Change detection is an essential and widely utilized task in remote sensing that aims to detect and analyze changes occurring in the same geographical area over time, which has broad applications in urban development, agricultural surveys, and land cover monitoring. Detecting changes in remote sensing images is a complex challenge due to various factors, including variations in image quality, noise, registration errors, illumination changes, complex landscapes, and spatial heterogeneity. In recent years, deep learning has emerged as a powerful tool for feature extraction and addressing these challenges. Its versatility has resulted in its widespread adoption for numerous image-processing tasks. This paper presents a comprehensive survey of significant advancements in change detection for remote sensing images over the past decade. We first introduce some preliminary knowledge for the change detection task, such as problem definition, datasets, evaluation metrics, and transformer basics, as well as provide a detailed taxonomy of existing algorithms from three different perspectives: algorithm granularity, supervision modes, and frameworks in the Methodology section. This survey enables readers to gain systematic knowledge of change detection tasks from various angles. We then summarize the state-of-the-art performance on several dominant change detection datasets, providing insights into the strengths and limitations of existing algorithms. Based on our survey, some future research directions for change detection in remote sensing are well identified. This survey paper sheds some light the topic for the community and will inspire further research efforts in the change detection task.

Semantic segmentation is a fundamental task in remote sensing image processing. The large appearance variations of ground objects make this task quite challenging. Recently, deep convolutional neural networks (DCNNs) have shown outstanding performance in this task. A common strategy of these methods (e.g., SegNet) for performance improvement is to combine the feature maps learned at different DCNN layers. However, such a combination is usually implemented via feature map summation or concatenation, indicating that the features are considered indiscriminately. In fact, features at different positions contribute differently to the final performance. It is advantageous to automatically select adaptive features when merging different-layer feature maps. To achieve this goal, we propose a gated convolutional neural network to fulfill this task. Specifically, we explore the relationship between the information entropy of the feature maps and the label-error map, and then a gate mechanism is embedded to integrate the feature maps more effectively. The gate is implemented by the entropy maps, which are generated to assign adaptive weights to different feature maps as their relative importance. Generally, the entropy maps, i.e., the gates, guide the network to focus on the highly-uncertain pixels, where detailed information from lower layers is required to improve the separability of these pixels. The selected features are finally combined to feed into the classifier layer, which predicts the semantic label of each pixel. The proposed method achieves competitive segmentation accuracy on the public ISPRS 2D Semantic Labeling benchmark, which is challenging for segmentation by only using the RGB images.

Cross-modal retrieval emphasizes understanding inter-modality semantic correlations, which is often achieved by designing a similarity function. Generally, one of the most important things considered by the similarity function is how to make the cross-modal similarity computable. In this paper, a deep and bidirectional representation learning model is proposed to address the issue of image-text cross-modal retrieval. Owing to the solid progress of deep learning in computer vision and natural language processing, it is reliable to extract semantic representations from both raw image and text data by using deep neural networks. Therefore, in the proposed model, two convolution-based networks are adopted to accomplish representation learning for images and texts. By passing the networks, images and texts are mapped to a common space, in which the cross-modal similarity is measured by cosine distance. Subsequently, a bidirectional network architecture is designed to capture the property of the cross-modal retrieval-the bidirectional search. Such architecture is characterized by simultaneously involving the matched and unmatched image-text pairs for training. Accordingly, a learning framework with maximum likelihood criterion is finally developed. The network parameters are optimized via backpropagation and stochastic gradient descent. A great deal of experiments are conducted to sufficiently evaluate the proposed method on three publicly released datasets: IAPRTC-12, Flickr30k, and Flickr8k. The overall results definitely show that the proposed architecture is effective and the learned representations have good semantics to achieve superior cross-modal retrieval performance.

Encoder-decoder models have been widely used in image captioning, and most of them are designed via single Long Short Term Memory (LSTM). The capacity of single-layer network, whose encoder and decoder are integrated together, is limited for such a complex task of image captioning. Moreover, how to effectively increase the “vertical depth” of encoder-decoder remains to be solved. To deal with these problems, a novel Deep Hierarchical Encoder-Decoder Network (DHEDN) is proposed for image captioning, where a deep hierarchical structure is explored to separate the functions of encoder and decoder. This model is capable of efficiently exerting the representation capacity of deep networks to fuse high level semantics of vision and language in generating captions. Specifically, visual representations in top levels of abstraction are simultaneously considered, and each of these levels is associated to one LSTM. The bottom-most LSTM is applied as the encoder of textual inputs. The application of the middle layer in encoder-decoder is to enhance the decoding ability of top-most LSTM. Furthermore, depending on the introduction of semantic enhancement module of image feature and distribution combine module of text feature, variants of architectures of our model are constructed to explore the impacts and mutual interactions among the visual representation, textual representations and the output of the middle LSTM layer. Particularly, the framework is training under a reinforcement learning method to address the exposure bias problem between the training and the testing by the policy gradient optimization. Qualitative analyses indicate the process that our model “translates” image to sentence and further visualization presents the evolution of the hidden states from different hierarchical LSTMs over time. Extensive experiments demonstrate that our model outperforms current state-of-the-art models on three benchmark datasets: Flickr8K, Flickr30K and MSCOCO. On both image captioning and retrieval tasks, our method achieves the best results. On MSCOCO captioning Leaderboard, our method also achieves superior performance.

Pixel-level classification for very high resolution (VHR) images is a crucial but challenging task in remote sensing. However, since the diverse ways of satellite image acquisition and the distinct structures of various regions, the distributions of the same semantic classes among different data sets are dissimilar. Therefore, the classification model trained on one data set (source domain) may collapse, when it is directly applied to another one (target domain). To solve this problem, many adversarial-based domain adaptation methods have been proposed. However, these methods only consider the source and the target domains independently in the adversarial training, where only the target domain is explicitly contributed to narrow the gap between the distributions of both domains. Unlike previous methods, we propose a triplet adversarial domain adaptation (TriADA) method that jointly considers both domains to learn a domain-invariant classifier by a novel domain similarity discriminator. Specifically, the discriminator takes a triplet of segmentation maps as input, where two segmentation maps from the same domain are to be distinguished from the two maps from the different domains during the adversarial learning. Consequently, it explicitly considers both domains' information to narrow the distribution gap across domains. To enhance the discriminability of the classifier on the target domain, a class-aware self-training strategy, which depends on the output of the discriminator, is proposed to assign pseudo-labels with high adapted confidence on target data to retrain the classifier. Extensive experiments on several VHR pixel-level classification benchmarks demonstrate the effectiveness of our method as well as its superiority to the-state of the art.

Sea–land segmentation and ship detection are two prevalent research domains for optical remote sensing harbor images and can find many applications in harbor supervision and management. As the spatial resolution of imaging technology improves, traditional methods struggle to perform well due to the complicated appearance and background distributions. In this paper, we unify the above two tasks into a single framework and apply the deep convolutional neural networks to predict pixelwise label for an input. Specifically, an edge aware convolutional network is proposed to parse a remote sensing harbor image into three typical objects, e.g., sea, land, and ship. Two innovations are made on top of the deep structure. First, we design a multitask model by simultaneously training the segmentation and edge detection networks. Hierarchical semantic features from the segmentation network are extracted to learn the edge network. Second, the outputs of edge pipeline are further employed to refine entire model by adding an edge aware regularization, which helps our method to yield very desirable results that are spatially consistent and well boundary located. It also benefits the segmentation of docked ships that are quite challenging for many previous methods. Experimental results on two datasets collected from Google Earth have demonstrated the effectiveness of our approach both in quantitative and qualitative performance compared with state-of-the-art methods.