Person re-identification (ReID) aims to match person images of the same identity under different camera views. Conventional ReID models mainly consider a closed-world setting where person identities in query and gallery are exactly the same. However, in real-world applications, query identities and gallery identities usually do not exactly contain the same persons. Therefore, open-world ReID has been proposed to match the images of gallery identities (targets) with a large number of non-gallery identities ( non-targets). Since some non-targets are quite similar to the targets, the ReID model may make incorrect judgments when verifying these non-targets. To solve this problem, we leverage the impressive cross-modal matching capabilities of the large vision-language model (VLM) to constructNegativeSemantic guided identity boundaries for each person to develop the open-worldReIDmodel (NS-ReID). To construct the identity boundary, we propose Virtual Non-target Repulsion that utilizes negative semantics to prompt the ReID model to push virtual non-targets away from the targets. The prompts expressing negative semantics offer a different perspective to guide the training process to avoid contradictory optimization. Moreover, we propose the Dual-Boost Refinement Learning strategy to train learnable identity prompts to capture detailed identity information, which is essential for constructing the identity boundary since the variations among identities are comparatively small. These facilitate the model in constructing the wide identity boundary of each person. Extensive experiments on two benchmark ReID datasets demonstrate that our proposed NS-ReID achieves state-of-the-art performance compared with existing methods.

Our supplementary material is organized into the following sections: • Section II provides the details of the LOCATION module. • Section III provides the evaluation protocol for the SBU dataset. • Section IV provides the evaluation protocol for cross-dataset experiment on the UCF101 dataset and the VISPR dataset. • Section V provides implementation details for each datasets. • Section VI provides more anonymized frames on the SBU dataset. • Section VII provides more anonymized frames on the UCF101 dataset. • Section VIII provides details about anonymized video file. • Section IX provides ablation studies of the adapter.

To address the low predictive accuracy of existing models for PM10concentration under complex-meteorological conditions, a novel PM10 concentration prediction network, referred to as the Divide Factors Network (DF-Net), is proposed. The DF-Net primarily comprises Divide Factors, a Residual Attention mechanism, and Gated Linear Units (GLU). Using the Variational Mode Decomposition (VMD) method, the PM10concentration signal is decomposed into multiple intrinsic mode functions (IMFs). This process extracts the variation patterns of PM10concentration signals. The SHapley Additive Explanations (SHAP) method is employed to evaluate the influence of meteorological factors on PM10concentration. Each meteorological factor is treated as an independent token and input into the DF-Net. The Residual Attention mechanism ensures the uniform distribution of feature channels across meteorological factors, while the adaptive gating mechanism captures and selects effective features. These features are mapped to the output space via a fully connected layer. Compared with five baseline models, the DF-Net demonstrates superior performance. Ablation experiments validate the model’s feasibility, providing an efficient solution for PM10prediction under complex-meteorological conditions. This solution offers valuable support for environmental management and policy-making.

P4 is widely adopted for programming data planes in software-defined networking. Formal verification of P4 programs is essential to ensure network reliability and security. However, existing P4 verifiers overlook the stateful nature of packet processing, rendering them inadequate for verifying complex stateful P4 programs.In this paper, we introduce a novel concept called packet invariants to address the stateful aspects of P4 programs. We present an automated verification tool specifically designed for stateful P4 programs. This algorithm efficiently discovers and validates packet invariants in a data-driven manner, offering a novel and effective verification approach for stateful P4 programs. To the best of our knowledge, this approach represents the first attempt to generate and leverage domain-specific invariants for P4 program verification. We implement our approach in a prototype tool called P4Inv. Experimental results demonstrate its effectiveness in verifying stateful P4 programs.

In today’s data-driven era, data privacy protection is a key challenge in artificial intelligence development. Federated learning (FL) effectively addresses data silos and privacy concerns, but the statistical heterogeneity among clients limits the performance and generalization of traditional FL methods. Personalized federated learning (pFL) tackles this by training customized models for each client based on local data distributions. However, current pFL methods either focus on fine-tuning the global model on the client side or generating personalized models on the server side, failing to balance global collaboration and personalized learning. To address this, we propose ProtoFedLA, an innovative pFL framework that uses data prototypes to guide personalized model updates. This ensures consistency with the global data distribution while adapting to local data through localized aggregation. We evaluated ProtoFedLA using five publicly available image/text classification datasets under two heterogeneous data environments. The results show significant performance improvements over state-of-the-art pFL methods, with ProtoFedLA outperforming the best baseline by 5.83%. Additionally, ProtoFedLA handles data heterogeneity effectively, while demonstrating excellent stability and scalability.

Playing a vital role in keeping gearbox working reliably and safely, smart fault diagnosis (FD) technology has attracted much attention in recent years. However, in practical industrial applications, owing to the imbalance of healthy state data and fault state data and various unpredictable compound fault modes, it is still extremely challenging to fulfill the high-accuracy and effective FD of gearbox based on existing intelligent diagnostic models. In this paper, a new method is proposed to tackle these problems by integrating an improved deep residual network (IDRN) and wavelet transform (WT). The proposed method mainly contains two parts: In the first part, the vibration signals are transformed into images by WT. In the second part, the IDRN is applied to realize an accurate FD of gearbox. Compared with the original deep residual network, the main differences of IDRN are as follows: first of all, a new loss function is used to replace the commonly used logistic loss function by adding a class-balanced re-weighting term and combining with multi-label classification. Then, attention modules focusing operations on specific regions and enhancing the features of some regions are combined with residual blocks. Finally, a spatial transformer module is inserted into the original deep residual network to scale images and clip the region of interest. Two trials are conducted to validate the effectiveness of WT-IDRN method. The experimental consequences demonstrate that the WT-IDRN method has more excellent performance than the existing intelligent FD method in accuracy and generalization ability.

