The attention mechanism has gained significant popularity in hyperspectral image classification (HSIC) for its ability to adaptively highlight key features. However, it often incurs expensive computational costs due to the iterative operations. Moreover, the high inter-class similarity and indistinct class boundaries in hyperspectral images (HSIs) pose challenges for classification tasks. To tackle these issues, we propose a spectral-spatial synergy guided attention network (SSSGAN) for HSIC. It initially employs a spectral-spatial synergistic mechanism to jointly extract local spectral and spatial features of HSIs, and then applies a guided attention mechanism to effectively reduce computational complexity and further improve its discriminative capabilities. Specifically, a stacked residual spectral feature extractor stacks scale-variable convolution blocks within the channel-connected residual structure. It precisely localizes boundaries and reduces boundary blur by extracting and fusing local multi-level spectral features. A hierarchical dual feature enhancement module employs parallel multi-scale branches combined with dual shift operations to extract multi-scale spatially enhanced features, thereby enriching the diversity of feature representations and improving the discriminability of inter-class features. Finally, a feature-aware guided attention module reduces the computational cost of the attention mechanism by incorporating the guiding token and convolutional operations. By introducing local regularization into the attention map, the convolution enhances the robustness and effectiveness of global and contextual information extraction from HSIs. Experiments conducted on four publicly available benchmark datasets (PU, HU2013, SV, and LK) demonstrate that the proposed SSSGAN method achieves overall accuracies of 98.96%, 95.93%, 98.72%, and 98.31%, respectively, thereby validating its effectiveness in HISC tasks. The source code for this work can be found at https://github.com/szq0816/DSGAN.

Cross-modal hashing retrieval approaches have received extensive attention owing to their storage superiority and retrieval efficiency. To achieve better retrieval performances, hashing methods seek to embed more semantic information of multi-modal data into hash codes. Existing deep cross-modal hashing methods typically learn hash functions from the similarity of paired data to generate hash codes. However, such locally-oriented learning methods often suffer from low efficiency and incomplete acquisition of semantic information. To address these challenges, this paper presents a novel deep hashing approach, called Proxy-based Graph Convolutional Hashing (PGCH), for cross-modal retrieval. Specifically, we use global similarity to construct proxy hash codes for two different modalities. This strategy of these proxy hash codes ensures that they include data points with significant distribution differences. It helps to match data from different modalities to different proxy hash codes, which can capture the global similarity of multi-modal hash codes and improve the efficiency of hash code learning. Subsequently, we employ a multi-modal contrastive loss to learn the global similarity. Furthermore, by constructing a proxy hash matrix from the proxy hash codes, we apply graph convolution to efficiently narrow the gap between different modalities, leading to a substantial improvement in retrieval performance for cross-modal retrieval tasks. The comprehensive experiments on four benchmark multimedia datasets demonstrate that our PGCH approach achieves better retrieval performances than a bundle of state-of-the-art hashing approaches.

In the past few years, many convolutional neural networks (CNNs) have been applied to hyperspectral image (HSI) classification. However, many of them have the following drawbacks: they do not fully consider the abundant band spectral information and insufficiently extract the spatial information of HSI; all bands and neighboring pixels are treated equally, so CNNs may learn features from redundant or useless bands/pixels; and a significant amount of hidden semantic information is lost when a single-scale convolution kernel is used in CNNs. To alleviate these problems, we propose a spatial–spectral split attention residual networks (S $^{3}$ ARN) for HSI classification. In S $^{3}$ ARN, a split attention strategy is used to fuse the features extracted from multireceptive fields, in which both spectral and spatial split attention modules are composed of bottleneck residual blocks. Thanks to the bottleneck structure, the proposed method can effectively prevent overfitting, speeds up the model training, and reduces the network parameters. Moreover, the spectral and spatial attention residual branches aim to generate the attention masks, which can simultaneously emphasize useful bands and neighbor pixels and suppress useless ones. Experimental results on three benchmark datasets demonstrate the effectiveness of the proposed model for HSI classification.

Deep hashing technology has recently become an essential tool for cross-modal retrieval on large-scale datasets. However, their performances heavily depend on accurate annotations to train the hashing model. In real applications, we usually only obtain low-quality label annotations owing to labor and time consumption limitations. To mitigate the performance degradation caused by noisy labels, in this paper, we propose a robust deep hashing method, called deep hashing with ranking learning (DHRL), for cross-modal retrieval. The proposed DHRL method consists of a refined semantic concept alignment module and a ranking-swapping module. In this first module, we adopt two transformers to perform the semantic alignment tasks between different modalities on a set of refined concepts, and then convert them into hash codes to reduce heterogeneous differences between multimodalities. The second module first identifies the noisy labels in the training set and ranks them according to ranking loss. Then it swaps the ranking information of different modal network branches. Unlike existing robust hashing methods for assuming noise distribution, our proposed DHRL method requires no prior assumptions for the input data. Extensive experiments on three benchmark datasets have shown that our proposed DHRL method has stronger advantages over other state-of-the-art hashing methods.