detecting objects from unknown classes. However, autonomous driving systems possess specific open-set characteristics that are not yet covered by OSOD methods. Indeed, a detection error could lead to catastrophic events, emphasizing the importance of prioritizing the quality of box detection over quantity. Also, the specific characteristics of objects encountered in road scenes could be leveraged to improve their detection in the open-world setting. In this vein, we introduce a new definition of objects of interest for autonomous driving perception, enabling the proposition of an AV specialized open-set object detector coined ADOS. The proposed model uses a new score, learnt with the background ground truth of the semantic segmentation. This On Road Object score measures whether the object is on drivable areas, enhancing the selection of unknown detection. Experimental evaluations are conducted on simulated and real world datasets and reveal that our method outperforms the baseline approaches in unknown object detection settings with the same detection performance on known objects as the closed-set object detector.

Automatic traffic surveillance usually relies on the estimation of traffic flow parameters through either dedicated sensors or the processing of road surveillance cameras. However, dedicated sensors are expensive to deploy and maintain. Moreover, available video processing algorithms usually require a complex multi-step pipeline, unsuited for large scale deployment. Herein, we address the problem of automatically estimating the flow rate (number of vehicles/unit of time) from surveillance cameras at low computation cost. To do so, we rely on end-to-end deep architectures applied to compressed MPEG4 part-2 video streams issued from road surveillance cameras. By leveraging the approximate flow representation induced by the compression, we heavily reduce the computation and memory requirements. We propose three end-to-end deep architectures using this coarse pixel flow representation as input. We also release two datasets, one based on synthetic videos and one collected on industrial tunnel cameras. By training the deep models on the newly introduced datasets, we evidence the effectiveness of predicting the flow rate directly from MPEG4 part-2 compressed video streams. We demonstrate an improved accuracy in comparison with a more classical RGB-based architecture and show an impressive speed up of$\times 2065$at prediction time.

Wasserstein distance (WD) and the associated optimal transport plan have been proven useful in many applications where probability measures are at stake. In this paper, we propose a new proxy of the squared WD, coined $\textnormal{min-SWGG}$, that is based on the transport map induced by an optimal one-dimensional projection of the two input distributions. We draw connections between $\textnormal{min-SWGG}$, and Wasserstein generalized geodesics in which the pivot measure is supported on a line. We notably provide a new closed form for the exact Wasserstein distance in the particular case of one of the distributions supported on a line allowing us to derive a fast computational scheme that is amenable to gradient descent optimization. We show that $\textnormal{min-SWGG}$, is an upper bound of WD and that it has a complexity similar to as Sliced-Wasserstein, with the additional feature of providing an associated transport plan. We also investigate some theoretical properties such as metricity, weak convergence, computational and topological properties. Empirical evidences support the benefits of $\textnormal{min-SWGG}$, in various contexts, from gradient flows, shape matching and image colorization, among others.

Non-convex sparse regularizers are common tools for learning with high-dimensional data. For accelerating convergence for Lasso problem involving those regularizers, a working set strategy addresses the optimization problem through an iterative algorithm by gradually incrementing the number of variables to optimize until the identification of the solution support. We propose in this paper the first Lasso working set algorithm for non-convex sparse regularizers with convergence guarantees. The algorithm, named FireWorks, is based on a non-convex reformulation of a recent duality-based approach and leverages on the geometry of the residuals. We provide theoretical guarantees showing that convergence is preserved even when the inner solver is inexact, under sufficient decay of the error across iterations. Experimental results demonstrate strong computational gain when using our working set strategy compared to full problem solvers for both block-coordinate descent or a proximal gradient solver.

Acoustic scene classification systems face performance degradation when trained and tested on data recorded by different devices. Unsupervised domain adaptation methods have been studied to reduce the impact of this mismatch. While they do not assume the availability of labels at test time, they often exploit parallel data recorded by both devices, and thus are not fully blind to the target domain. In this paper, we address a more practical scenario where parallel data are not available. We thoroughly analyze the impact of normalization and moment matching strategies to compensate for the linear distortion introduced by the recording device and propose their integration with adversarial domain adaptation to handle the remaining non-linear distortion. Experiments on the DCASE Challenge 2018 Task 1B dataset show that the proposed integrated approach considerably reduces domain mismatch, reaching an accuracy in the target domain close to that obtained in the source domain.