Learning linear temporal logic on finite traces (LTLf) formulae aims to learn a target formula that characterizes the high-level behavior of a system from observation traces in planning. Existing approaches to learning LTLf formulae, however, can hardly learn accurate LTLf formulae from noisy data. It is challenging to design an efficient search mechanism in the large search space in form of arbitrary LTLf formulae while alleviating the wrong search bias resulting from noisy data. In this paper, we tackle this problem by bridging LTLf inference to GNN inference. Our key theoretical contribution is showing that GNN inference can simulate LTLf inference to distinguish traces. Based on our theoretical result, we design a GNN-based approach, GLTLf, which combines GNN inference and parameter interpretation to seek the target formula in the large search space. Thanks to the non-deterministic learning process of GNNs, GLTLf is able to cope with noise. We evaluate GLTLf on various datasets with noise. Our experimental results confirm the effectiveness of GNN inference in learning LTLf formulae and show that GLTLf is superior to the state-of-the-art approaches.

Configuration checking (CC) has been confirmed to alleviate the cycling problem in local search for combinatorial optimization problems (COPs). When using CC heuristics in local search for graph problems, a critical concept is the configuration of the vertices. All existing CC variants employ either 1- or 2-level neighborhoods of a vertex as its configuration. Inspired by the idea that neighborhoods with different levels should have different contributions to solving COPs, we propose the probabilistic configuration (PC), which introduces probabilities for neighborhoods at different levels to consider the impact of neighborhoods of different levels on the CC strategy. Based on the concept of PC, we first propose probabilistic configuration checking (PCC), which can be developed in an automated and lightweight favor. We then apply PCC to two classic COPs which have been shown to achieve good results by using CC, and our preliminary results confirm that PCC improves the existing algorithms because PCC alleviates the cycling problem.

Linear temporal logic over finite traces (LTLf) satisfiability checking is a fundamental and hard (PSPACE-complete) problem in the artificial intelligence community. We explore teaching end-to-end neural networks to check satisfiability in polynomial time. It is a challenge to characterize the syntactic and semantic features of LTLf via neural networks. To tackle this challenge, we propose LTLfNet, a recursive neural network that captures syntactic features of LTLf by recursively combining the embeddings of sub-formulae. LTLfNet models permutation invariance and sequentiality in the semantics of LTLf through different aggregation mechanisms of sub-formulae. Experimental results demonstrate that LTLfNet achieves good performance in synthetic datasets and generalizes across large-scale datasets. They also show that LTLfNet is competitive with state-of-the-art symbolic approaches such as nuXmv and CDLSC.

Linear temporal logic (LTL) satisfiability checking is a fundamental and hard (PSPACE-complete) problem. In this paper, we explore checking LTL satisfiability via end-to-end learning, so that we can take only polynomial time to check LTL satisfiability. Existing approaches have shown that it is possible to leverage end-to-end neural networks to predict the Boolean satisfiability problem with performance considerably higher than random guessing. Inspired by these approaches, we study two interesting questions: can end-to-end neural networks check LTL satisfiability, and can neural networks capture the semantics of LTL? To this end, we train different neural networks for keeping three logical properties of LTL, i.e., recursive property, permutation invariance, and sequentiality. We demonstrate that neural networks can indeed capture some effective biases for checking LTL satisfiability. Besides, designing a special neural network keeping the logical properties of LTL can provide a better inductive bias. We also show the competitive results of neural networks compared with state-of-the-art approaches, i.e., nuXmv and Aalta, on large scale datasets.

Skin conditions affect 1.9 billion people. Because of a shortage of dermatologists, most cases are seen instead by general practitioners with lower diagnostic accuracy. Current skin disease researches adopt the auto-classification system for improving the accuracy rate of skin disease classification. It is therefore an important task to develop Computer Aided Detection (CAD) systems that can aid/enhance dermatologists workflow and improve the classification performances. However, the long-tailed class distribution in the database and the limitation of ability to achieve a spatially invariant features make this problem challenging. We propose a ST-MetaDiagnosis, which utilizes meta-learning and spatial transform learning to facilitate quick adaptation and generalization of deep neural networks trained on the common diseases data for identification of rare diseases with much less annotated data. In particular, in order to predict the target risk where there are limited data samples, we train a meta-learner with spatial transforming from a set of related risk prediction tasks which learns how a good predictor is learned. The meta-learned can be directly used in target risk prediction, and the limited available samples can be used for further fine-tuning the model performance. Experiments on the recent ISIC 2018 skin lesion classification dataset show that our ST-MetaDiagnosis obtains 64.6% (accuracy) and 64.4% (F1-score) on the diagnosis of actinic keratosis, vascular lesion and dermatofibroma, demonstrating that ST-MetaDiagnosis can improve performance for predicting target risk with low resources comparing with the predictor trained on the limited samples available for this risk.