Advances in multimodal pre-training have propelled object-level foundation models, such as Grounding DINO and Florence-2, in tasks like visual grounding and object detection. However, interpreting these models’ decisions has grown increasingly challenging. Existing interpretable attribution methods for object-level task interpretation have notable limitations: (1) gradient-based methods lack precise localization due to visual-textual fusion in foundation models, and (2) perturbation-based methods produce noisy saliency maps, limiting fine-grained interpretability. To address these, we propose a Visual Precision Search method that generates accurate attribution maps with fewer regions. Our method bypasses internal model parameters to overcome attribution issues from multimodal fusion, dividing inputs into sparse sub-regions and using consistency and collaboration scores to accurately identify critical decision-making regions. We also conducted a theoretical analysis of the boundary guarantees and scope of applicability of our method. Experiments on RefCOCO, MS COCO, and LVIS show our approach enhances object-level task interpretability over SOTA for Grounding DINO and Florence-2 across various evaluation metrics, with faithfulness gains of 23.7%, 31.6%, and 20.1% on MS COCO, LVIS, and RefCOCO for Grounding DINO, and 50.7% and 66.9% on MS COCO and RefCOCO for Florence-2. Additionally, our method can interpret failures in visual grounding and object detection tasks, surpassing existing methods across multiple evaluation metrics. The code is released at https://github.com/RuoyuChen10/VPS.

The technology of autonomous driving vehicles has made rapid progress over the last decade, but the challenge of proving these system's safety still exists. Compared to conventional mile-based testing, scenario-based testing (SBT) is a more promising solution since scenarios covering diverse and rare driving conditions in real traffic can be simulated to assess the system's performance in safety-critical scenarios. Furthermore, understanding run-time scenarios is vital to trigger safety mechanisms designed for the Safety Of The Intended Functionality (SOTIF). However, a challenging task is to extract or generate scenarios in the design phase and recognize driving scenarios in the run-time phase due to the complexity and diversity of driving scenarios, especially the interaction with other driving agents. In this study, we proposed a complete framework for offline extraction and online identification of all kinds of interaction scenarios. A covariance-clustering based method was adopted to identify the meta-driving actions, which used the Toeplitz matrix to achieve more interpretable clustering results than distance-based methods. Experiments demonstrated the effectiveness of our method by its robust identification results for cut-in and merge-in scenarios. With a lightweight design and a theoretically valid confidence estimation method, our approach is computationally efficient for reliable online applications.

Crop biomass offers crucial insights into plant health and yield, making it essential for crop science, farming systems, and agricultural research. However, current measurement methods, which are labor-intensive, destructive, and imprecise, hinder large-scale quantification of this trait. To address this limitation, we present a biomass prediction network (BioNet), designed for adaptation across different data modalities, including point clouds and drone imagery. Our BioNet, utilizing a sparse 3D convolutional neural network (CNN) and a transformer-based prediction module, processes point clouds and other 3D data representations to predict biomass. To further extend BioNet for drone imagery, we integrate a neural feature field (NeFF) module, enabling 3D structure reconstruction and the transformation of 2D semantic features from vision foundation models into the corresponding 3D surfaces. For the point cloud modality, BioNet demonstrates superior performance on two public datasets, with an approximate 6.1% relative improvement (RI) over the state-of-the-art. In the RGB image modality, the combination of BioNet and NeFF achieves a 7.9% RI. Additionally, the NeFF-based approach utilizes inexpensive, portable drone-mounted cameras, providing a scalable solution for large field applications.

