Search

In the field of computer vision, the persistent presence of color bias, resulting from fluctuations in real-world lighting and camera conditions, presents a substantial challenge to the robustness of models. This issue is particularly pronounced in complex wide-area surveillance scenarios, such as person re-identification and industrial dust segmentation, where models often experience a decline in performance due to overfitting on color information during training, given the presence of environmental variations. Consequently, there is a need to effectively adapt models to cope with the complexities of camera conditions. To address this challenge, this study introduces a learning strategy named Random Color Erasing, which draws inspiration from ensemble learning. This strategy selectively erases partial or complete color information in the training data without disrupting the original image structure, thereby achieving a balanced weighting of color features and other features within the neural network. This approach mitigates the risk of overfitting and enhances the model's ability to handle color variation, thereby improving its overall robustness. The approach we propose serves as an ensemble learning strategy, characterized by robust interpretability. A comprehensive analysis of this methodology is presented in this paper. Across various tasks such as person re-identification and semantic segmentation, our approach consistently improves strong baseline methods. Notably, in comparison to existing methods that prioritize color robustness, our strategy significantly enhances performance in cross-domain scenarios. The code available at \url{https://github.com/layumi/Person\_reID\_baseline\_pytorch/blob/master/random\_erasing.py} or \url{https://github.com/finger-monkey/Data-Augmentation}.

Kolmogorov-Arnold Networks (KAN) is a groundbreaking model recently proposed by the MIT team, representing a revolutionary approach with the potential to be a game-changer in the field. This innovative concept has rapidly garnered worldwide interest within the AI community. Inspired by the Kolmogorov-Arnold representation theorem, KAN utilizes spline-parametrized univariate functions in place of traditional linear weights, enabling them to dynamically learn activation patterns and significantly enhancing interpretability. In this paper, we explore the application of KAN to time series forecasting and propose two variants: T-KAN and MT-KAN. T-KAN is designed to detect concept drift within time series and can explain the nonlinear relationships between predictions and previous time steps through symbolic regression, making it highly interpretable in dynamically changing environments. MT-KAN, on the other hand, improves predictive performance by effectively uncovering and leveraging the complex relationships among variables in multivariate time series. Experiments validate the effectiveness of these approaches, demonstrating that T-KAN and MT-KAN significantly outperform traditional methods in time series forecasting tasks, not only enhancing predictive accuracy but also improving model interpretability. This research opens new avenues for adaptive forecasting models, highlighting the potential of KAN as a powerful and interpretable tool in predictive analytics.

Despite the widespread applications of machine learning force field (MLFF) on solids and small molecules, there is a notable gap in applying MLFF to complex liquid electrolytes. In this work, we introduce BAMBOO (ByteDance AI Molecular Simulation Booster), a novel framework for molecular dynamics (MD) simulations, with a demonstration of its capabilities in the context of liquid electrolytes for lithium batteries. We design a physics-inspired graph equivariant transformer architecture as the backbone of BAMBOO to learn from quantum mechanical simulations. Additionally, we pioneer an ensemble knowledge distillation approach and apply it on MLFFs to improve the stability of MD simulations. Finally, we propose the density alignment algorithm to align BAMBOO with experimental measurements. BAMBOO demonstrates state-of-the-art accuracy in predicting key electrolyte properties such as density, viscosity, and ionic conductivity across various solvents and salt combinations. Our current model, trained on more than 15 chemical species, achieves the average density error of 0.01 g/cm$^3$ on various compositions compared with experimental data. Moreover, our model demonstrates transferability to molecules not included in the quantum mechanical dataset. We envision this work as paving the way to a "universal MLFF" capable of simulating properties of common organic liquids.

Machine learning techniques have outperformed numerous rule-based methods for decision-making in autonomous vehicles. Despite recent efforts, lane changing remains a major challenge, due to the complex driving scenarios and changeable social behaviors of surrounding vehicles. To help improve the state of the art, we propose to leveraging the emerging \underline{D}eep \underline{R}einforcement learning (DRL) approach for la\underline{NE} changing at the \underline{T}actical level. To this end, we present "DRNet", a novel and highly efficient DRL-based framework that enables a DRL agent to learn to drive by executing reasonable lane changing on simulated highways with an arbitrary number of lanes, and considering driving style of surrounding vehicles to make better decisions. Furthermore, to achieve a safe policy for decision-making, DRNet incorporates ideas from safety verification, the most important component of autonomous driving, to ensure that only safe actions are chosen at any time. The setting of our state representation and reward function enables the trained agent to take appropriate actions in a real-world-like simulator. Our DRL agent has the ability to learn the desired task without causing collisions and outperforms DDQN and other baseline models.

