AD-DETR:在拥挤的场景中具有不对称关系和分离注意力的DETR
Yueming Huang1,2, Guowu Yuan1,2
1School of Information Science and Engineering, Yunnan University, Kunming 650504, China.
Mathematical biosciences and engineering : MBE
|September 7, 2023
概括
这项研究介绍了AD-DETR,这是一个用于在拥挤场景中检测行人新的框架. 它通过使用非对称的关系融合机制和脱的交叉注意力头来有效地减少重复和错误检测.
科学领域:
- 计算机视觉 计算机视觉
- 深度学习 (Deep Learning) 是一种深度学习.
- 对象检测检测器可以检测到物体.
背景情况:
- 在拥挤的场景中检测行人面临着重复预测,高阻塞率和小可见行人区域的挑战.
- 现有的检测变压器 (DETR) 框架表现出对称性,导致同步预测更新和重复检测.
研究的目的:
- 解决目前在拥挤环境中的行人检测方法的局限性.
- 提出一种新的检测框架,AD-DETR (非对称关系检测变压器),以消除重复预测并减少错误/缺失检测.
主要方法:
- 引入了一个不对称的关系融合机制,使查询能够通过融合周围预测的相对关系来学习消除重复预测.
- 开发了一个脱的交叉注意力头来限制注意力范围,专注于可见区域和高可信度区域,从而减少来自隐蔽物体的噪音.
- 将这些模块集成到基于DETR的框架中,使用可变形DETR与ResNet-50骨干.
主要成果:
- 在CrowdHuman数据集上实现了最先进的性能,平均精度为92.6%,MR$^{-2}$为40.0%,Jaccard指数为84.4%.
- 与Iter-E2EDet和MIP等现有方法相比,已经证明了显著的改进.
- 展示了对拥挤场景行人检测的拟议方法的稳定性和有效性.
结论:
- 拟议的AD-DETR框架有效地解决了拥挤场景中行人检测的关键挑战.
- 不对称的关系融合和脱的交叉注意力机制显著提高了检测准确度,并减少了错误.
- 在复杂,拥挤的环境中,AD-DETR为基于查询的对象检测提供了强大的高性能解决方案.
相关概念视频
Deindividuation
26.4K
Deindividuation is a form of social influence on an individual’s behavior such that the individual engages in unusual or non-normal behavior while in a group setting. Why? Because in these group settings, the individual no longer sees themselves as an individual anymore, disinhibiting their behavior and personal restraint.
26.4K
Attention-Deficit/Hyperactivity Disorder
90
Attention-deficit/hyperactivity disorder (ADHD) is a neurodevelopmental disorder characterized by persistent inattention, hyperactivity, and impulsivity. It affects approximately 5-8% of children globally, with around 60-70% of cases persisting into adulthood. ADHD has significant implications for educational attainment, social interactions, and occupational success.
Diagnostic Criteria and Symptoms
To diagnose ADHD, symptoms must manifest before age 12 and be evident across multiple settings....
Diagnostic Criteria and Symptoms
To diagnose ADHD, symptoms must manifest before age 12 and be evident across multiple settings....
90
Schemas
11.7K
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.
11.7K
Gestalt Principles of Perception
340
Gestalt principles provide a framework for understanding how humans perceive objects as unified wholes within their context. These principles are essential in explaining the cognitive processes that make sense of complex visual stimuli by organizing them into coherent groups. One fundamental principle is proximity, which posits that objects located close to each other are perceived as a collective group. For instance, when dots are positioned near one another, the visual system interprets them...
340
Association Areas of the Cortex
5.5K
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,...
5.5K
Directional Terms
8.7K
Directional terms are essential for describing the relative locations of different body structures. For instance, an anatomist might describe one band of tissue as "inferior to" another, or a physician might describe a tumor as "superficial to" a deeper body structure. These terms often use comparative terms in pairs to trace out the relative locations of one body part to another or descriptions of body tissues like the deeper ones from superficially present with reference to...
8.7K


