In the annotation of remote sensing images (RSIs), effectiveness common object detection methods trained on only a few samples decreases instantly, which has prompted increasing research few-shot problem in sensing. RSIs often exhibit suboptimal performance scenarios due to intricate nature scene information interference and high degree cosine similarity, both present significant challenges their effectiveness. this paper, two-stage framework based fine-tuning is selected deal with problems...

The overwhelming majority of models for remote sensing image (RSI) scene classification generally require the weights pre-trained on natural images initialization before formal training. However, differences in imaging mechanisms lead to huge discrepancies between and RSIs, strong visual representation learned from massive limits performance when inferencing RSIs. To address this issue, well-established self-supervised contrastive learning paradigm field is introduced RSI field. We propose a...

Labeling data in the field of remote sensing is time-consuming and labor-intensive, making domain adaptation between different domains an urgently needed solution. To address gap diverse datasets domain, numerous methods tailored for high-resolution imagery have emerged. Some existing focus on reducing at either feature level or pixel level, often overlooking their underlying connection. tackle this issue, we introduce a prototype-wise contrastive alignment paradigm (PCFA) aimed bridging...

For the past few years, barrier of explainability accompanying by deep neural networks (DNNs) has been increasingly studied. The methods based on class activation map (CAM) which interpret model decision mapping output back to input space, have achieved a notable momentum among research. However, CAM-based cannot stably produce effective explanation results remote sensing images (RSIs), owing coarse location generated high-level features, whereas, RSIs contain abundant detailed spatial...

Active learning (AL) attempts to select informative samples in a dataset minimize the number of required labels while maximizing performance model. Current AL segmentation tasks is limited expansion popular classification-based methods including entropy, MC-dropout, etc. Meanwhile, most applications medical field are simply migrations that fail consider nature images, such as high class imbalance, domain difference, and data scarcity. In this study, we address these challenges propose novel...

Recent works for face editing usually manipulate the latent space of StyleGAN via linear semantic directions. However, they suffer from entanglement facial attributes, need to tune optimal strength, and are limited binary attributes with strong supervision signals. This paper proposes a novel adaptive nonlinear transformation disentangled conditional editing, termed AdaTrans. Specifically, our AdaTrans divides manipulation process into several finer steps; i.e., direction size at each step...

The gap between self-supervised visual representation learning and supervised is gradually closing. Self-supervised does not rely on a large amount of labeled data reduces the loss human information. Compared with natural images, remote sensing images require rich samples annotation by experts. Moreover, many algorithms have poor interpretability unconvincing results. Therefore, this paper proposes method based prototype assignment designing pretext task so that network maps features to...

Facial attribute manipulation (FAM) aims to edit the semantic attributes of facial images according user's requirements. Unfortunately, majority existing FAM methods struggle in meeting at least one two requirements: high reconstruction quality and irrelevance preservation. To alleviate these limitations, we propose a novel Disentangled nOn-linear latent navigation framework for FAM, termed DO-FAM. promote quality, leverage hypernetworks fine-tune pre-trained StyleGAN2 generator. decouple...

Active learning (AL) has found wide applications in medical image segmentation, aiming to alleviate the annotation workload and enhance performance. Conventional uncertainty-based AL methods, such as entropy Bayesian, often rely on an aggregate of all pixel-level metrics. However, imbalanced settings, these methods tend neglect significance target regions, eg., lesions, tumors. Moreover, selection introduces redundancy. These factors lead unsatisfactory performance, many cases, even...

To overcome the inherent domain gap between remote sensing (RS) images and natural images, some self-supervised representation learning methods have made promising progress. However, they overlooked diverse angles present in RS objects. This paper proposes Masked Angle-Aware Autoencoder (MA3E) to perceive learn during pre-training. We design a \textit{scaling center crop} operation create rotated crop with random orientation on each original image, introducing explicit angle variation. MA3E...

Facial attribute manipulation (FAM) aims to infer desired facial images by modifying specific attributes while keeping others unchanged. Existing works suffer from the entanglement of attributes, leading unexpected artifacts and loss identity information after editing. To alleviate these issues, we propose a novel FAM framework based on StyleGAN, termed VR-FAM, which can meet requirements FAM—editing ability, distortion, fidelity. First, variance-reduced encoder make latent space close one...

Recent works for face editing usually manipulate the latent space of StyleGAN via linear semantic directions. However, they suffer from entanglement facial attributes, need to tune optimal strength, and are limited binary attributes with strong supervision signals. This paper proposes a novel adaptive nonlinear transformation disentangled conditional editing, termed AdaTrans. Specifically, our AdaTrans divides manipulation process into several finer steps; i.e., direction size at each step...