CNIPA.AI
Back to Search
Dossier

一种基于层间自蒸馏解耦的小样本语义分割方法

InventionActive
6Claims · 1 independent
§ Ⅰ

Dossier Overview

Inventor

常兆斌; 李亚锋; 武继杰; 杨世丞; 李晓旭

IPC Classification

G06V 20/70 (2022.01)G06V 10/26 (2022.01)G06V 10/82 (2022.01)G06V 10/77 (2022.01)G06V 10/74 (2022.01)G06N 3/096 (2023.01)G06N 5/045 (2023.01)G06N 3/045 (2023.01)G06N 3/0985 (2023.01)

本发明公开了一种基于层间自蒸馏解耦的小样本语义分割方法,包括特征编码、层间特征分离与交互、多模态交互特征蒸馏、联合引导学习四个步骤。本发明利用了多模态特征交互和分支间交互特征蒸馏将查询混合特征进行了解耦,降低了查询混合特征内部不同语义之间的相互干扰,提升了分割模型对已知目标和未知目标的分割精度。

Sign in to read the full text

Claim 1 is shown. Create a free account to read all 6 claims, the full description, all drawings, translations and legal status.

  • All claims
  • Technical field
  • Background
  • Summary
  • Drawing descriptions
  • Detailed description

External Resources