With the rapid development of sensor networks, machine vision faces the problem of storing and computing massive data. The human visual system has a very efficient information sense and computation ability, which has enlightening significance for solving the above problems in machine vision. This review aims to comprehensively summarize the latest advances in bio-inspired image sensors that can be used to improve machine-vision processing efficiency. After briefly introducing the research background, the relevant mechanisms of visual information processing in human visual systems are briefly discussed, including layer-by-layer processing, sparse coding, and neural adaptation. Subsequently, the cases and performance of image sensors corresponding to various bio-inspired mechanisms are introduced. Finally, the challenges and perspectives of implementing bio-inspired image sensors for efficient machine vision are discussed.

Artificial synapses utilizing spike signals are essential elements of new generation brain-inspired computers. In this paper, we realize light-stimulated adaptive artificial synapse based on nanocrystalline zinc oxide film. The artificial synapse photoconductivity shows spike-type signal response, long and short-term memory (LTM and STM), STM-to-LTM transition and paired-pulse facilitation. It is also retaining the memory of previous exposures and demonstrates spike-frequency adaptation properties. A way to implement neurons with synaptic depression, tonic excitation, and delayed accelerating types of response under the influence of repetitive light signals is discussed. The developed artificial synapse is able to become a key element of neuromorphic chips and neuromorphic sensorics systems.

针对高光谱遥感图像分类时有标注的源域训练数据与无标注目标域数据分布不一致的问题，提出基于部分最优传输的无监督领域自适应方法，实现对处于不同数据分布的高光谱遥感地物像素级分类。利用深度卷积神经网络将样本映射到潜在高维空间，根据部分最优传输理论建立样本传输方案，最小化域间分布差异，构建适配模型。采用类感知采样技术和质量分数因子自适应调整策略，促进域间类别对齐，建立全局最优传输。在两组公开高光谱遥感图像数据集上进行实验，从总体分类精度OA（%）、类别平均分类精度AA（%）、分类一致性检验Kappa（×100）等3个评价指标对像素分类结果量化比较。实验结果显示，在两组迁移任务上，相较于仅使用源域数据的基线模型，总体分类准确率分别提升2.21%和2.75%，相较于原始最优传输策略提升1.71%和2.01%，表明模型能够有效提升高光谱遥感影像中像素级地物的分类精度。

从人眼视觉系统的角度出发，结合凝视点位置的变化和人眼中心凹的采样特性，提出一种基于人眼凝视点自适应的中心凹图像传输算法，降低数据传输带宽。实验结果表明，当视距为2且凝视点位置位于图像中心时，综合压缩比为12.257，数据传输时钟频率为12.532MHz，传输的数据总量为原先数据总量的8.158%，有效地降低了数据传输总量，极大地缓解了数据传输带宽的压力，使得同一时钟频率下能够实现更高分辨率和刷新率的视频图像。

针对跨场景高光谱遥感图像分类中源域和目标域的频谱偏移问题，提出一种结合空谱域适应与极度梯度提升树（eXtreme Gradient Boosting， XGBoost）的跨场景高光谱图像分类模型。将深度超参数卷积模型（Depthwise Over-parameterized Convolution Model，DOCM）和大核注意力（Large Kernel Attention，LKA）结合，构成空谱注意力模型，提取源域空谱特征。利用相同的空谱注意力模型对目标域进行特征提取，并与鉴别器完成对抗域适应，减少源域与目标域之间的频谱偏移；通过目标域中少量有标签数据对目标域特征提取器进行有监督域适应，使目标域特征提取器进一步学习目标域的真实分布，并对源域和目标域的特征进行映射，形成相似的空间分布，完成聚类域适应。最后，使用集成分类器XGBoost进行高光谱图像分类，进一步提高模型的训练速度与置信度。在Pavia和Indiana高光谱数据集上的实验结果表明，本文算法的总体分类精度分别达到了91.62%和 65.98%。相比较于其他跨场景高光谱图像分类模型，本文所提模型具有更高的地物分类精度。

To improve the performance of few-shot classification, we present a general and flexible method named Multi-Scale Attention and Domain Adaptation Network (MADA). Firstly, to tackle the problem of limited samples, a masked autoencoder is used to image augmentation. Moreover, it can be inserted as a plug-and-play module into a few-shot classification. Secondly, the multi-scale attention module can adapt feature vectors extracted by embedding function to the current classification task. Multi-scale attention machine strengthens the discriminative image region by focusing on relating samples in both base class and novel class, which makes prototypes more accurate. In addition, the embedding function pays attention to the task-specific feature. Thirdly, the domain adaptation module is used to address the domain shift caused by the difference in data distributions of the two domains. The domain adaptation module consists of the metric module and the margin loss function. The margin loss pushes different prototypes away from each other in the feature space. Sufficient margin space in feature space improves the generalization performance of the method. The experimental results show the classification accuracy of the proposed method is 67.45% for 5-way 1-shot and 82.77% for 5-way 5-shot on the miniImageNet dataset. The classification accuracy is 70.57% for 5-way 1-shot and 85.10% for 5-way 5-shot on the tieredImageNet dataset. The classification accuracy of our method is better than most previous methods. After dimension reduction and visualization of features by using t-SNE, it can be concluded that domain drift is alleviated, and prototypes are more accurate. The multi-scale attention module enhanced feature representations are more discriminative for the target classification task. In addition, the domain adaptation module improves the generalization ability of the model.

Multiphoton microscopy is the enabling tool for biomedical research, but the aberrations of biological tissues have limited its imaging performance. Adaptive optics (AO) has been developed to partially overcome aberration to restore imaging performance. For indirect AO, algorithm is the key to its successful implementation. Here, based on the fact that indirect AO has an analogy to the black-box optimization problem, we successfully apply the covariance matrix adaptation evolution strategy (CMA-ES) used in the latter, to indirect AO in multiphoton microscopy (MPM). Compared with the traditional genetic algorithm (GA), our algorithm has a greater improvement in convergence speed and convergence accuracy, which provides the possibility of realizing real-time dynamic aberration correction for deep in vivo biological tissues.