We present a framework based on bilevel optimization for learning multilayer, deep data representations. On the one hand, the lower-level problem finds a representation by successively minimizing layer-wise objectives made of the sum of a prescribed regularizer as well as a fidelity term and some linear function both depending on the representation found at the previous layer. On the other hand, the upper-level problem optimizes over the linear functions to yield a linearly separable final representation. We show that, by choosing the fidelity term as the quadratic distance between two successive layer-wise representations, the bilevel problem reduces to the training of a feed-forward neural network. Instead, by elaborating on Bregman distances, we devise a novel neural network architecture additionally involving the inverse of the activation function reminiscent of the skip connection used in ResNets. Numerical experiments suggest that the proposed Bregman variant benefits from better learning properties and more robust prediction performance.

Common compartmental modeling for COVID-19 is based on a priori knowledge and numerous assumptions. Additionally, they do not systematically incorporate asymptomatic cases. Our study aimed at providing a framework for data-driven approaches, by leveraging the strengths of the grey-box system theory or grey-box identification, known for its robustness in problem solving under partial, incomplete, or uncertain data. Empirical data on confirmed cases and deaths, extracted from an open source repository were used to develop the SEAIRD compartment model. Adjustments were made to fit current knowledge on the COVID-19 behavior. The model was implemented and solved using an Ordinary Differential Equation solver and an optimization tool. A cross-validation technique was applied, and the coefficient of determination R 2 was computed in order to evaluate the goodness-of-fit of the model. Key epidemiological parameters were finally estimated and we provided the rationale for the construction of SEAIRD model. When applied to Brazil’s cases, SEAIRD produced an excellent agreement to the data, with an R 2 ≥ 90 % . The probability of COVID-19 transmission was generally high (≥ 95 % ). On the basis of a 20-day modeling data, the incidence rate of COVID-19 was as low as 3 infected cases per 100,000 exposed persons in Brazil and France. Within the same time frame, the fatality rate of COVID-19 was the highest in France (16.4%) followed by Brazil (6.9%), and the lowest in Russia (≤ 1 % ). SEAIRD represents an asset for modeling infectious diseases in their dynamical stable phase, especially for new viruses when pathophysiology knowledge is very limited.

We propose a novel approach for comparing distributions whose supports do not necessarily lie on the same metric space. Unlike Gromov-Wasserstein (GW) distance which compares pairwise distances of elements from each distribution, we consider a method allowing to embed the metric measure spaces in a common Euclidean space and compute an optimal transport (OT) on the embedded distributions. This leads to what we call a sub-embedding robust Wasserstein (SERW) distance. Under some conditions, SERW is a distance that considers an OT distance of the (low-distorted) embedded distributions using a common metric. In addition to this novel proposal that generalizes several recent OT works, our contributions stand on several theoretical analyses: (i) we characterize the embedding spaces to define SERW distance for distribution alignment; (ii) we prove that SERW mimics almost the same properties of GW distance, and we give a cost relation between GW and SERW. The paper also provides some numerical illustrations of how SERW behaves on matching problems.

This paper addresses the problem of Unbalanced Optimal Transport (UOT) in which the marginal conditions are relaxed (using weighted penalties in lieu of equality) and no additional regularization is enforced on the OT plan. In this context, we show that the corresponding optimization problem can be reformulated as a non-negative penalized linear regression problem. This reformulation allows us to propose novel algorithms inspired from inverse problems and nonnegative matrix factorization. In particular, we consider majorization-minimization which leads in our setting to efficient multiplicative updates for a variety of penalties. Furthermore, we derive for the first time an efficient algorithm to compute the regularization path of UOT with quadratic penalties. The proposed algorithm provides a continuity of piece-wise linear OT plans converging to the solution of balanced OT (corresponding to infinite penalty weights). We perform several numerical experiments on simulated and real data illustrating the new algorithms, and provide a detailed discussion about more sophisticated optimization tools that can further be used to solve OT problems thanks to our reformulation.

