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.

RGB-D salient object detection (SOD) aims at locating the most eye-catching object in visual input by fusing complementary information of RGB modality and depth modality. Most of the existing RGB-D SOD methods integrate multi-modal features to generate the saliency map indiscriminately, ignoring the ambiguity between different modalities. To better use multi-modal complementary information and alleviate the negative impact of ambiguity among different modalities, this paper proposes a novel Alternate Steered Attention and Trapezoidal Pyramid Fusion Network (A2TPNet) for RGB-D SOD composed of Cross-modal Alternate Fusion Module (CAFM) and Trapezoidal Pyramid Fusion Module (TPFM). CAFM is focused on fusing cross-modal features, taking full consideration of the ambiguity between cross-modal data by an Alternate Steered Attention (ASA), and it reduces the interference of redundant information and non-salient features in the interactive process through a collaboration mechanism containing channel attention and spatial attention. TPFM endows the RGB-D SOD model with more powerful feature expression capabilities by combining multi-scale features to enhance the expressive ability of contextual semantics of the model. Extensive experimental results on five publicly available datasets demonstrate that the proposed model consistently outperforms 17 state-of-the-art methods.

Feature Pyramid Network (FPN) has been widely applied in the task of salient object detection (SOD), which has achieved great performance. However, most existing FPN-based SOD methods still have some limitations, such as insufficient guidance due to gradual dilution of semantic information, excessive computation leading to slow inference speed, and low efficiency of training models. In this paper, we design a novel Gradual Shrinkage and Cyclic Interaction Network (GSCINet) for efficient and accurate SOD, consisting of a Multi-Scale Contextual Attention Module (MSCAM) and an Adjacent Feature Shrinkage and Interaction Module (AFSIM). Specifically, the MSCAM aims at efficiently capturing multi-scale and multi-receptive-field contextual attention information through a series of well-designed convolutions and attention weight matrices of different scales to enhance the performance of initial input features. Subsequently, in AFSIM, we propose a gradual shrinkage structure and introduce a circular interaction mechanism to optimize the compressed features with less calculation cost, thereby enabling fast and accurate inference of salient objects. Extensive experimental results demonstrate the high efficiency and superiority of GSCINet against 17 state-of-the-art (SOTA) saliency detection methods under multiple evaluation metrics.