中文
相关论文

相关论文: FSDENet: A Frequency and Spatial Domains based Det…

200 篇论文

The increasing realism of synthetic images generated by advanced models such as VAEs, GANs, and LDMs poses significant challenges for synthetic image detection. To address this issue, we explore two artifact types introduced during the…

计算机视觉与模式识别 · 计算机科学 2025-10-24 Shuqiao Liang , Jian Liu , Renzhang Chen , Quanlong Guan

In this paper, we focus on exploring effective methods for faster and accurate semantic segmentation. A common practice to improve the performance is to attain high-resolution feature maps with strong semantic representation. Two strategies…

计算机视觉与模式识别 · 计算机科学 2023-08-09 Xiangtai Li , Jiangning Zhang , Yibo Yang , Guangliang Cheng , Kuiyuan Yang , Yunhai Tong , Dacheng Tao

Weather forecasting plays a critical role in various sectors, driving decision-making and risk management. However, traditional methods often struggle to capture the complex dynamics of meteorological systems, particularly in the presence…

计算机视觉与模式识别 · 计算机科学 2024-05-30 Jiaze Wang , Hao Chen , Hongcan Xu , Jinpeng Li , Bowen Wang , Kun Shao , Furui Liu , Huaxi Chen , Guangyong Chen , Pheng-Ann Heng

Transformers have recently emerged as a significant force in the field of image deraining. Existing image deraining methods utilize extensive research on self-attention. Though showcasing impressive results, they tend to neglect critical…

计算机视觉与模式识别 · 计算机科学 2024-02-08 Yuhong He , Aiwen Jiang , Lingfang Jiang , Zhifeng Wang , Lu Wang

Spatiotemporal predictive learning aims to forecast future frames from historical observations in an unsupervised manner, and is critical to a wide range of applications. The key challenge is to model long-range dynamics while preserving…

计算机视觉与模式识别 · 计算机科学 2026-04-17 Xinyong Cai , Runming Xie , Hu Chen , Yuankai Wu

Existing few-shot medical image segmentation (FSMIS) models fail to address a practical issue in medical imaging: the domain shift caused by different imaging techniques, which limits the applicability to current FSMIS tasks. To overcome…

计算机视觉与模式识别 · 计算机科学 2024-12-30 Yuntian Bo , Yazhou Zhu , Lunbo Li , Haofeng Zhang

Semantic segmentation necessitates approaches that learn high-level characteristics while dealing with enormous amounts of data. Convolutional neural networks (CNNs) can learn unique and adaptive features to achieve this aim. However, due…

计算机视觉与模式识别 · 计算机科学 2023-07-19 Hasan AlMarzouqi , Lyes Saad Saoud

Low-light remote sensing images generally feature high resolution and high spatial complexity, with continuously distributed surface features in space. This continuity in scenes leads to extensive long-range correlations in spatial domains…

计算机视觉与模式识别 · 计算机科学 2024-09-09 Zishu Yao , Guodong Fan , Jinfu Fan , Min Gan , C. L. Philip Chen

Due to the fast inference and good performance, discriminative learning methods have been widely studied in image denoising. However, these methods mostly learn a specific model for each noise level, and require multiple models for…

计算机视觉与模式识别 · 计算机科学 2018-08-01 Kai Zhang , Wangmeng Zuo , Lei Zhang

Large-scale fine-grained image retrieval has two main problems. First, low dimensional feature embedding can fasten the retrieval process but bring accuracy reduce due to overlooking the feature of significant attention regions of images in…

计算机视觉与模式识别 · 计算机科学 2021-10-12 Qi Zhao , Xu Wang , Shuchang Lyu , Binghao Liu , Yifan Yang

Current methods aggregate multi-level features or introduce edge and skeleton to get more refined saliency maps. However, little attention is paid to how to obtain the complete salient object in cluttered background, where the targets are…

计算机视觉与模式识别 · 计算机科学 2023-01-19 Ge Zhu , Jinbao Li , Yahong Guo

Cross-Domain Few-shot Semantic Segmentation (CD-FSS) aims to train generalized models that can segment classes from different domains with a few labeled images. Previous works have proven the effectiveness of feature transformation in…

计算机视觉与模式识别 · 计算机科学 2024-05-27 Jiayi Chen , Rong Quan , Jie Qin

For real-time semantic segmentation, how to increase the speed while maintaining high resolution is a problem that has been discussed and solved. Backbone design and fusion design have always been two essential parts of real-time semantic…

计算机视觉与模式识别 · 计算机科学 2021-06-21 Tan Sixiang

High dynamic range (HDR) imaging from multiple low dynamic range (LDR) images has been suffering from ghosting artifacts caused by scene and objects motion. Existing methods, such as optical flow based and end-to-end deep learning based…

图像与视频处理 · 电气工程与系统科学 2023-11-09 Tianhong Dai , Wei Li , Xilei Cao , Jianzhuang Liu , Xu Jia , Ales Leonardis , Youliang Yan , Shanxin Yuan

Recently, deep learning has achieved promising performance in the change detection task. However, the deep models are task-specific and data set bias often exists, thus it is difficult to transfer a network trained on one multi-temporal…

计算机视觉与模式识别 · 计算机科学 2020-04-14 Hongruixuan Chen , Chen Wu , Bo Du , Liangepei Zhang

Foreground segmentation algorithms aim segmenting moving objects from the background in a robust way under various challenging scenarios. Encoder-decoder type deep neural networks that are used in this domain recently perform impressive…

计算机视觉与模式识别 · 计算机科学 2019-09-04 Long Ang Lim , Hacer Yalim Keles

In recent years, how to strike a good trade-off between accuracy and inference speed has become the core issue for real-time semantic segmentation applications, which plays a vital role in real-world scenarios such as autonomous driving…

计算机视觉与模式识别 · 计算机科学 2021-07-19 Guangwei Gao , Guoan Xu , Yi Yu , Jin Xie , Jian Yang , Dong Yue

Ultrasound image segmentation is pivotal for clinical diagnosis, yet challenged by speckle noise and imaging artifacts. Recently, DINOv3 has shown remarkable promise in medical image segmentation with its powerful representation…

计算机视觉与模式识别 · 计算机科学 2025-12-15 Yixuan Zhang , Qing Xu , Yue Li , Xiangjian He , Qian Zhang , Mainul Haque , Rong Qu , Wenting Duan , Zhen Chen

Automatic recognition and segmentation methods now become the essential requirement in identifying co-seismic landslides, which are fundamental for disaster assessment and mitigation in large-scale earthquakes. This approach used to be…

计算机视觉与模式识别 · 计算机科学 2023-10-27 Qingsong Xu , Chaojun Ouyang , Tianhai Jiang , Xuanmei Fan , Duoxiang Cheng

The rapid development of spatial transcriptomics (ST) offers new opportunities to explore the gene expression patterns within the spatial microenvironment. Current research integrates pathological images to infer gene expression, addressing…