The proposal of Segment Anything Model (SAM) has created a new paradigm for deep learning-based semantic segmentation field, and has shown amazing generalization performance. However, we find it may fail or perform poorly on multimodal remote sensing scenarios, especially the Synthetic Aperture Radar (SAR) images. Besides, SAM does not provide category information of objects. In this paper, we propose a foundation model for multimodal remote sensing image segmentation called RingMo-SAM, which can not only segment anything in optical and SAR remote sensing data, but also identify object categories. First, a large-scale dataset containing millions of segmentation instances is constructed by collecting multiple open-source datasets in this field to train the model. Then, by constructing an instance-type and terrain-type category-decoupling mask decoder, the category-wise segmentation of various objects is achieved. In addition, a prompt encoder embedded with the characteristics of multimodal remote sensing data is designed. It not only supports multi-box prompts to improve the segmentation accuracy of multi-objects in complicated remote sensing scenes, but also supports SAR characteristics prompts to improve the segmentation performance on SAR images. Extensive experimental results on several datasets including iSAID, ISPRS Vaihingen, ISPRS Potsdam, AIR-PolSAR-Seg, etc. have demonstrated the effectiveness of our method.

The balance between high accuracy and high speed has always been a challenging task in semantic image segmentation. Compact segmentation networks are more widely used in the case of limited resources, while their performances are constrained. In this paper, motivated by the residual learning and global aggregation, we propose a simple yet general and effective knowledge distillation framework called double similarity distillation (DSD) to improve the classification accuracy of all existing compact networks by capturing the similarity knowledge in pixel and category dimensions, respectively. Specifically, we propose a pixel-wise similarity distillation (PSD) module that utilizes residual attention maps to capture more detailed spatial dependencies across multiple layers. Compared with exiting methods, the PSD module greatly reduces the amount of calculation and is easy to expand. Furthermore, considering the differences in characteristics between semantic segmentation task and other computer vision tasks, we propose a category-wise similarity distillation (CSD) module, which can help the compact segmentation network strengthen the global category correlation by constructing the correlation matrix. Combining these two modules, DSD framework has no extra parameters and only a minimal increase in FLOPs. Extensive experiments on four challenging datasets, including Cityscapes, CamVid, ADE20K, and Pascal VOC 2012, show that DSD outperforms current state-of-the-art methods, proving its effectiveness and generality. The code and models will be publicly available.

Existing deep learning models usually assume that all data obeys independent identically distribution, which is unreasonable in remote sensing. Due to the differences in camera parameters, spectral ranges, resolutions, and so on, the images acquired by remote sensing sensors may be greatly diverse, causing models to face catastrophic forgetting when they are trained on new data only. Thus, incremental learning is introduced. An ideal incremental learning model should be expanded as the number of tasks increases, so as to have enough ability to adapt to the changes in data. However, existing approaches normally expand heavy modules for each task, making the holistic models cumbersome. In this article, a lightweight incremental learning approach (LIL) is proposed for remote sensing image scene classification. We replace the role of the feature extractor with extracting features of a single task instead of task-sharing features of all tasks to lighten the backbone. In addition, we propose a light feature transfer module (FTM) to realize the alignment of data distributions between different tasks in the feature domain. Furthermore, dual-constraint loss with knowledge distillation and adversarial learning is introduced to promote the mapping and alignment of data distributions at both the feature level and the semantic level. In LIL, only a tiny FTM and a classifier are added to the model when the model learns a new task. Experimental results show that our approach with a small number of parameters outperforms state-of-the-art approaches for incremental learning on both a single dataset and a sequence of multiple datasets.

Recently, multi-modal large language models (MLLMs) have shown excellent reasoning capabilities in various fields. Most of the existing remote sensing MLLMs solve image-level text generation problems (e.g., image captioning), but ignore the core issues of object-level recognition, location and multi-temporal changes in the field of remote sensing. In this paper, we propose RingMoGPT, a multi-modal foundation model that unifies vision, language, and localization. Based on the idea of domain adaption, RingMoGPT can complete training by fine-tuning only a few parameters. To make the model capable of object detection and change captioning, we further propose a Location- and Instruction-aware Q-Former and a change detection module, respectively. To improve the performance of RingMoGPT, we carefully design the pre-training dataset and the instruction-tuning dataset. The pre-training dataset contains over a half million high-quality image and text pairs, which are generated through a low-cost and efficient data generation paradigm. The instruction-tuning dataset contains more than 1.6 million question-answer pairs, including 6 downstream tasks: scene classification, object detection, visual question answering, image captioning, grounded image captioning, and change captioning. Our experiments show that RingMoGPT performs well on 6 tasks, especially its ability to analyze multi-temporal data changes and identify dense objects. We also verified the model under zero-shot setting, and the results show that the proposed RingMoGPT also has good generalization ability in the face of new data.

Ship category classification in high-resolution aerial images has attracted great interest in applications such as maritime security, naval construction, and port management. However, the applications of previous methods were mainly limited by the following issues: (i) The existing ship category classification methods were mainly to classify on accurately-cropped image patches. This is unsatisfactory for the results of the existing methods in practical applications, because the location of the ship in the patch obtained by the object detection varies greatly. (ii) The factors such as target scale variations and class imbalance have a great influence on the performance of ship category classification. Aiming at the issues above, we propose a novel ship detection and category classification framework. The category classification is based on accurate location. The detection network can generate more precise rotated bounding boxes in large-scale aerial images by introducing a novel Sequence Local Context (SLC) module. Besides, three different ship category classification networks are proposed to eliminate the effect of scale variations, and the Spatial Transform Crop (STC) operation is used to get aligned image patches. Whatever the problem of insufficient samples or class imbalance have, the Proposals Simulation Generator (PSG) is considered to handle this properly. Most remarkably, the state-of-the-art performance of our framework is demonstrated by experiments based on the 19-class ship dataset HRSC2016 and our multiclass warship dataset.

For more efficient generalization to unseen domains (classes), most Few-shot Segmentation (FSS) would directly exploit pre-trained encoders and only fine-tune the decoder, especially in the current era of large models. However, such fixed feature encoders tend to be class-agnostic, inevitably activating objects that are irrelevant to the target class. In contrast, humans can effortlessly focus on specific objects in the line of sight. This paper mimics the visual perception pattern of human beings and proposes a novel and powerful prompt-driven scheme, called “Prompt and Transfer” (PAT), which constructs a dynamic class-aware prompting paradigm to tune the encoder for focusing on the interested object (target class) in the current task. Three key points are elaborated to enhance the prompting: 1) Cross-modal linguistic information is introduced to initialize prompts for each task. 2) Semantic Prompt Transfer (SPT) that precisely transfers the class-specific semantics within the images to prompts. 3) Part Mask Generator (PMG) that works in conjunction with SPT to adaptively generate different but complementary part prompts for different individuals. Surprisingly, PAT achieves competitive performance on 4 different tasks including standard FSS, Cross-domain FSS (e.g., CV, medical, and remote sensing domains), Weak-label FSS, and Zero-shot Segmentation, setting new state-of-the-arts on 11 benchmarks.