Pre-trained vision-language models (PVLMs) and pseudo-labeling have proven effective in open-vocabulary object detection (OVD). However, when PVLMs trained on image-text data are adapted for OVD tasks, they often encounter challenges with region-text misalignment, resulting in low-quality pseudo-labels (PLs) and suboptimal detection performance. In this paper, we introduce a Confusion-aware Prototypical Contrastive Learning (CPCL) method to address these issues. Our key observation is that while most PLs generated by PVLMs are correctly classified, they still suffer from low inter-class separability and contain a small amount of noise. Therefore, we first cluster pseudo-labels within each category to obtain category prototypes, reducing the impact of noise during training. These category prototypes are then used in confusion-aware prototypical contrastive learning to effectively decrease inference confusion probabilities, leading to improved detection accuracy for novel categories. Extensive experiments on the COCO and LVIS-v1 benchmarks demonstrate that our method significantly enhances inter-class separability and achieves competitive, and even state-of-the-art detection performance.

Large-aperturecoprime arrays(CAs) are expected to achieve higher sensing resolution than conventional dense arrays (DAs), yet with lower hardware and energy cost. However, existing CA far-field localization methods cannot be directly applied to near-field scenarios due to channel model mismatch. To address this issue, in this paper, we propose an efficient near-field localization method for CAs. Specifically, we first construct an effective covariance matrix, which allows to decouple the target angle-and-range estimation. Then, a customized two-phase multiple signal classification (MUSIC) method for CAs is proposed, which first detects all possible angles of targets by using an angular-domain MUSIC method, followed by a second phase to resolve the true angles of targets and their ranges by devising a range-domain MUSIC method. We show that the proposed method can achieve near-optimal multi-target localization performance as conventional two-dimensional (2D)-MUSIC method with much lower computational complexity. Additionally, we characterize the Cramér-Rao bounds for symmetric CAs and provide interesting insights. Finally, numerical results demonstrate that our proposed method is able to localize more targets than the existing subarray-based method as well as achieve lower root mean square error than DAs.

Data replay and knowledge distillation are the most effective techniques for mitigating catastrophic forgetting in incremental object detection (IOD). Despite the recent achievements of IOD, there has been limited exploration regarding active learning of previously learned data, model plasticity, and industrial-grade incremental detectors. In this paper, we propose a multi-teacher distillation (MTD) method for the incremental learning of industrial detectors. Our proposed method leverages structural similarity loss to identify the most representative data, enhancing the efficiency of the incremental learning process. Additionally, we introduce an expert model that trained on the new data to alleviate the suppression from the teacher model on new categories. One of the key advantages of our method is its ability to significantly improve the performance on newly learned categories, especially when the amount of new data is limited. Through extensive experiments conducted on the PASCAL VOC and MS COCO benchmarks, we demonstrate that our proposed method achieves state-of-the-art performance, while ensuring both model stability and plasticity.

Large-aperture coprime arrays (CAs) are expected to achieve higher sensing resolution than conventional dense arrays (DAs), yet with lower hardware and energy cost. However, existing CA far-field localization methods cannot be directly applied to near-field scenarios due to channel model mismatch. To address this issue, in this paper, we propose an efficient near-field localization method for CAs. Specifically, we first construct an effective covariance matrix, which allows to decouple the target angle-and-range estimation. Then, a customized two-phase multiple signal classification (MUSIC) algorithm for CAs is proposed, which first detects all possible targets' angles by using an angular-domain MUSIC algorithm, followed by the second phase to resolve the true targets' angles and ranges by devising a range-domain MUSIC algorithm. Finally, we show that the proposed method is able to locate more targets than the subarray-based method as well as achieve lower root mean square error (RMSE) than DAs.

Deep learning has been proved to be one of the most effective method in feature encoding for different intelligent applications such as video-based human action recognition. However, its nonconvex optimization mechanism leads large memory consumption, which hinders its deployment on the smart embedded systems with limited computational resources. To overcome this challenge, we propose a novel deep model compression technique for smart embedded systems, which realizes both the memory size reduction and inference complexity decrease within a small drop of accuracy. First, we propose an improved naive Bayes inference-based channel parameter pruning to obtain a sparse model with higher accuracy. Then, to improve the inference efficiency, the improved Tucker decomposition method is proposed, where an improved genetic algorithm is used to optimize the Tucker ranks. Finally, to elevate the effectiveness of our proposed method, extensive experiments are conducted. The experimental results show that our method can achieve the state-of-the-art performance compared with existing methods in terms of accuracy, parameter compression, and floating-point operations reduction.