Few-shot object detection has attracted extensive attention due to the abomination of time-consuming or even impractical large-scale data labeling. Current studies attempted to employ prototype-matching approaches for object detection, constructing class prototypes from textual or visual features. However, single visual prototypes exhibit limited generalization in few-shot scenarios, while single textual prototypes lack the spatial details of remote sensing targets. Therefore, to achieve the best of both worlds, we propose a prototype aggregating module to integrate textual and visual prototypes, leveraging both semantics from textual prototypes and spatial details from visual prototypes. In addition, the transferability of multi-modal few-shot detectors from natural scenarios to remote sensing scenarios remains unexplored, and previous training strategies for FSOD do not adequately consider the characteristics of text encoders. To address the issue, we have conducted extensive ablation studies on different feature extractors of the detector and propose an efficient two-stage training strategy, which takes the characteristics of the text feature extractor into account. Experiments on two common few-shot detection benchmarks demonstrate the effectiveness of our proposed method. In four widely used data splits of DIOR, our method significantly outperforms previous state-of-the-art methods by at most 8.7%.

Few-shot object detection (FSOD) aims to detect novel instances with only a limited number of labeled training samples, presenting a challenge that is particularly prominent in numerous remote sensing applications such as endangered species monitoring and disaster assessment. Existing FSOD methods for remote sensing images (RSIs) have achieved promising progress but remain constrained by the limited diversity of instances. To address this issue, we propose a novel framework that can leverage a diffusion model pretrained on large-scale natural images to synthesize diverse remote sensing instances, thereby improving the performance of few-shot object detectors. Instead of directly synthesizing complete remote sensing images, we first generate instance-level slices via a specialized slice-to-slice module, and then embed these slices into full-scale imagery for enhanced data augmentation. To further adapt diffusion models for remote sensing scenarios, we develop a class-agnostic image inversion module that can invert remote sensing instance slices into semantic space. Additionally, we introduce contrastive loss to semantically align the synthesized images with their corresponding classes. Experimental results show that our method has achieved an average performance improvement of 4.4% across multiple datasets and various approaches. Ablation experiments indicate that the elaborately designed inversion module can effectively enhance the performance of FSOD methods, and the semantic contrastive loss can further boost the performance.

The performance of deep learning approaches for Synthetic Aperture Radar (SAR) target detection is often limited by the scarcity of annotated data. While Self-Supervised Learning (SSL) has emerged as a powerful paradigm to mitigate data dependence, its potential in SAR target detection remains largely underexplored. In this study, we propose SARDet-MIM, a comprehensive framework based on Masked Image Modeling (MIM), to enhance SAR target detection. The approach consists of two stages. In the self-supervised pre-training stage, we propose an innovative Structural and Scattering Masked Autoencoder (SSMAE) method for SAR imagery. Unlike conventional MIM methods, which typically reconstruct raw pixels, SSMAE employs a physics-aware reconstruction target comprising multi-scale gradient and SAR-Harris features. This strategy explicitly guides the network to capture discriminative structural contexts and intrinsic scattering features that benefit SAR target detection. For downstream detection, we construct a Maximally Pre-trained Detector (MPD), which integrally transfers the pre-trained ViT encoder–decoder architecture to the detection network to fully exploit pre-trained representations. Extensive experiments on three SAR target detection datasets demonstrate that SARDet-MIM consistently outperforms competing methods.

Deep learning networks, such as convolutional neural networks (CNNs), are increasingly applied to synthetic aperture radar (SAR) feature representation and image classification. However, the performance of most deep learning methods relies on sufficient labeled data, which is difficult to collect for SAR images. As a result, self-supervised contrastive learning (CL) methods have attracted enthusiasm in recent studies to learn SAR representations with unlabeled data. Most existing CL-based methods for SAR representation learning simply utilize the amplitude information as the network input but neglect the particular features of complex-valued SAR images such as spectral information, leading to insufficient feature extraction. To address this issue, we propose a self-supervised sublook contrastive learning (SCL) method to learn spectral representations from unlabeled data. Firstly, we extract sublooks from SAR images to establish a spectral representation branch to discover the spectral information. Secondly, a novel SCL method with a sublook-matching task is proposed based on a contrastive network to learn spectral representations. The branch is applied to SAR image classification tasks by integrating it with a typical amplitude network through feature concatenation. Experimental results have validated the effectiveness and generalization ability of the proposed method with a different experimental protocol that distinguishes the pretrain and downstream datasets.