Jingling Huang,Hanzi Wang,Qiangqiang Wu et al.
Jingling Huang et al.
Existing meta-learning based few-shot object detection methods suffer from limitations in learning representative prototypes. Specifically, directly aggregating bounding box contents from support images into prototypes renders these methods...
Unsupervised Domain Adaptation in Biomedical Images Segmentation With Guided Diffusion Generative Prior [0.03%]
Alexandre Stenger,Etienne Baudrier,Nicolas Passat et al.
Alexandre Stenger et al.
Semantic segmentation has suffered for a while from a lack of datasets such as ImageNet for image classification. This issue was partially alleviated by the advent of the segment anything model (SAM), which provides a foundation model train...
Yu Wang,Baoyu Liang,Shoutai Zhu et al.
Yu Wang et al.
3D Semantic Scene Completion (SSC) aims to infer voxel-level occupancy and semantics from partial 2D observations. However, existing methods often rely on global attention or uniform voxel modeling, which may cause semantic interference acr...
Jun Chen,Wei Yu,Xin Tian et al.
Jun Chen et al.
Existing image fusion methods focus on containing more complementary information, but source images always suffer from motion blur owing to object motion, which results in distorted details in fused images and further deteriorates performan...
Spectral-Spatial Enhanced Local Contrast Strategy for Hyperspectral Small Air Target Detection [0.03%]
Feng Han,He Sun,Lianru Gao et al.
Feng Han et al.
Detecting small air target is an important task in civil aviation. However, the weak characteristics of these targets make detection challenging. Hyperspectral image (HSI), provides a new approach for the small air target detection task due...
Liuxiang Qiu,Hui Da,Wenxi Liu et al.
Liuxiang Qiu et al.
Previous multimodal visual-tactile image representation learning (VTL) methods have achieved significant success in object understanding through large-scale training data. However, obtaining sufficient training data is often infeasible, and...
Lianghui Zhu,Yingyue Li,Jiemin Fang et al.
Lianghui Zhu et al.
Transformer has been very successful in various computer vision tasks and understanding the working mechanism of transformer is important. As touchstones, weakly-supervised semantic segmentation (WSSS) and class activation map (CAM) are use...
Self-Anchored Progressive Framework With Noise Mitigation for Unsupervised Camouflaged Object Detection [0.03%]
Shijie Liu,Binwei Xu,Tuo Shen et al.
Shijie Liu et al.
Unsupervised Camouflaged Object Detection (UCOD) presents a significant challenge due to the inherent similarity between camouflaged objects and their backgrounds, compounded by the absence of manual annotations. Although pixel-level pseudo...
From Coarse to Continuous: Progressive Refinement Implicit Neural Representation for Motion-Robust Anisotropic MRI Reconstruction [0.03%]
Zhenxuan Zhang,Lipei Zhang,Yanqi Cheng et al.
Zhenxuan Zhang et al.
In motion-robust magnetic resonance imaging (MRI), slice-to-volume reconstruction is critical for recovering anatomically consistent 3D brain volumes from 2D slices, especially under accelerated acquisitions or patient motion. However, this...
FD-SCU: Frequency Decomposition-Based Spectrum Collaborative Upsampling for Point Cloud Color Attribute [0.03%]
Hao Liu,Wenchao Wang,Hui Yuan et al.
Hao Liu et al.
Existing point cloud color upsampling methods typically treat color upsampling as an interpolation problem within a local color or implicit feature domain. This largely overlooks the ability of the frequency domain to capture color correlat...