RC-DETR:通过基于等级的对比学习来改善拥挤的行人检测中的DETR
Feng Gao1, Jiaxu Leng1, Ji Gan1
1Chongqing Key Laboratory of Image Cognition, College of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing, 400065, China.
概括
这项研究引入了一种基于等级的新型对比式学习方法,以改善检测转换器 (DETR) 检测拥挤的行人检测. 这种方法增强了特征的区分能力,大大提高了对具有挑战性的数据集的性能.
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:
- 检测 转换器 (DETR) 在一般物体检测方面表现出色,但在拥挤的行人场景中扎.
- 目前的DETR培训方法仅依赖于行人标签,导致行人和背景之间无法区分的特征,导致检测错误.
研究的目的:
- 开发一种方法,通过增强特征区分能力,提高DETR在拥挤的行人检测中的性能.
- 引入基于等级的对比学习方法,为训练样本创建特定的约束.
主要方法:
- 提出了一种基于等级的对比学习方法,过训练样本并创建可区分的正负对.
- 该方法使用这些对训练DETR,确保行人信心得分始终超过背景得分.
- 这种方法可以插入到现有的DETR中,而不会增加推断开销.
主要成果:
- 拟议的方法在三个DETR变体中显示出卓越的性能.
- 在Crowdhuman数据集上实现了最先进的38.9%的平均减少 (MR).
- 有效地解决了DETR在拥挤的行人检测中的性能下降问题.
结论:
- 基于等级的对比学习方法有效地提高了DETR在拥挤的场景中区分行人与背景的能力.
- 这种方法在没有增加推断复杂性的情况下,为拥挤的行人检测提供了显著的改进.
- 该方法代表了对需要在密集环境中准确的行人检测的现实应用的有前途的进步.
相关概念视频
01:05Difference from Background: Limit of Detection
5.9K
The limit of detection (LOD) is the smallest amount of analyte that can be distinguished from the background noise. The LOD value corresponds to the concentration at which the analyte signal is three times larger than the standard deviation of the blank signal. Below this value, the analyte signal cannot be differentiated from the background noise. It is calculated by dividing the calibration slope by 3 times the standard deviation of the blank signals.
The LOD indicates the presence or absence...
The LOD indicates the presence or absence...
5.9K
02:07Improving Translational Accuracy
9.1K
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
9.1K
01:22Force Classification
1.1K
Forces play a crucial role in the study of physics and engineering. They are essential in describing the motion, behavior, and equilibrium of objects in the physical world. Forces can be classified based on their origin, type, and direction of action.
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...
1.1K