Object detection in images has reached unprecedented performances. The state-of-the-art methods rely on deep architectures that extract salient features and predict bounding boxes enclosing the objects of interest. These methods essentially run on RGB images. However, the RGB images are often compressed by the acquisition devices for storage purpose and transfer efficiency. Hence, their decompression is required for object detectors. To gain in efficiency, this paper proposes to take advantage of the compressed representation of images to carry out object detection usable in constrained resources conditions. Specifically, we focus on JPEG images and propose a thorough analysis of detection architectures newly designed in regard of the peculiarities of the JPEG norm. This leads to a ×1.7 speed up in comparison with a standard RGB-based architecture, while only reducing the detection performance by 5.5%. Additionally, our empirical findings demonstrate that only part of the compressed JPEG information, namely the luminance component, may be required to match detection accuracy of the full input methods. Code is made available at: https://github.com/D3lt4lph4/jpeg_deep.

Classical optimal transport problem seeks a transportation map that preserves the total mass between two probability distributions, requiring their masses to be equal. This may be too restrictive in some applications such as color or shape matching, since the distributions may have arbitrary masses and/or only a fraction of the total mass has to be transported. In this paper, we address the partial Wasserstein and Gromov-Wasserstein problems and propose exact algorithms to solve them. We showcase the new formulation in a positive-unlabeled (PU) learning application. To the best of our knowledge, this is the first application of optimal transport in this context and we first highlight that partial Wasserstein-based metrics prove effective in usual PU learning settings. We then demonstrate that partial Gromov-Wasserstein metrics are efficient in scenarii in which the samples from the positive and the unlabeled datasets come from different domains or have different features.

Leveraging on the convexity of the Lasso problem, screening rules help in accelerating solvers by discarding irrelevant variables, during the optimization process. However, because they provide better theoretical guarantees in identifying relevant variables, several non-convex regularizers for the Lasso have been proposed in the literature. This work is the first that introduces a screening rule strategy into a non-convex Lasso solver. The approach we propose is based on a iterative majorization-minimization (MM) strategy that includes a screening rule in the inner solver and a condition for propagating screened variables between iterations of MM. In addition to improve efficiency of solvers, we also provide guarantees that the inner solver is able to identify the zeros components of its critical point in finite time. Our experimental analysis illustrates the significant computational gain brought by the new screening rule compared to classical coordinate-descent or proximal gradient descent methods.

We introduce in this paper a novel strategy for efficiently approximating the Sinkhorn distance between two discrete measures. After identifying neglectable components of the dual solution of the regularized Sinkhorn problem, we propose to screen those components by directly setting them at that value before entering the Sinkhorn problem. This allows us to solve a smaller Sinkhorn problem while ensuring approximation with provable guarantees. More formally, the approach is based on a new formulation of dual of Sinkhorn divergence problem and on the KKT optimality conditions of this problem, which enable identification of dual components to be screened. This new analysis leads to the Screenkhorn algorithm. We illustrate the efficiency of Screenkhorn on complex tasks such as dimensionality reduction and domain adaptation involving regularized optimal transport.

We introduce a novel algorithm for solving learning problems where both the loss function and the regularizer are nonconvex but belong to the class of difference of convex (DC) functions. Our contribution is a new general purpose proximal Newton algorithm that is able to deal with such a situation. The algorithm consists in obtaining a descent direction from an approximation of the loss function and then in performing a line search to ensure a sufficient descent. A theoretical analysis is provided showing that the iterates of the proposed algorithm admit as limit points stationary points of the DC objective function. Numerical experiments show that our approach is more efficient than the current state of the art for a problem with a convex loss function and a nonconvex regularizer. We have also illustrated the benefit of our algorithm in high-dimensional transductive learning problem where both the loss function and regularizers are nonconvex.

