人类启发的场景理解:一个有基础的认知方法,用于无偏的场景图表生成
IEEE transactions on pattern analysis and machine intelligence
|November 21, 2025
概括
本研究引入了一个基于认知方法 (GCM) 来解决场景图形生成 (SGG) 中的偏差. GCM 提高了模型的概括性和在罕见的视觉关系上的性能.
科学领域:
- 计算机视觉 计算机视觉
- 人工智能的人工智能
- 机器学习 机器学习
背景情况:
- 场景图形生成 (SGG) 对于图像理解至关重要,但患有长尾偏差,有利于共同的视觉关系.
- 由于有限的概括性,现有的不偏见的SGG方法在数据集变化方面遇到了困难.
- 显式建模类多样性对于强大的SGG至关重要.
研究的目的:
- 提出一种新的基于认知方法 (GCM),用于无偏的场景图生成.
- 通过结合类似人类的认知过程来增强 SGG 模型的概括能力.
- 为了减轻目前的SGG方法中普遍存在的长尾偏差.
主要方法:
- 通过外域知识注入和语义组意识合成器进行GCM模型模拟.
- 身体状态通过模式删除来模拟,以改善跨模式补偿.
- 使用Shapley增强多式反事实模块来建模局势行动,以获得上下文理解.
主要成果:
- 在Visual Genome,GQA和Open Images V6数据集上,GCM显著超过了最先进的方法.
- 拟议的方法有效地减轻了场景图表生成中的长尾偏差.
- GCM在头部 (常见) 和尾部 (罕见) 的视觉关系之间实现了平衡的表现.
结论:
- 接地认知方法为客观的场景图生成提供了一个强大的解决方案.
- 该方法增强了模型的概括性,并解决了现有方法的局限性.
- GCM提供了平衡的表现,提高了对常见和罕见视觉背景的理解.
相关概念视频
Schemas
12.3K
A schema is a mental construct consisting of a cluster or collection of related concepts (Bartlett, 1932). There are many different types of schemata, and they all have one thing in common: schemata are a method of organizing information that allows the brain to work more efficiently. When a schema is activated, the brain makes immediate assumptions about the person or object being observed.
12.3K
Stereotype Content Model
15.3K
The Stereotype Content Model (SCM) was first proposed by Susan Fiske and her colleagues (Fiske, Cuddy, Glick & Xu, 2002; see also Fiske, 2012 and Fiske, 2017). The SCM specifies that when someone encounters a new group, they will stereotype them based on two metrics: warmth—or that group’s perceived intent, and how likely they are to provide help or inflict harm—and competence—or their ability to carry out that objective. Depending on the warmth-competence...
15.3K
Introduction to Cognitive Psychology
2.2K
Cognitive psychology is the field of psychology dedicated to examining how people think. It attempts to explain how and why we think the way we do by studying the interactions among human thinking, emotion, creativity, language, and problem-solving, as well as other cognitive processes. Cognitive psychology studies how information is processed and manipulated in remembering, thinking, and knowing.
This field emerged in the mid-20th century, following a period dominated by behaviorism, which...
This field emerged in the mid-20th century, following a period dominated by behaviorism, which...
2.2K
Schemata
328
A schema is a mental construct that organizes related concepts, allowing the brain to process information efficiently. Upon activation, schemata facilitate assumptions about people or objects.
Two types of schemata are:
Two types of schemata are:
328
Naturalistic Observations
16.9K
If you want to understand how behavior occurs, one of the best ways to gain information is to simply observe the behavior in its natural context. However, people might change their behavior in unexpected ways if they know they are being observed. How do researchers obtain accurate information when people tend to hide their natural behavior? As an example, imagine that your professor asks everyone in your class to raise their hand if they always wash their hands after using the restroom. Chances...
16.9K
Modeling and Similitude
588
Scaled modeling is a fundamental technique in engineering, enabling the study of large and complex systems by creating smaller, manageable replicas that recreate critical characteristics of the original. In hydrology and civil infrastructure, for example, scaled models of dams help analyze water flow, turbulence, and pressure. This method allows for accurate predictions of real-world behavior within a controlled environment, significantly reducing the cost and time involved in full-scale...
588


