Underwater images often suffer from color distortion and low contrast resulting in various image types, due to the scattering and absorption of light by water. While it is difficult to obtain high-quality paired training samples with a generalized model. To tackle these challenges, we design a Generalized Underwater image enhancement method via a Physical-knowledge-guided Dynamic Model (short for GUPDM). In particular, to cover complex underwater scenes, this study changes the global atmosphere light and the transmission to simulate various underwater image types through the formation model. We then design an Atmosphere-based Dynamic Structure (ADS) and Transmission-guided Dynamic Structure (TDS) that use dynamic convolutions to adaptively extract prior information from underwater images and generate parameters for Prior-based Multi-scale Structure (PMS). These two modules enable the network to select appropriate parameters for various water types adaptively. Besides, the multi-scale feature extraction module in PMS uses convolution blocks with different kernel sizes and obtains weights for each feature map via channel attention block. The source code will be available at https://github.com/shiningZZ/GUPDM

Recently, siamese-based trackers have achieved significant successes. However, those trackers are restricted by the difficulty of learning consistent feature representation with the object. To address the above challenge, this paper proposes a novel siamese implicit region proposal network with compound attention for visual tracking. First, an implicit region proposal (IRP) module is designed by combining a novel pixel-wise correlation method. This module can aggregate feature information of different regions that are similar to the pre-defined anchor boxes in Region Proposal Network. To this end, the adaptive feature receptive fields then can be obtained by linear fusion of features from different regions. Second, a compound attention module including a channel and non-local attention is raised to assist the IRP module to perform a better perception of the scale and shape of the object. The channel attention is applied for mining the discriminative information of the object to handle the background clutters of the template, while non-local attention is trained to aggregate the contextual information to learn the semantic range of the object. Finally, experimental results demonstrate that the proposed tracker achieves state-of-the-art performance on six challenging benchmark tests, including VOT-2018, VOT-2019, OTB-100, GOT-10k, LaSOT, and TrackingNet. Further, our obtained results demonstrate that the proposed approach can be run at an average speed of 72 FPS in real time.

Visible–infrared person reidentification (VI-ReID) aims to search for pedestrian identities in different spectra. The major challenge is the modality differences between infrared and visible images for the VI-ReID task. Existing approaches try to design networks based on a single-stage training strategy to extract features. However, they often excessively rely on a particular feature, such as modality-specific features or modality-independent features, and overlook the significance of the diverse features obtained by combining them. To address this problem, we propose a diverse-feature collaborative progressive learning network (DCPLNet) for VI-ReID in this article. With the benefit of diverse information, our DCPLNet can effectively learn informative representations for reducing the modality differences. Specifically, we propose a novel three-stage progressive learning strategy (t-PLS) to progressively learn diverse features. For the proposed t-PLS, we design a contour feature enhancement module to mine human contour features and raise a perceptual contour feature loss for supervised feature extraction. Finally, we advance a batch adaptation module to establish feature links between samples. Extensive experiments on SYSU-MM01, RegDB, and LLCM datasets demonstrate that our proposed model performs better than most state-of-the-art methods.

The U-Net-like model has been widely studied in the field of building extraction. However, most of these models are based on locally sensed Convolutional Neural Networks(CNNs) designed with symmetric structure and single feature processing, which cannot accurately identify buildings with different sizes, shapes, and colors in remote sensing images. To overcome these problems, we propose the asymmetric cascade fusion network(ACFN), based on the Vision Transformer(ViT), to design a novel asymmetric architecture to recognize buildings of different sizes and shapes by processing multi-granularity features by different means. First, the asymmetric architecture obtains multi-granularity features with global contextual information by embedding different types of attention in encoder-decoders of different sizes. This architecture can identify densely distributed and occluded buildings by semantic reasoning in remote sensing images with complex information. Second, we design a multi-branch weighted pyramid pooling module, which sets different branch weights to offset the background noise introduced in introducing global contextual information. Our ACFN significantly improves the Beijing buildings, ISPRS-Vaihingen, and LoveDA datasets.

Building extraction plays an important role in high-resolution remote sensing image processing, which can be used as the basis for urban planning and demographic analysis. In recent years, many powerful general semantic segmentation models have emerged, but these models often perform poorly when transferred to remote sensing images because of the characteristics of remote sensing images. To this end, we propose a new deep learning network called Selective Nonlocal ResUNeXt++ (SNLRUX++) for building extraction. First, the cascaded multiscale feature fusion is proposed to transform the high-performance image classification network ResNeXt into the segmentation network ResUNeXt++. Second, selective nonlocal operation is designed to establish long-range dependencies while avoiding introducing excessive noise and computational effort. Finally, multiscale prediction is applied as deep supervision to accelerate training and convergence, and improves prediction performance of objects at different scales. The experimental results on two different remote sensing image datasets show the effectiveness and generalization ability of the proposed method.