Low-light images suffer from low contrast and unclear details, which not only reduces the available information for humans but limits the application of computer vision algorithms. Among the existing enhancement techniques, Retinex-based and learning-based methods are under the spotlight today. In this paper, we bridge the gap between the two methods. First, we propose a novel “generative” strategy for Retinex decomposition, by which the decomposition is cast as a generative problem. Second, based on the strategy, a unified deep framework is proposed to estimate the latent components and perform low-light image enhancement. Third, our method can weaken the coupling relationship between the two components while performing Retinex decomposition. Finally, the RetinexDIP performs Retinex decomposition without any external images, and the estimated illumination can be easily adjusted and is used to perform enhancement. The proposed method is compared with ten state-of-the-art algorithms on seven public datasets, and the experimental results demonstrate the superiority of our method. Code is available at: https://github.com/zhaozunjin/RetinexDIP .

Recent progress in the development of artificial intelligence technologies, aided by deep learning algorithms, has led to an unprecedented revolution in neuromorphic circuits, bringing us ever closer to brain-like computers. However, the vast majority of advanced algorithms still have to run on conventional computers. Thus, their capacities are limited by what is known as the von-Neumann bottleneck, where the central processing unit for data computation and the main memory for data storage are separated. Emerging forms of non-volatile random access memory, such as ferroelectric random access memory, phase-change random access memory, magnetic random access memory, and resistive random access memory, are widely considered to offer the best prospect of circumventing the von-Neumann bottleneck. This is due to their ability to merge storage and computational operations, such as Boolean logic. This paper reviews the most common kinds of non-volatile random access memory and their physical principles, together with their relative pros and cons when compared with conventional CMOS-based circuits (Complementary Metal Oxide Semiconductor). Their potential application to Boolean logic computation is then considered in terms of their working mechanism, circuit design and performance metrics. The paper concludes by envisaging the prospects offered by non-volatile devices for future brain-inspired and neuromorphic computation.

Background: As a result of the growing body of protein phosphorylation sites data, the number of phosphoprotein databases is constantly increasing, and dozens of tools are available for predicting protein phosphorylation sites to achieve fast automatic results. However, none of the existing tools has been developed to predict protein phosphorylation sites in rice. Results: In this paper, the phosphorylation site predictors, NetPhos 2.0, NetPhosK, Kinasephos, Scansite, Disphos and Predphosphos, were integrated to construct meta-predictors of rice-specific phosphorylation sites using several methods, including unweighted voting, unreduced weighted voting, reduced unweighted voting and weighted voting strategies. PhosphoRice, the meta-predictor produced by using weighted voting strategy with parameters selected by restricted grid search and conditional random search, performed the best at predicting phosphorylation sites in rice. Its Matthew's Correlation Coefficient (MCC) and Accuracy (ACC) reached to 0.474 and 73.8%, respectively. Compared to the best individual element predictor (Disphos_default), PhosphoRice archieved a significant increase in MCC of 0.071 (P < 0.01), and an increase in ACC of 4.6%. Conclusions: PhosphoRice is a powerful tool for predicting unidentified phosphorylation sites in rice. Compared to the existing methods, we found that our tool showed greater robustness in ACC and MCC. PhosphoRice is available to the public at http://bioinformatics.fafu.edu.cn/PhosphoRice.

Dynamic scene deblurring is a significant technique in the field of computer vision. The multiscale strategy has been successfully extended to the deep end-to-end learning-based deblurring task. Its expensive computation gives birth to the multi-patch framework. The success of the multi-patch framework benefits from the local residual information passed across the hierarchy. One problem is that the finest levels rarely contribute to their residuals so that the contributions of the finest levels to their residuals are excluded by coarser levels, which limits the deblurring performance. To this end, we substitute the nested module blocks, whose powerful and complex representation ability is utilized to improve the deblurring performance, for the building blocks of the encoder-decoders in the multi-patch network. Additionally, the attention mechanism is introduced to enable the network to differentiate blur across the whole blurry image from dynamic scene, thereby further improving the ability to handle the motion object blur. Our modification boosts the contributions of the finest levels to their residuals and enables the network to learn different weights for feature information extracted from spatially-varying blur image. Extensive experiments show that the improved network achieves competitive performance on the GoPro dataset according to PSNR and SSIM.

Unmanned aerial vehicle (UAV) remote-sensing images present unique challenges to the object-detection task due to uneven object densities, low resolution, and drastic scale variations. Downsampling is an important component of deep networks that expands the receptive field, reduces computational overhead, and aggregates features. However, object detectors using multi-layer downsampling result in varying degrees of texture feature loss for various scales in remote-sensing images, degrading the performance of multi-scale object detection. To alleviate this problem, we propose a lightweight texture reconstructive downsampling module called TRD. TRD models part of the texture features lost as residual information during downsampling. After modeling, cascading downsampling and upsampling operators provide residual feedback to guide the reconstruction of the desired feature map for each downsampling stage. TRD structurally optimizes the feature-extraction capability of downsampling to provide sufficiently discriminative features for subsequent vision tasks. We replace the downsampling module of the existing backbone network with the TRD module and conduct a large number of experiments and ablation studies on a variety of remote-sensing image datasets. Specifically, the proposed TRD module improves 3.1% AP over the baseline on the NWPU VHR-10 dataset. On the VisDrone-DET dataset, the TRD improves 3.2% AP over the baseline with little additional cost, especially the ${\mathrm{AP}}_{\mathrm{S}}$, ${\mathrm{AP}}_{\mathrm{M}}$, and ${\mathrm{AP}}_{\mathrm{L}}$ by 3.1%, 8.8%, and 13.9%, respectively. The results show that TRD enriches the feature information after downsampling and effectively improves the multi-scale object-detection accuracy of UAV remote-sensing images.