Infrared small target detection technology is one of the key technologies in the field of computer vision. In recent years, several methods have been proposed for detecting small infrared targets. However, the existing methods are highly sensitive to challenging heterogeneous backgrounds, which are mainly due to: 1) infrared images containing mostly heavy clouds and chaotic sea backgrounds and 2) the inefficiency of utilizing the structural prior knowledge of the target. In this article, we propose a novel approach for infrared small target detection in order to take both the structural prior knowledge of the target and the self-correlation of the background into account. First, we construct a tensor model for the high-dimensional structural characteristics of multiframe infrared images. Second, inspired by the low-rank background and morphological operator, a novel method based on low-rank tensor completion with top-hat regularization is proposed, which integrates low-rank tensor completion and a ring top-hat regularization into our model. Third, a closed solution to the optimization algorithm is given to solve the proposed tensor model. Furthermore, the experimental results from seven real infrared sequences demonstrate the superiority of the proposed small target detection method. Compared with traditional baseline methods, the proposed method can not only achieve an improvement in the signal-to-clutter ratio gain and background suppression factor but also provide a more robust detection model in situations with low false-positive rates.

Recently, infrared small target detection problem has attracted substantial attention. Many works based on local low-rank model have been proven to be very successful for enhancing the discriminability during detection. However, these methods construct patches by traversing local images and ignore the correlations among different patches. Although the calculation is simplified, some texture information of the target is ignored, and targets of arbitrary forms cannot be accurately identified. In this paper, a novel target-aware method based on a non-local low-rank model and saliency filter regularization is proposed, with which the newly proposed detection framework can be tailored as a non-convex optimization problem, therein enabling joint target saliency learning in a lower dimensional discriminative manifold. More specifically, non-local patch construction is applied for the proposed target-aware low-rank model. By combining similar patches, we reconstruct them together to achieve a better generalization of non-local spatial sparsity constraints. Furthermore, to encourage target saliency learning, our proposed saliency filtering regularization term based on entropy is restricted to lie between the background and foreground. The regularization of the saliency filtering locally preserves the contexts from the target and surrounding areas and avoids the deviated approximation of the low-rank matrix. Finally, a unified optimization framework is proposed and solved with the alternative direction multiplier method (ADMM). Experimental evaluations of real infrared images demonstrate that the proposed method is more robust under different complex scenes compared with some state-of-the-art methods.

This paper proposes distributionally robust energy-reserve-storage co-dispatch model and method to facilitate the integration of variable and uncertain renewable energy. The uncertainties of renewable generation forecasting errors are characterized through an ambiguity set, which is a set of probability distributions consistent with observed historical data. The proposed model minimizes the expected operation costs corresponding to the worst case distribution in the ambiguity set. Distributionally robust chance constraints are employed to guarantee reserve and transmission adequacy. The more historical data are available, the smaller the ambiguity set is and the less conservative the solution is. The formulation is finally cast into a mixed integer linear programming whose scale remains unchanged as the number of historical data increases. Inactive constraint identification and convex relaxation techniques are introduced to reduce the computational burden. Numerical results and Monte Carlo simulations on IEEE 118-bus systems demonstrate the effectiveness and efficiency of the proposed method.

Efficient radio resource allocation is essential to provide quality-of-service (QoS) for wireless networks. In this paper, we propose an adaptive multiuser radio resource allocation model for the downlink of OFDMA system, which efficiently exploits the time diversity, frequency diversity as well as multiuser diversity in the time, frequency and user domain, respectively. According to the allocation algorithm's computational complexity, two different-complexity adaptive resource allocation algorithms algorithm A and algorithm B - are proposed which adopt a two-step allocation method to reduce the scheduling complexity and meanwhile improve the scheduling performance. Simulation results show that while the performance of algorithm A and B is slightly different, both of the proposed algorithms yield much higher spectral efficiency and much lower outage probability, which are flexible and efficient for the downlink of OFDMA systems

Automated guided vehicle (AGV) systems traditionally utilize a central controller to assign transportation tasks among vehicles. Because of its rigidity, a centralized architecture may not suitable for modern manufacturing with its rapidly changing markets, demands for products with higher quality, smaller batch sizes, customer specifications, and shorter delivery times. This research applies concepts from holonic manufacturing systems to develop a distributed AGV control system that is flexible and robust in the presence of disturbances. We present the architecture of the holonic manufacturing system, a coordination strategy based on contract nets, and simulation results that indicate an improvement in utilization when compared with traditional centralized control.