Researchers have recently proposed arbitrary style transfer methods based on various model frameworks. Although all of them have achieved good results, they still face the problems of insufficient stylization, artifacts and inadequate retention of content structure. In order to solve these problems, we propose a flow style-aware network (FSANet) for arbitrary style transfer, which combines a VGG network and a flow network. FSANet consists of a flow style transfer module (FSTM), a dynamic regulation attention module (DRAM), and a style feature interaction module (SFIM). The flow style transfer module uses the reversible residue block features of the flow network to create a sample feature containing the target content and style. To adapt the FSTM to VGG networks, we design the dynamic regulation attention module and exploit the sample features both at the channel and pixel levels. The style feature interaction module computes a style tensor that optimizes the fused features. Extensive qualitative and quantitative experiments demonstrate that our proposed FSANet can effectively avoid artifacts and enhance the preservation of content details while migrating style features.

Abstract Monocular depth estimation (MDE) has made great progress with the development of convolutional neural networks (CNNs). However, these approaches suffer from essential shortsightedness due to the utilization of insufficient feature-based reasoning. To this end, we propose an effective parallel CNNs and Transformer model for MDE via dual attention (PCTDepth). Specifically, we use two stream backbones to extract features, where ResNet and Swin Transformer are utilized to obtain local detail features and global long-range dependencies, respectively. Furthermore, a hierarchical fusion module (HFM) is designed to actively exchange beneficial information for the complementation of each representation during the intermediate fusion. Finally, a dual attention module is incorporated for each fused feature in the decoder stage to improve the accuracy of the model by enhancing inter-channel correlations and focusing on relevant spatial locations. Comprehensive experiments on the KITTI dataset demonstrate that the proposed model consistently outperforms the other state-of-the-art methods.

Multi-modality complementary information brings new impetus and innovation to saliency object detection (SOD). However, most existing RGB-D SOD methods either indiscriminately handle RGB features and depth features or only take depth features as additional information of RGB subnet-work, ignoring the different roles of two modalities for SOD tasks. To tackle this issue, we propose a novel multi-modality diversity fusion network with SwinTransformer (M2DFNet) for RGB-D SOD from the perspective of the different status of multi-modality, which adequately explores the roles of RGB and depth modalities. To this end, a triple-diversity supervision mechanism (TDSM) and a diversity fusion module (DFM) are designed to parse the function of different modalities. Besides, we designed a dense decoder (DSD) to integrate multi-scale features and transfer gain information from top to bottom, which can improve the performance of SOD. Extensive experiments on five benchmark datasets demonstrate that the proposed M2DFNet outperforms 17 other state-of-the-art (SOTA) RGB-D SOD methods.

Multi-scale context is crucial for the accurate salient object detection (SOD) in the real-world scenes. Although current contextual information-based SOD methods have achieved great progress, they may fail to generate precise saliency maps due to their seldom considering the correlation of different scale context during the extraction process. To address these issues, we propose an Efficient Multi-Scale Context Exploration Network (EMCENet) for SOD. Specifically, a progressive multi-scale context extraction (PMCE) module is designed to progressively capture strongly correlated multi-scale context by using multi-receptive-field convolution operations. Afterwards, a hierarchical feature hybrid interaction (HFHI) module is introduced to generate powerful feature representations by adaptively aggregating multi-level features in a hybrid interaction strategy. Extensive experimental results on six public datasets demonstrate that the proposed EMCENet method without any post-processing performs favorably against 13 state-of-the-art SOD methods.

To balance the performance of chaos and the algorithm’s efficiency, a Henon-Modulated-Iterative (HMI) map is constructed in this paper. And the chaotic characteristics of the HMI map are analyzed from three aspects: bifurcation map, Lyapunov exponent and balance degree. On this basis, an image encryption algorithm based on a convolutional neural network (CNN) and four square matrix encoding is proposed. Then, the random sequence generation module is designed using CNN, and the generated random sequence is used to construct the scrambling coordinate matrix and modify the position of the pixel values. Finally, the scrambled image is diffused by four square matrix encoding so that the pixel values are evenly distributed, while non-sequential diffusion using hexadecimal addition and subtraction rules improves the security of the encryption algorithm. Experimental results show that the encryption algorithm proposed in this paper has a good encryption effect and can resist various attacks.

RGB-D Salient object detection (SOD) is a pixel-level dense prediction task, which can highlight the prominent object in the scene. Recently, Convolution Neural Network (CNN) is widely applied in SOD to generate multi-level features, which are complementary to each other. However, most methods ignore the unique characteristics of multi-level features (high-level and low-level features). Given the effective employment of multi-level features, we propose a novel multi-modality hierarchy-aware decision network (HDNet) by embedding a Swin Transformer as an encoder. The proposed HDNet contains three primary designs: (1) a Swin Transformer encoder is employed instead of a CNN to learn long-range dependencies; (2) a hierarchy-aware feature decision mechanism (HFDM) is proposed to exploit effective local detail cues of low-level features and global semantic information of high-level features, which consists of two sub-modules, namely low-hierarchy edge module (LEM) and high-hierarchy region module (HRM); (3) a decision-based fusion module (DFM) is designed to fuse RGB and depth features under the attribute of multi-level features generated from HFDM. Experiments on five public benchmarks verify that our framework has better performance than the other 18 state-of-the-art algorithms.