Xue Li

In practical applications of aerial object detection, real-time unmanned aerial vehicle (UAV) imagery is often affected by noise, low light, and cloud occlusion, leading to poor image quality. The performance of mainstream UAV object detection algorithms tends to degrade when applied to such imagery, as these models are typically trained and evaluated on clean datasets. To address these challenges, we propose a robust YOLO based network, YOLO-AFP, which integrates an atrous feature pyramid (AFP) module. This allows the model to generalize effectively under various corrupted conditions, despite being trained only on clean data. First, we introduced AFP module, which employs atrous convolutions with varying dilation rates, and integrate it into the path aggregation network (PAN) to expand the receptive field. This enhancement allows the model to better capture object-background relationships and reduce feature corruption caused by local pixel changes. Second, we propose a robust ResNet-SPPF as the backbone network, which retains strong feature extraction capabilities while having fewer residual connections compared to YOLO's Darknet. This design effectively mitigates the impact of corrupted image features on subsequent feature extraction. To validate the effectiveness of our method, we constructed two new datasets based on the DOTAv1.0 dataset, named DOTA-HC and DOTA-HCloud. Experimental results demonstrate that on the DOTA-HC dataset, YOLO-AFP achieved a mPC of 60.8% and a rPC of 80.3%, outperforming the best real-time detection model by 1.5% and 2%, respectively. On the DOTA-HCloud dataset, YOLO-AFP achieved an rPC of 88.5%, surpassing the top model by 1.1%.

Object detection is a challenging task that aims to locate and classify instances in an image simultaneously. High-performing deep detectors are typically trained on extensive labeled datasets and will face the problem of accuracy degradation in different scenarios. Through domain adaptation, the detector can attain generalization, making precise detections even in the presence of different data distributions without labels. In this paper, we propose a confidence-driven region mixing (CR-Mixing) framework, which is a novel approach that integrates the region-selective mixing (RSM) method into a mean-teacher framework with an unbiased adversarial module (UAM), addressing the domain-shift and knowledge transfer problems in the unsupervised domain adaptation object detection task. First, we construct RSM, which utilizes pseudo-detection labels to compute object information at the region level and integrates this information in a balanced manner to maximize accurate foreground details for the detection model. This enables the detection model to adjust its focus to unlabeled domains gradually. Secondly, to acquire a backbone network with object-focused features, we develop the UAM method. This method is a multiscale alignment network designed to constrain the backbone network in learning domain-invariant features. We conducted extensive experiments on two benchmarks, and the final results show that the CR-Mixing model demonstrates significant effectiveness in robust unsupervised domain adaptation for optical remote sensing object detection tasks.

The object classification in SAR imagery is a challenging task, due to the low resolution and high-level speckle noise. The electro-optical images provide complementary information to SAR images, and thus, the knowledge from the electro-optical (EO) images can be used to improve the SAR imagery interpretation. This letter proposes a deep cross-modal transfer network for object classification in SAR imagery. Specifically, the knowledge from the teacher model constructed on the EO images is transferred to the student model for mining discriminative fine-grained features of SAR images. Meanwhile, to perform the cross-modality transferring and fine-grained feature mining, a novel loss function is developed. Experimental results on real-world datasets demonstrate the effectiveness and reliability of the proposed method.

Domain adaptation purposes to transfer well-labelled domain knowledge to poor-labelled domain. However, many domain adaptation methods focus too much on spectral features and simple spatial features, causing failure to eliminate noise that is an important risk in remote sensing image classification. Degenerated features are also a potential risk to feature transformation in domain adaptation. In addition, it is also a typical problem that reduces the difference in probability distribution between different domains for domain adaptation. To alleviate these issues, we propose a multilevel spatial features-based manifold metric learning (MSF-MML) method for domain adaptation in remote sensing image classification. Firstly, it applies and iterates a spatial information filtering to extract multilevel spatial features by calculating the average of sample pixels and neighboring pixels, effectively obtaining more stable feature information. Then, it utilizes the Grassmann manifold space to alleviate the problem of degenerated features of remote sensing data in domain adaptation. Finally, it exploits maximum mean discrepancy to construct metric constraints that reduces discrepancy in domains probability distributions. The effectiveness of MSF-MML was demonstrated on three real-world datasets.