视觉转换器和卷积神经网络之间的全面比较,用于面部识别任务.
Marcos Rodrigo1, Carlos Cuevas2, Narciso García2
1Grupo de Tratamiento de Imágenes (GTI), Information Processing and Telecommunications Center (IPTC), Universidad Politécnica de Madrid (UPM), Madrid, 28040, Spain. marcos.rodrigo@upm.es.
Scientific reports
|September 13, 2024
概括
视觉转换器在面部识别任务中优于卷积神经网络,在阻塞和距离方面表现出卓越的准确性和稳定性. 这些模型提供了更高效的解决方案,推断速度更快,内存足迹更小.
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:
- 面部识别是计算机视觉中的一个关键任务.
- 卷积神经网络 (CNN) 占主导地位,但视觉转换器 (ViT) 正在出现.
- 在多样化,具有挑战性的数据集上对已建立的CNN进行ViT评估是必要的.
研究的目的:
- 对视觉转换器和卷积神经网络进行面部识别的全面比较.
- 在各种数据集中评估模型性能,包括闭塞和距离变化.
- 分析培训,评估和硬件/软件配置.
主要方法:
- 对六种最先进的模型进行了比较分析:EfficientNet,Inception,MobileNet,ResNet,VGG和Vision Transformers. 这些模型包括:
- 在五个不同的面部识别数据集 (LFw,RWF,SCF,UPM-GTI-Face,VGG Face 2) 上进行了广泛的实验.
- 深入检查实验结果,包括培训,评估和系统配置.
主要成果:
- 与CNN相比,视觉转换器在面部识别和验证方面表现出更高的准确性和稳定性.
- ViTs在处理面部遮 (口罩,眼镜) 和不同距离方面显著改善.
- ViTs实现了具有竞争力的推断速度,并且比可比的CNN模型需要更少的内存.
结论:
- 视觉转换器代表了面部识别任务的更高效和有效的解决方案比传统的CNN.
- ViT提供了增强的性能,特别是在具有挑战性的真实世界场景中.
- 这项研究为未来面部识别技术的研发提供了宝贵的见解.
相关概念视频
Vision
53.1K
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.
53.1K
Types Of Transformers
952
Transformers can provide desired voltages to a circuit by modifying the number of turns in the secondary windings.
If the ratio of the number of turns in the secondary winding to that of the primary winding is greater than one, then the transformer is said to be a step-up transformer. In a step-up transformer, the voltage at the secondary winding is greater than the voltage applied at the primary winding.
However, if this ratio is less than one, the transformer is said to be a step-down...
If the ratio of the number of turns in the secondary winding to that of the primary winding is greater than one, then the transformer is said to be a step-up transformer. In a step-up transformer, the voltage at the secondary winding is greater than the voltage applied at the primary winding.
However, if this ratio is less than one, the transformer is said to be a step-down...
952
Transformers with Off-Nominal Turns Ratios
142
In scenarios involving parallel transformers with disparate ratings, developing per-unit models requires accommodating off-nominal turns ratios. This situation arises when the selected base voltages are not proportional to the transformer’s voltage ratings. Consider a transformer where the rated voltages are related by the term a. If the chosen voltage bases satisfy a relationship involving term b, term c is defined as the ratio of these bases. This ratio is then substituted into the...
142
The Ideal Transformer
364
In single-phase two-winding transformers, two windings are coiled around a magnetic core characterized by cross-sectional area A and magnetic permeability μ. A phasor current i1 enters the left winding while i2 exits the right winding, establishing the fundamental working of the transformer through electromagnetic principles.
Ampere's Law forms the basis of understanding the magnetic field within the transformer. It states that the integral of the magnetic field intensity's...
Ampere's Law forms the basis of understanding the magnetic field within the transformer. It states that the integral of the magnetic field intensity's...
364
Equivalent Circuits for Practical Transformers
401
The practical equivalent circuits of single-phase two-winding transformers exhibit significant deviations from their idealized versions due to the inherent properties of winding resistance and finite core permeability. These properties result in real and reactive power losses, affecting the transformer's performance. Understanding these deviations is crucial for designing more efficient transformers.
In a practical transformer, each winding exhibits resistance and leakage reactance. The...
In a practical transformer, each winding exhibits resistance and leakage reactance. The...
401
Visual System
557
Light enters the eye through the cornea, a transparent, dome-shaped surface covering the surface of the eyeball that helps to direct and focus incoming light. This light is then channeled toward the pupil, an adjustable opening whose size is controlled by the iris. The iris, a pigmented muscle, regulates the amount of light entering the eye by contracting or dilating the pupil, thereby ensuring optimal light levels for clear vision.
Once through the pupil, the light passes through the lens, a...
Once through the pupil, the light passes through the lens, a...
557


