对视觉变压器进行比较调查,用于纹理分析中的特征提取
Leonardo Scabini1, Andre Sacilotti2, Kallil M Zielinski1
1São Carlos Institute of Physics, University of São Paulo, São Carlos 13560-970, SP, Brazil.
Journal of imaging
|September 26, 2025
概括
视觉转换器 (ViT) 显示出强大的纹理识别潜力,在GPU上的精度和效率方面超过卷积神经网络 (CNN) 和传统方法. BeiTv2-B/16实现了最高的精度.
科学领域:
- 计算机视觉 计算机视觉
- 机器学习 机器学习
- 模式识别 模式识别
背景情况:
- 纹理是图像分析和模式识别中的关键视觉特征.
- 卷积神经网络 (CNN) 是已建立的纹理分析方法.
- 视觉转换器 (ViT) 在更广泛的视觉识别任务中表现有前途.
研究的目的:
- 研究视觉转换器 (ViT) 对于纹理识别的有效性.
- 分析各种ViT架构作为特征提取器的功能和局限性.
- 将ViT的性能与基于CNN和手工设计的方法进行比较.
主要方法:
- 评估了25个ViT变体作为纹理分析的特征提取器.
- 比较ViT,CNN (ResNet50) 和手工工程方法的精度和计算效率.
- 利用野生纹理数据集和强大的预训练策略.
主要成果:
- 在纹理识别准确度方面,ViT通常优于CNN和手工设计模型.
- BeiTv2-B/16获得了最高的平均精度 (85.7%),其次是ViT-B/16-DINO (84.1%) 和Swin-B (80.8%).
- 尽管FLOP/参数较高,但ViT如ViT-B和BeiT(v2) 提供了比ResNet50.2更快的GPU功能提取速度.
结论:
- ViT是一种强大而高效的纹理分析工具,超越了传统方法.
- 强有力的预训练可以提高ViT的性能,尤其是在多样化,现实世界的纹理数据集上.
- 未来的研究应该专注于ViT效率的提高和对纹理识别的特定领域的调整.
相关概念视频
Continuous -time Fourier Transform
831
The Fourier series is instrumental in representing periodic functions, offering a powerful method to decompose such functions into a sum of sinusoids. This technique, however, necessitates modification when applied to nonperiodic functions. Consider a pulse-train waveform consisting of a series of rectangular pulses. When these pulses have a finite period, they can be accurately represented by a Fourier series. Yet, as the period approaches infinity, resulting in a single, isolated pulse, the...
831
Vision
59.4K
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.
59.4K
Visual System
1.7K
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...
1.7K
Depth Perception and Spatial Vision
1.8K
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.
1.8K