Presents our entry to the Detection and Classification of Acoustic Scenes challenge. The approach we propose for classifying acoustic scenes is based on transforming the audio signal into a time-frequency representation and then in extracting relevant features about shapes and evolutions of time-frequency structures. These features are based on histogram of gradients that are subsequently fed to a multi-class linear support vector machines.

Chord represents the back-bone of occidental music genre as it contains rich harmonic information which is useful for various music applications such as music genre classification or music retrieval. Hence, chord recognition or transcription is of importance for music representation. In this paper we focus on chord recognition and especially investigate different features representation used in such a system: classical features as well as a new type of feature we propose are explored. We evaluate their usefulness through a multi-class chord classification problem.

The objective of the paper is to investigate the effect of subject's emotional states on Brain Computer Interface (BCI) performance. Two psycho-physiological experiments are designed and implemented. The first one induces subjects' emotion using video clips first, then involves subjects' in SSVEP task. The second one induces subjects' emotions and SSVEP simultaneously by flickering IAPS pictures in four directions. used to recognize the performed BCI tasks. Based on the performances of learned classifiers, we analyzed the influence of emotion using two statistical tests. The McNamara's test serves to assess if emotion has any influences on mental task performing while Wilcox on signed-rank test analyses if emotion has a positive or detrimental effect on ability to achieve a SSVEP task. Obtained results suggest influence of emotional states: the positive and neutral emotions influence BCI performance similarly, while the negative emotion tends to deteriorate classification accuracy.

This paper addresses the problem of principal subspace tracking in presence of a colored noise. We propose to extend the YAST algorithm to handle such a case. We also propose a Riemannian framework that could benefit to other classical trackers. Finally, as a proof of concept, our method is compared to the only oblique tracker of the literature on a toy dataset.

We describe and evaluate two algorithms for Neyman-Pearson (NP) classification problem which has been recently shown to be of a particular importance for bipartite ranking problems. NP classification is a nonconvex problem involving a constraint on false negatives rate. We investigated batch algorithm based on DC programming and stochastic gradient method well suited for large-scale datasets. Empirical evidences illustrate the potential of the proposed methods.

Recently, there has been much interest around multitask learning (MTL) problem with the constraints that tasks should share a common sparsity profile. Such a problem can be addressed through a regularization framework where the regularizer induces a joint-sparsity pattern between task decision functions. We follow this principled framework and focus on l(p)-l(q) (with 0 ≤ p ≤ 1 and 1 ≤ q ≤ 2) mixed norms as sparsity-inducing penalties. Our motivation for addressing such a larger class of penalty is to adapt the penalty to a problem at hand leading thus to better performances and better sparsity pattern. For solving the problem in the general multiple kernel case, we first derive a variational formulation of the l(1)-l(q) penalty which helps us in proposing an alternate optimization algorithm. Although very simple, the latter algorithm provably converges to the global minimum of the l(1)-l(q) penalized problem. For the linear case, we extend existing works considering accelerated proximal gradient to this penalty. Our contribution in this context is to provide an efficient scheme for computing the l(1)-l(q) proximal operator. Then, for the more general case, when , we solve the resulting nonconvex problem through a majorization-minimization approach. The resulting algorithm is an iterative scheme which, at each iteration, solves a weighted l(1)-l(q) sparse MTL problem. Empirical evidences from toy dataset and real-word datasets dealing with brain-computer interface single-trial electroencephalogram classification and protein subcellular localization show the benefit of the proposed approaches and algorithms.

Using unlabeled data to unravel the structure of the data to leverage the learning process is the goal of semi supervised learning. A common way to represent this underlying structure is to use graphs. Flexibility of the maximum margin kernel framework allows to model graph smoothness and to build kernel machine for semi supervised learning such as Laplacian SVM [1]. But a common complaint of the practitioner is the long running time of these kernel algorithms for classification of new points. We provide an efficient way of alleviating this problem by using a L1 penalization term and a regularization path algorithm to efficiently compute the solution. Empirical evidence shows the benefit of the algorithm.