Person re-identification (ReID) aims to match pedestrian images across disjoint cameras. Existing supervised ReID methods utilize deep networks and train them with identity-labeled images, which suffer from limited annotations. Recently, clustering-based unsupervised ReID attracts more and more attention. It first clusters unlabeled images and assigns cluster index to the pseudo-identity-labels, then trains a ReID model with the pseudo-identity-labels. However, considering the slight inter-class variations and significant intra-class variations, pseudo-identity-labels learned from clustering algorithms are usually noisy and coarse. To alleviate the problems above, besides clustering pseudo-identity-labels, we propose to learn pseudo-patch-labels, which brings two advantages: (1) Patch naturally alleviates the effect of backgrounds, occlusions, and carryings since they usually occupy small parts in images, thus overcome noisy labels. (2) It is plausible that patches from different pedestrians belong to the same pseudo-identity-label. For example, pedestrians have a high probability of wearing either the same shoes or pants but a low possibility of wearing both. The experiments demonstrate our proposed method achieves the best performance by a large margin on both image- and video-based datasets.

This study proposes an optimized genetic algorithm-based wavelet image fusion technique for printed circuit board (PCB) detection, incorporating an improved Genetic Algorithm (GA) with the Elite Strategy and integrating it with discrete wavelet transform (DWT). The proposed method aims to enhance both the accuracy and efficiency of image fusion, which is crucial for defect detection in PCB inspection. A DWT is utilized to decompose images into multiple frequency components, where the low-frequency band preserves the structural integrity of the image, and the high-frequency band retains essential fine details such as edges and textures, which are critical for identifying defects. An improved genetic algorithm is applied to optimize the fusion process, incorporating the Elite Strategy to retain the best solutions in each evolutionary iteration. This strategy prevents the loss of optimal wavelet decomposition weights, and ensures steady convergence towards the global optimum. By maintaining superior solutions throughout the evolutionary process, the algorithm effectively enhances the fusion quality and computational efficiency. Experimental evaluations validate the effectiveness of the proposed approach, demonstrating superior performance over conventional fusion methods. The enhanced algorithm achieves significant improvements in key performance metrics, including relative standard deviation (RSD), peak signal-to-noise ratio (PSNR), image clarity, and processing efficiency. The team developed a prototype system and conducted simulations in a relatively realistic environment to validate the proposed method’s potential for high-precision PCB detection. The results demonstrate that the approach offers a robust solution for automated defect detection and quality assessment.

Cloth-changing Person Re-Identification (CC-ReID) poses a significant challenge in tracking pedestrians across cameras while accounting for changes in clothing appearance. Despite recent progress in CC-ReID, existing methods predominantly focus on learning the unique biological features of pedestrians, often overlooking constraints that promote the learning of cloth-agnostic features. Addressing this limitation, we propose a Robust Fine-grained Learning Network (RFLNet) to effectively learn robust cloth-agnostic features by leveraging fine-grained semantic constraints. Specifically, we introduce a four-body-part attention module to enhance the learning of detailed pedestrian semantic features. To further strengthen the model’s robustness to clothing variations, we employ a random erasing algorithm, encouraging the network to concentrate on cloth-irrelevant attributes. Additionally, we design a fine-grained semantic loss to guide the model in learning identity-related, detailed semantic features, thereby improving its focus on cloth-agnostic regions. Comprehensive experiments on widely used CC-ReID benchmarks demonstrate the effectiveness of RFLNet. Our method achieves state-of-the-art performance, including a 0.7% increase in mAP on PRCC and a 1.6% improvement in rank-1 accuracy on DeepChange.

Person Re-Identification (ReID) has witnessed tremendous improvements with the help of deep convolutional neural networks (CNN). Nevertheless, because different fields have their characteristics, most existing methods encounter the problem of poor generalization ability to invisible people. To address this problem, based on the relationship between the temporal and camera position, we propose a robust and effective training strategy named temporal smoothing dynamic re-weighting and cross-camera learning (TSDRC). It uses robust and effective algorithms to transfer valuable knowledge of existing labeled source domains to unlabeled target domains. In the target domain training stage, TSDRC iteratively clusters the samples into several centers and dynamically re-weights unlabeled samples from each center with a temporal smoothing score. Then, cross-camera triplet loss is proposed to fine-tune the source domain model. Particularly, to improve the discernibility of CNN models in the source domain, generally shared person attributes and margin-based softmax loss are adapted to train the source model. In terms of the unlabeled target domain, the samples are clustered into several centers iteratively and the unlabeled samples are dynamically re-weighted from each center. Then, cross-camera triplet loss is proposed to fine-tune the source domain model. Comprehensive experiments on the Market-1501 and DukeMTMC-reID datasets demonstrate that the proposed method vastly improves the performance of unsupervised domain adaptability.

Recent advances in deep learning have intensified the need for robust low-light image processing in critical applications like autonomous driving, where single-photon cameras (SPCs) offer high photon sensitivity but produce noisy outputs requiring specialized enhancement. This work addresses this challenge through a unified framework integrating three key components: an SNR-guided adaptive enhancement framework that dynamically processes regions with varying noise levels using spatial-adaptive operations and intelligent feature fusion; a specialized self-attention mechanism optimized for low-light conditions; and a conditional autoregressive generation approach applied to robust depth estimation from enhanced SPC images. Our comprehensive evaluation across multiple datasets demonstrates improved performance over state-of-the-art methods, achieving a PSNR of 24.61 dB on the LOL-v1 dataset and effectively recovering fine-grained textures in depth estimation, particularly in real-world SPC applications, while maintaining computational efficiency. The integrated solution effectively bridges the gap between single-photon sensing and practical computer vision tasks, facilitating more reliable operation in photon-starved environments through its novel combination of adaptive noise processing, attention-based feature enhancement, and generative depth reconstruction.