Satellite image time series (SITS) classification is a major research topic in remote sensing and is relevant for a wide range of applications. Deep learning approaches have been commonly employed for SITS classification and have provided state-of-the-art performance. However, deep learning methods suffer from overfitting when labeled data is scarce. To address this problem, we propose a novel self-supervised pre-training scheme to initialize a Transformer-based network by utilizing large-scale unlabeled data. In detail, the model is asked to predict randomly contaminated observations given an entire time series of a pixel. The main idea of our proposal is to leverage the inherent temporal structure of satellite time series to learn general-purpose spectral-temporal representations related to land cover semantics. Once pre-training is completed, the pre-trained network can be further adapted to various SITS classification tasks by fine-tuning all the model parameters on small-scale task-related labeled data. In this way, the general knowledge and representations about SITS can be transferred to a label-scarce task, thereby improving the generalization performance of the model as well as reducing the risk of overfitting. Comprehensive experiments have been carried out on three benchmark datasets over large study areas. Experimental results demonstrate the effectiveness of the proposed pre-training scheme, leading to substantial improvments in classification accuracy using Transformer, one-dimensional convolutional neural network (CNN-1D), and Bidirectional Long Short-Term Memory (Bi-LSTM) network. The code and the pre-trained model will be available at https://github.com/linlei1214/SITS-BERT upon publication.

Haze superimposes a veil over remote sensing images, which severely limits the extraction of valuable military information. To this end, we present a novel trinity model to restore realistic surface information by integrating the merits of both prior-based and deep learning-based strategies. Concretely, the critical insight of our Trinity-Net is to investigate how to incorporate prior information into CNNs and Swin Transformer for reasonable estimation of haze parameters. Then, haze-free images are obtained by reconstructing the remote sensing image formation model. Although Swin Transformer has shown tremendous potential in the dehazing task, which typically results in ambiguous details. We devise a gradient guidance module that naturally inherits structure priors of gradient maps, guiding the deep model to generate visually pleasing details. In light of the generality of image formation parameters, we successfully promote Trinity-Net to natural image dehazing and underwater image enhancement tasks. Notably, the acquisition of large-scale remote sensing hazy images and natural hazy images in military scenes is not feasible in practice. To bridge this gap, we construct a Remote Sensing Image Dehazing Benchmark (RSID) and a Natural Image Dehazing Benchmark (NID), including 1000 real-world hazy images with corresponding ground truth images, respectively. To our knowledge, this is the first exploration to develop dehazing benchmarks in the military field, alleviating the dilemma of data scarcity. Extensive experiments on three vision tasks illustrate the superiority of our Trinity-Net against multiple state-of-the-art methods. The datasets and code are available at https://github.com/chi-kaichen/Trinity-Net.

The multimodal interplay of the five fundamental senses—Sight, Hearing, Smell, Taste, and Touch—provides humans with superior environmental perception and learning skills. Adapted from the human perceptual system, multimodal machine learning tries to incorporate different forms of input, such as image, audio, and text, and determine their fundamental connections through joint modeling. As one of the future development forms of artificial intelligence, it is necessary to summarize the progress of multimodal machine learning. In this article, we start with the form of a multimodal combination and provide a comprehensive survey of the emerging subject of multimodal machine learning, covering representative research approaches, the most recent advancements, and their applications. Specifically, this article analyzes the relationship between different modalities in detail and sorts out the key issues in multimodal research from the application scenarios. Besides, we thoroughly reviewed state-of-the-art methods and datasets covered in multimodal learning research. We then identify the substantial challenges and potential developing directions in this field. Finally, given the comprehensive nature of this survey, both modality-specific and task-specific researchers can benefit from this survey and advance the field.

Vision-and-language pre-training (VLP) models have experienced a surge in popularity recently. By fine-tuning them on specific datasets, significant performance improvements have been observed in various tasks. However, full fine-tuning of VLP models not only consumes a significant amount of computational resources but also has a significant environmental impact. Moreover, as remote sensing (RS) data is constantly being updated, full fine-tuning may not be practical for real-world applications. To address this issue, in this work, we investigate the parameter-efficient transfer learning (PETL) method to effectively and efficiently transfer visual-language knowledge from the natural domain to the RS domain on the image-text retrieval task. To this end, we make the following contributions. 1) We construct a novel and sophisticated PETL framework for the RS image-text retrieval (RSITR) task, which includes the pretrained CLIP model, a multimodal remote sensing adapter, and a hybrid multi-modal contrastive (HMMC) learning objective; 2) To deal with the problem of high intra-modal similarity in RS data, we design a simple yet effective HMMC loss; 3) We provide comprehensive empirical studies for PETL-based RS image-text retrieval. Our results demonstrate that the proposed method is promising and of great potential for practical applications. 4) We benchmark extensive state-of-the-art PETL methods on the RSITR task. Our proposed model only contains 0.16M training parameters, which can achieve a parameter reduction of 98.9% compared to full fine-tuning, resulting in substantial savings in training costs. Our retrieval performance exceeds traditional methods by 7-13% and achieves comparable or better performance than full fine-tuning. This work can provide new ideas and useful insights for RS vision-language tasks.