通过循环注意力强大的细粒度视觉分类
IEEE transactions on neural networks and learning systems
|September 29, 2025
概括
这项研究引入了一种用于细粒度视觉分类 (FGVC) 的新方法,该方法处理重度遮蔽 (HO) 图像. 新的循环注意力方法提高了在具有挑战性的现实世界条件中的准确性.
科学领域:
- 计算机视觉 计算机视觉
- 机器学习 机器学习
背景情况:
- 细粒度视觉分类 (FGVC) 与严重遮蔽 (HO) 图像进行斗争,这些图像掩盖了关键特征.
- 目前处理封闭的方法有局限性,经常丢弃或人工重建封闭的区域.
研究的目的:
- 为在开放世界的环境中开发一种新的FGVC强大的方法,特别是解决严重封闭的挑战.
- 利用人类自我调节学习 (SRL) 原则来改善隐蔽图像中的特征歧视.
主要方法:
- 提出了一种新的多实例模型,结合循环注意力,灵感来自于SRL行为.
- 在反循环中开发了一个合作游戏机制,以重新校准注意力和重新评估图像补丁选择.
- 将多实例模型集成到变压器架构中,创建了SRL-FGVC变压器.
主要成果:
- 与现有方法相比,SRL-FGVC变压器在六个公共数据集和一个新建立的数据集上表现出更高的性能.
- 循环注意力机制通过制定前进和反自我注意力之间的合作联盟,有效地减轻了注意力偏差.
- 该模型在重度阻塞场景中显示出一致的超出性能.
结论:
- 拟议的SRL-FGVC变压器在具有挑战性的现实条件下为强大的细粒度视觉分类提供了一个有希望的新方向.
- 利用SRL原则和循环注意力为处理严重封闭的图像数据提供了有效的策略.
相关概念视频
Association Areas of the Cortex
8.9K
Association areas are regions of the cerebral cortex that do not have a specific sensory or motor function. Instead, they integrate and interpret information from various sources to enable higher cognitive processes such as memory, learning, and decision-making. Some key association areas include the following:
Prefrontal Association Area: This area is located in the frontal lobe and is involved in planning, decision-making, and moderating social behavior. It connects with primary motor areas,...
Prefrontal Association Area: This area is located in the frontal lobe and is involved in planning, decision-making, and moderating social behavior. It connects with primary motor areas,...
8.9K
Perceptual Constancy
1.3K
Perceptual constancy is the ability to recognize that objects remain consistent and unchanged even when their appearance varies due to changes in sensory input. There are four main types of perceptual constancy: size constancy, shape constancy, color constancy, and brightness constancy.
Size constancy is the recognition that an object remains the same size, even when its image on the retina changes. For instance, a bus is perceived to be large enough to carry people, even if it looks tiny from...
Size constancy is the recognition that an object remains the same size, even when its image on the retina changes. For instance, a bus is perceived to be large enough to carry people, even if it looks tiny from...
1.3K


