我们真的需要大量的视觉提示吗?
Youngeun Kim1, Yuhang Li1, Abhishek Moitra1
1Department of Electrical Engineering, Yale University, New Haven, CT, USA.
概括
可使视觉提示调整 (VPT) 更高效. 这项研究引入了快速凝结 (PC),以减少70%的提示,而不会失去视觉变压器的准确性.
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:
- 参数效率转移学习对于在资源受限的边缘设备上调整模型至关重要.
- 视觉提示调整 (VPT) 通过预先学习提示提供竞争性性能,但由于更多的输入令牌,增加了计算开销.
研究的目的:
- 分析提示量对视觉变压器微调性能和自我注意力机制的影响.
- 开发一种方法来减少快速使用,同时保持准确性.
主要方法:
- 提示数字对视觉变压器性能影响的理论和经验分析.
- 关于快速凝结 (PC) 技术的建议,以减少使用更少的提示来减轻性能损失.
主要成果:
- 提示的增加不会产生线性改进的微调性能.
- 提出的快速凝结 (PC) 技术有效地将FGVC和VTAB-1k任务的快速凝结数量减少了约70%.
- 尽管迅速使用的时间大大减少,但准确性仍然保持不变.
结论:
- 优化提示量对于高效的参数效率转移学习至关重要.
- 提示缩 (PC) 提供了一种可行的解决方案,可以在不影响模型准确性的情况下减少视觉提示调整 (VPT) 中的计算开销.
相关概念视频
Vision
48.6K
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.
48.6K
Accessory Structures of the Eye
4.3K
Optical perception, or vision, is an extraordinary sense dependent on converting light signals received via the ocular organs. These organs, known as eyes, are securely positioned within the bony cavities of the skull, called orbits. The orbits serve a dual purpose: a protective shield for the ocular globes and a stable attachment point for the soft ocular tissues. The eye's external protective mechanisms include the eyelids, which are edged with lashes that act as a barrier against foreign...
4.3K
Photoreceptors and Visual Pathways
8.5K
At the molecular level, visual signals trigger transformations in photopigment molecules, resulting in changes in the photoreceptor cell's membrane potential. The photon's energy level is denoted by its wavelength, with each specific wavelength of visible light associated with a distinct color. The spectral range of visible light, classified as electromagnetic radiation, spans from 380 to 720 nm. Electromagnetic radiation wavelengths exceeding 720 nm fall under the infrared category,...
8.5K
Depth Perception and Spatial Vision
2.7K
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.
2.7K
Visual System
2.3K
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...
2.3K
Non-Verbal Cues
774
Non-verbal communication extends beyond gestures and facial expressions to include vocal elements known as paralanguage. Paralanguage consists of non-verbal vocal cues such as pitch, loudness, speech rate, pauses, and non-verbal vocalizations like laughter, sighs, and moans. These elements not only accompany speech but also provide critical emotional and contextual information.The Role of Paralanguage in CommunicationParalanguage adds depth to spoken language by conveying emotions and...
774


