Global-optimal semi-supervised learning for single-pixel image-free sensing.

Single-pixel sensing offers low-cost detection and reliable perception, and the image-free sensing technique enhances its efficiency by extracting high-level features directly from compressed measurements. However, the conventional methods have great limitations in practical applications, due to their high dependence on large labelled data sources and incapability to do complex tasks. In this Letter, we report an image-free semi-supervised sensing framework based on GAN and achieve an end-to-end global optimization on the part-labelled datasets. Simulation on the MNIST realizes 94.91% sensing accuracy at 0.1 sampling ratio, with merely 0.3% of the dataset holding its classification label. When comparing to the conventional single-pixel sensing methods, the reported technique not only contributes to a high-robust result in both conventional (98.49% vs. 97.36%) and resource-constrained situations (94.91% vs. 83.83%) but also offers a more practical and powerful detection fashion for single-pixel sensing, with much less human effort and computation resources.

Self-supervised learning for single-pixel imaging via dual-domain constraints.

Deep-learning-augmented single-pixel imaging (SPI) provides an efficient solution for target compressive sensing. However, the conventional supervised strategy suffers from laborious training and poor generalization. In this Letter, we report a self-supervised learning method for SPI reconstruction. It introduces dual-domain constraints to integrate the SPI physics model into a neural network. Specifically, in addition to the traditional measurement constraint, an extra transformation constraint is employed to ensure target plane consistency. The transformation constraint uses the invariance of reversible transformation to impose an implicit prior, which avoids the non-uniqueness of measurement constraint. A series of experiments validate that the reported technique realizes self-supervised reconstruction in various complex scenes without any paired data, ground truth, or pre-trained prior. It can tackle the underdetermined degradation and noise, with ∼3.7-dB improvement on the PSNR index compared with the existing method.

Sparse single-pixel imaging via optimization in nonuniform sampling sparsity.

Reducing the imaging time while maintaining reconstruction accuracy remains challenging for single-pixel imaging. One cost-effective approach is nonuniform sparse sampling. The existing methods lack intuitive and intrinsic analysis in sparsity. The lack impedes our comprehension of the form's adjustable range and may potentially limit our ability to identify an optimal distribution form within a confined adjustable range, consequently impacting the method's overall performance. In this Letter, we report a sparse sampling method with a wide adjustable range and define a sparsity metric to guide the selection of sampling forms. Through a comprehensive analysis and discussion, we select a sampling form that yields satisfying accuracy. These works will make up for the existing methods' lack of sparsity analysis and help adjust methods to accommodate different situations and needs.

Weighted sampling-adaptive single-pixel sensing.

The novel single-pixel sensing technique that uses an end-to-end neural network for joint optimization achieves high-level semantic sensing, which is effective but computation-consuming for varied sampling rates. In this Letter, we report a weighted optimization technique for sampling-adaptive single-pixel sensing, which only needs to train the network once for any dynamic sampling rate. Specifically, we innovatively introduce a weighting scheme in the encoding process to characterize different patterns' modulation efficiencies, in which the modulation patterns and their corresponding weights are updated iteratively. The optimal pattern series with the highest weights is employed for light modulation in the experimental implementation, thus achieving highly efficient sensing. Experiments validated that once the network is trained with a sampling rate of 1, the single-target classification accuracy reaches up to 95.00% at a sampling rate of 0.03 on the MNIST dataset and 90.20% at a sampling rate of 0.07 on the CCPD dataset for multi-target sensing.

Ultrahigh-security single-pixel semantic encryption.

Single-pixel encryption is a recently developed encryption technique enabling the ciphertext amount to be decreased. It adopts modulation patterns as secret keys and uses reconstruction algorithms for image recovery in the decryption process, which are time-consuming and can easily be illegally deciphered if the patterns are exposed. We report an image-free single-pixel semantic encryption technique that significantly enhances security. The technique extracts semantic information directly from the ciphertext without image reconstruction, which significantly reduces computing resources for end-to-end real-time decoding. Moreover, we introduce a stochastic mismatch between keys and ciphertext, with random measurement shift and dropout, which effectively enhances the difficulty of illegal deciphering. Experiments on the MNIST dataset validate that 78 coupling measurements (0.1 sampling rate) with stochastic shift and random dropout achieved 97.43% semantic decryption accuracy. In the worst situation, when all the keys are illegally obtained by unauthorized attackers, only 10.80% accuracy can be achieved (39.47% in an ergodic manner).

The Mechanisms of Chief Executive Officer Characteristics and Corporate Social Responsibility Reporting: Evidence From Chinese-Listed Firms.

Corporate social responsibility (CSR) strategy hinges largely on the CEO characteristics in the context of an emerging market. Based on a sample of 16,144 firm-year observations obtained from 1,370 unique Chinese-listed firms, which whether voluntarily issue CSR reports over the period 2008-2019, this paper empirically examined the impact of CEO characteristics on the likelihood of issuing CSR reports. We find that CEO age, MBA education, international experience and political ideology consciousness are positively associated with the possibility of issuing CSR reports, while a newly appointed CEO will decrease the likelihood of issuing CSR reports. Moreover, we consider a contingent factor, namely CEO power over the board, can significantly enhance the relationship between CEO age, political ideology consciousness, and the likelihood of issuing CSR reports. Furthermore, there's no significant evidence indicating that CEO power can moderate the relationship between MBA education, international experience, and the likelihood of issuing CSR reports. Nonetheless, CEO power moderates the negative relationship between a newly appointed CEO and CSR reporting initiatives. This study attaches understandings to the extant literature that how top management characteristics can shape firm CSR strategies.