Remote sensing semantic segmentation has broad applications in critical fields such as urban planning and environmental monitoring. Semi-supervised semantic segmentation methods tackle the time and cost challenges of annotating remote sensing images by using abundant unlabeled data to optimize the model. Many existing semi-supervised methods generate pseudo-labels by inputting unlabeled data into the network, and then use these labels to progressively improve the model’s segmentation performance. However, the imbalanced class distribution and complex spatial layout of remote sensing images may result in unreliable pseudo-labels generated by the networks. To address this issue, we propose a Prior Information Guided Network (PGNet) that integrates a Prior Feature Guided Module (PFGM) for reliable feature priors and a Prior Edge Extraction Module (PEEM) to provide edge prior information. By leveraging the lightweight Segment Anything Model (SAM), PGNet enhances the ability to extract valuable information from unlabeled data, enabling the generation of more reliable pseudo-label. The PFGM employs Symmetric Cross-Attention to more balancedly integrate the SAM prior features with the semantic features from the encoder. Additionally, the PEEM employs SAM to extract reliable edge priors from unlabeled data, guiding the feature maps during training for more accurate segmentation boundaries. We conducted extensive experiments on the ISPRS Vaihingen, ISPRS Potsdam, and LoveDA datasets. The results demonstrate that our PGNet outperforms existing state-of-the-art semi-supervised methods.

Learning-based stereo matching techniques have made significant progress. However, existing methods inevitably lose geometrical structure information during the feature channel generation process, resulting in edge detail mis-matches. In this paper, the Motif Channel Attention Stereo Matching Network (MoCha-Stereo) is designed to address this problem. We provide the Motif Channel Correlation Volume (MCCV) to determine more accurate edge matching costs. MCCV is achieved by projecting motif channels, which capture common geometric structures in feature channels, onto feature maps and cost volumes. In addition, edge variations in the reconstruction error map also affect details matching, we propose the Reconstruction Error Motif Penalty (REMP) module to further refine the full-resolution disparity estimation. REMP integrates the frequency information of typical channel features from the re-construction error. MoCha-Stereo ranks 1st on the KITTI-2015 and KITTI-2012 Reflective leaderboards. Our structure also shows excellent performance in Multi- View Stereo.

In recent years, the detection of infrared small targets using deep learning methods has garnered substantial attention due to notable advancements. To improve the detection capability of small targets, these methods commonly maintain a pathway that preserves high-resolution (HR) features of sparse and tiny targets. However, it can result in redundant and expensive computations. To tackle this challenge, we propose a sparse infrared-target detector (SpirDet) for the efficient detection of infrared small targets. Specifically, to cope with the computational redundancy issue, we employ a new dual-branch sparse decoder (DBSD) to restore the feature map. First, the fast branch directly predicts a sparse map indicating potential small-target locations. Second, the slow branch conducts fine-grained adjustments at the positions indicated by the sparse map. In addition, we design a lightweight DO-RepEncoder based on reparameterization with the downsampling orthogonality (DO), which can effectively reduce memory consumption and inference latency. Extensive experiments show that the proposed SpirDet significantly outperforms state-of-the-art (SOTA) models while achieving faster inference speed and fewer parameters. For example, on the NUDT-SIRST dataset, SpirDet improves mean intersection over union (MIoU) by 2.09 and has a$3.1\times $frames/s acceleration compared to the previous SOTA model. The code is available athttps://github.com/laCorse/SpirDet-Pytorch.

In the field of binocular stereo matching, remarkable progress has been made by iterative methods like RAFT-Stereo and CREStereo. However, most of these methods lose information during the iterative process, making it difficult to generate more detailed difference maps that take full advantage of high-frequency information. We propose the Decouple module to alleviate the problem of data coupling and allow features containing subtle details to transfer across the iterations which proves to alleviate the problem significantly in the ablations. To further capture high-frequency details, we propose a Normalization Refinement module that unifies the disparities as a proportion of the disparities over the width of the image, which address the problem of module failure in cross-domain scenarios. Further, with the above improvements, the ResNet-like feature extractor that has not been changed for years becomes a bottleneck. Towards this end, we proposed a multi-scale and multi-stage feature extractor that introduces the channel-wise self-attention mechanism which greatly addresses this bottleneck. Our method (DLNR) ranks 1st on the Middlebury leaderboard, significantly outperforming the next best method by 13.04%. Our method also achieves SOTA performance on the KITTI-2015 benchmark for D1-fg. Code and demos are available at: https://github.com/David-Zhao-1997/High-frequency-Stereo-Matching-Network.

Semantic segmentation of remote sensing images is essential for various applications, including vegetation monitoring, disaster management, and urban planning. Previous studies have demonstrated that the self-attention mechanism (SA) is an effective approach for designing segmentation networks that can capture long-range pixel dependencies. SA enables the network to model the global dependencies between the input features, resulting in improved segmentation outcomes. However, the high density of attentional feature maps used in this mechanism causes exponential increases in computational complexity. Additionally, it introduces redundant information that negatively impacts the feature representation. Inspired by traditional threshold segmentation algorithms, we propose a novel threshold attention mechanism (TAM). This mechanism significantly reduces computational effort while also better modeling the correlation between different regions of the feature map. Based on TAM, we present a threshold attention network (TANet) for semantic segmentation. TANet consists of an attentional feature enhancement module (AFEM) for global feature enhancement of shallow features and a threshold attention pyramid pooling module (TAPP) for acquiring feature information at different scales for deep features. We have conducted extensive experiments on the ISPRS Vaihingen and Potsdam datasets. The results demonstrate the validity and superiority of our proposed TANet compared to the most state-of-the-art models.

Rain streaks can seriously degrade the visual quality of an image and are detrimental to subsequent algorithms such as object detection and semantic segmentation. Therefore, removing rain streaks is a very important task. The deraining task has two main limitations: the first is to encode information about rain streaks in different densities and directions, the second is to keep the background details of the image while removing the rain streak. To address these limitations, we propose an effective algorithm, called multi-stage and multi-scale joint channel coordinate attention fusion network (MMAFN). We mainly propose a two-stage network structure, both of which use an encoder-decoder network to extract features. The first-stage network extracts coarse features and the second-stage network integrates the features of the former to further refine features. We design the joint channel coordinate attention block to encode features of rain streaks in different directions and densities. In addition, to better fuse features of different scales and enhance the generalization performance of the network, the inception attention branch block and the multi-level feature fusion block are designed. Extensive experiments substantiate the superiority of the proposed network and prove that our method outperforms the recent state-of-the-art method. The average PSNR of the five test sets is improved by 0.2dB. On the Test100 test set, the PSNR is increased by 0.93dB at most.