Min Shi,* Jing Chen,* Tianxiao Liu,* Weixin Dai, Zhan Zhou, Lifei Chen, Yubo Xie Department of Anesthesiology, The First Affiliated Hospital of Guangxi Medical University, Nanning, 530021, People’s Republic of China*These authors contributed equally to this workCorrespondence: Yubo Xie, Department of Anesthesiology, The First Affiliated Hospital of Guangxi Medical University, No. 6 Shuang-yong Road, Nanning, 530021, People’s Republic of China, Tel +86 186 7795 8208, Email xybdoctor@163.comIntroduction: Remimazolam is a novel benzodiazepine γ-aminobutyric acid A (GABAa) receptor agonist used for sedation and the induction as well as maintenance of general anesthesia. Previous research proved that anesthetic agents acting on GABAa receptor, such as thiopentone, propofol and midazolam, have protective actions for cerebral ischemia/reperfusion (I/R) injury. We here probed into remimazolam for its protective effect and potential mechanism of action against cerebral I/R injury.Material and Methods: A rat model of middle cerebral artery occlusion (MCAO) with focal transient cerebral I/R injury was established and was given tail vein injection of gradient remimazolam (5, 10, 20 mg/kg) after 2 h of ischemia. Following 24 h of reperfusion, neurological function, brain infarct volume, morphology of cerebral cortical neurons, and expressions of corticocerebral NLRP3, ASC, caspase-1, GSDMD, IL-1β and IL-18 were evaluated.Results: The results showed that remimazolam could effectively improve the neurological dysfunction, reduce the infarct volume and alleviate the damage of cortical neurons after I/R injury. Notably, the expression of NLRP3 inflammasome pathway was down-regulated, suggesting that remimazolam exerted protective actions on I/R injury by suppressing pyroptosis with decreased expression and release of inflammatory factors, and the involvement of the NLRP3 inflammasome pathway might be the core during that process. Overall, our re

The main challenges of ReID is the intra-class variations caused by color deviation under different camera conditions. Simultaneously, we find that most of the existing adversarial metric attacks are realized by interfering with the color characteristics of the sample. Based on this observation, we first propose a local transformation attack (LTA) based on color variation. It uses more obvious color variation to randomly disturb the color of the retrieved image, rather than adding random noise. Experiments show that the performance of the proposed LTA method is better than the advanced attack methods. Furthermore, considering that the contour feature is the main factor of the robustness of adversarial training, and the color feature will directly affect the success rate of attack. Therefore, we further propose joint adversarial defense (JAD) method, which include proactive defense and passive defense. Proactive defense fuse multi-modality images to enhance the contour feature and color feature, and considers local homomorphic transformation to solve the over-fitting problem. Passive defense exploits the invariance of contour feature during image scaling to mitigate the adversarial disturbance on contour feature. Finally, a series of experimental results show that the proposed joint adversarial defense method is more competitive than a state-of-the-art methods., Comment: Accepted by CVPR2022 Workshops (https://openaccess.thecvf.com/content/CVPR2022W/HCIS/html/Gong_Person_Re-Identification_Method_Based_on_Color_Attack_and_Joint_Defence_CVPRW_2022_paper.html)

One of the challenges of computer vision is that it needs to adapt to color deviations in changeable environments. Therefore, minimizing the adverse effects of color deviation on the prediction is one of the main goals of vision task. Current solutions focus on using generative models to augment training data to enhance the invariance of input variation. However, such methods often introduce new noise, which limits the gain from generated data. To this end, this paper proposes a strategy eliminate deviation with deviation, which is named Random Color Dropout (RCD). Our hypothesis is that if there are color deviation between the query image and the gallery image, the retrieval results of some examples will be better after ignoring the color information. Specifically, this strategy balances the weights between color features and color-independent features in the neural network by dropouting partial color information in the training data, so as to overcome the effect of color devitaion. The proposed RCD can be combined with various existing ReID models without changing the learning strategy, and can be applied to other computer vision fields, such as object detection. Experiments on several ReID baselines and three common large-scale datasets such as Market1501, DukeMTMC, and MSMT17 have verified the effectiveness of this method. Experiments on Cross-domain tests have shown that this strategy is significant eliminating the domain gap. Furthermore, in order to understand the working mechanism of RCD, we analyzed the effectiveness of this strategy from the perspective of classification, which reveals that it may be better to utilize many instead of all of color information in visual tasks with strong domain variations.

Spécialement conçue pour traiter des problèmes d'occurrences évènementielles, l'analyse de survie a très souvent été appliquée dans de nombreux domaines tels que l'ingénierie, la médicine et les soins de santé. Au fil des années de nombreuses approches statistiques liées à l'analyse de survie ont été développées pour à priori adresser la question de prédiction du temps de réalisation d'un évènement. Avec l'avancée des technologies de l'information et de la communication, dans plusieurs domaines d'expertises, nous faisons face de nos jours à une explosion de données qui sont pour la plupart variables avec le temps. De part les différents travaux portés sur l'analyse de survie, le forage et la classification des données volumineuses et longitudinales suscitent de plus en plus l'intérêt des chercheurs. Bien que riches en variables informatives, l'analyse des données évènementiels posent de nombreux défis dus à: une corrélation non-linéaire entre variables, un fort taux de données censurées (données manquantes), une dépendance temporelle sur les variables, une distribution complexe sur les données massives et multi-dimensionnelles. La présente thèse a pour objectif de résoudre les problèmes ci-haut mentionnés. Pour ce faire, nous proposons: (1) un modèle de classification des données massives et longitudinales pour l'analyse de survie. (2) Une nouvelle fonction cumulative de hasard. Cette fonction cumulative met en exergue de manière effective et concise la relation entre la probabilité de survie et l'aspect chronologique des variables. (3) Une nouvelle fonction de hasard semi-proportionnelle qui rend les paramètres de la régression de Cox localement variables. (4) Une nouvelle technique de séquençage des données évènementiels et une vraisemblance complète pour mieux et facilement prédire l'occurrence d'un évènement à travers les différents intervalles de temps. (5) Un réseau de neurones binaire purement basé sur les données observées qui sera capable d'estimer le risqu