通过语义自编码器和视觉关系转移增强零拍摄场景识别
Chen Wang1, Man Wang2, Guohua Peng3
1School of Computer Science and Artificial Intelligence, Wuhan Textile University, Wuhan, 430200, China. wangchen@wtu.edu.cn.
Scientific reports
|December 19, 2025
概括
本研究引入了一种用于场景图像中零拍摄学习的新方法,它结合了语义自动编码器 (SAE) 和视觉关系传输 (VRT). 该方法通过改善视觉语义关系来提高未见类的识别精度.
科学领域:
- 计算机视觉 计算机视觉
- 机器学习 机器学习
- 人工智能的人工智能
背景情况:
- 零射击学习 (ZSL) 旨在识别在培训期间未见过的课堂图像.
- 传统的ZSL方法在场景图像方面遇到了困难,原因是阶级内存在显著的差异.
- 现有的方法往往侧重于视觉语义或看不见的语义关系,为场景识别产生不理想的性能.
研究的目的:
- 开发一种新的零拍摄场景图像识别方法,克服现有方法的局限性.
- 为了提高复杂场景数据集中未见类的识别性能.
- 在ZSL中有效地弥合视觉和语义空间之间的领域差距.
主要方法:
- 提出了一种名为SAEVRT的新方法,它结合了语义自编码器 (SAE) 和视觉关系传输 (VRT).
- 学习了两个可见和不可见场景类的SAE,以减轻视觉和语义空间之间的域移动.
- 开发了一种可解释的VRT方法,以学习有效的看不见的语义向量,解决语义向量的效率较低,与场景图像的视觉特征相比.
主要成果:
- 在四个基准场景数据集中,SAEVRT方法实现了卓越的性能.
- 在Scene15上,识别精度达到63.77%,在MIT67上达到67.75%,在UCM21上达到58.68%,在NWPU45上达到53.26%.
- 统一的框架有效地利用了视觉语义和可见-不可见的关系.
结论:
- 拟议的SAEVRT方法显著提升了零拍摄场景图像识别.
- 结合SAEs和VRT提供了一个强大的解决方案,用于处理场景图像中的大型类内变化.
- 该方法展示了更准确,更可靠地识别未见的视觉类别的潜力.
相关概念视频
01:27Associative Learning
1.2K
Associative learning is a fundamental concept in behavioral psychology, wherein a connection is established between two stimuli or events, leading to a learned response. This process is critical in understanding how behaviors are acquired and modified. Conditioning, the mechanism through which associations are formed, can be divided into two main types: classical conditioning and operant conditioning, each elucidating different aspects of associative learning.
Classical conditioning, also known...
Classical conditioning, also known...
1.2K
01:12Observational Learning
791
Albert Bandura's observational learning, also known as imitation or modeling, occurs when a person observes and imitates another's behavior. It is a quicker process than operant conditioning. A well-known example is the Bobo doll study, where children who saw an adult acting aggressively towards the doll were more likely to act aggressively when left alone, compared to those who observed a nonaggressive adult. Many psychologists view observational learning as a form of latent learning...
791
01:28Automatic Processing and Automatic Social Behavior
196
Automatic processing refers to the cognitive operations that occur without conscious intent or awareness, playing a fundamental role in shaping social cognition and behavior. These processes enable individuals to navigate complex social environments efficiently by relying on mental shortcuts and pre-existing knowledge structures known as schemas. One of the most influential mechanisms underlying automatic processing is priming, which subtly activates mental representations through exposure to...
196
01:15Depth Perception and Spatial Vision
1.7K
Depth perception is the ability to perceive objects three-dimensionally. It relies on two types of cues: binocular and monocular. Binocular cues depend on the combination of images from both eyes and how the eyes work together. Since the eyes are in slightly different positions, each eye captures a slightly different image. This disparity between images, known as binocular disparity, helps the brain interpret depth. When the brain compares these images, it determines the distance to an object.
1.7K
01:24Vision
59.2K
Vision is the result of light being detected and transduced into neural signals by the retina of the eye. This information is then further analyzed and interpreted by the brain. First, light enters the front of the eye and is focused by the cornea and lens onto the retina—a thin sheet of neural tissue lining the back of the eye. Because of refraction through the convex lens of the eye, images are projected onto the retina upside-down and reversed.
59.2K