Computer Vision
开放词汇分割
Open-vocabulary segmentationA computer vision task that aims to segment images into semantic regions using text queries, extending traditional segmentation to arbitrary classes not seen during training. / 一种计算机视觉任务，旨在利用文本查询将图像分割为语义区域，将传统分割扩展到训练期间未见的任意类别。
- Knowledge type
- 实际应用
- First proposed or discovered
- Proposer
- Turkey Farm member
- Creator
- 农场主
- Last updated
- 2026-10-22 16:03:08
Sub-knowledge points
Multimodal fusionSemantic re-alignmentScattering-evidence-guided fusion
Higher-order knowledge points
Semantic Segmentation / 工艺技术Image understanding
Main parameters and performance indicators
Query: Text description of the target object or classInput: Optical and SAR image data
Open problems
No unresolved problem recorded yet
Related literature
ranked by community starsSRASEF-OVSeg: Task-adaptive semantic re-alignment and scattering-evidence-guided multimodal fusion for optical–SAR open-vocabulary segmentationOpen source
Related products and links
No item recorded yet
Creation and modification trail
1 recordsRecord title: Open-vocabulary segmentation.
Node update feedback
review required