完全自主监督的域外短暂学习,使用面具自动编码器
Reece Walsh1, Islam Osman1, Omar Abdelaziz1
1Irving K. Barber Faculty of Science, University of British Columbia, Kelowna, BC V1V 1V7, Canada.
Journal of imaging
|January 22, 2024
概括
本研究介绍了一种完全自主监督的使用视觉变压器的短时间学习 (FSS) 方法. 在没有监督培训的情况下,FSS提高了对域外数据的概括性,提高了几次拍摄的学习性能.
科学领域:
- 计算机科学 计算机科学
- 人工智能的人工智能
- 机器学习 机器学习
背景情况:
- 短暂学习 (FSL) 旨在使用最小的标记数据对新类别进行分类.
- 现有的FSL方法难以进行域外概括,通常依赖于受监督的微调.
- 这种依赖限制了适应能力,增加了数据需求.
研究的目的:
- 提出一种全新的,完全自主监督的少数射击学习 (FSS) 技术.
- 增强FSL模型的概括能力,特别是在域外场景中.
- 为了减少对FSL任务的监督微调的依赖.
主要方法:
- 开发了一种完全自主监督的几次射击学习技术 (FSS).
- 使用视觉变压器架构与面具自动编码器相结合.
- 采用情节智能,完全自我监督的微调,用于域外概括.
主要成果:
- 在域外数据集上实现了1.05% (ISIC),0.12% (EuroSat) 和1.28% (BCCD) 的精度增长.
- 在没有任何监督培训的情况下,证明了有效的概括.
- 在三个不同的数据集中验证了FSS技术.
结论:
- 拟议的FSS技术成功地对未见的域外类进行了概括.
- 完全自我监督的微调提供了一个可行的替代FSL监督方法.
- 对于强大且可适应的少量学习系统来说,FSS是一个有前途的方向.
相关概念视频
Masking and Demasking Agents
2.4K
EDTA titrations may necessitate masking and demasking agents to temporarily protect a particular metal ion in a mixture from the EDTA reaction. These agents facilitate the sequential analysis of the metal ions by forming stable complexes with some—but not all—metal ions during certain steps.
There are many masking agents, such as cyanide, fluoride, triethanolamine, thiourea, and 2,3-bis(sulfanyl)propan-1-ol (formerly 2,3-dimercapto-1-propanol), with the masking agent chosen based on...
There are many masking agents, such as cyanide, fluoride, triethanolamine, thiourea, and 2,3-bis(sulfanyl)propan-1-ol (formerly 2,3-dimercapto-1-propanol), with the masking agent chosen based on...
2.4K
Associative Learning
375
Associative learning is a fundamental concept in behavioral psychology, wherein a connection is established between two stimuli or events, leading to a learned response. This process is critical in understanding how behaviors are acquired and modified. Conditioning, the mechanism through which associations are formed, can be divided into two main types: classical conditioning and operant conditioning, each elucidating different aspects of associative learning.
Classical conditioning, also known...
Classical conditioning, also known...
375
Force Classification
1.2K
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,...
1.2K
Generalization, Discrimination, and Extinction
563
Generalization, discrimination, and extinction are key concepts in operant conditioning that influence how behaviors are learned and maintained.
Generalization occurs when a behavior reinforced in one context is performed in similar situations. For instance, a student who studies diligently for calculus and receives excellent grades might apply the same study habits to psychology and history, expecting similar results. Generalization shows how learning in one setting can influence behavior in...
Generalization occurs when a behavior reinforced in one context is performed in similar situations. For instance, a student who studies diligently for calculus and receives excellent grades might apply the same study habits to psychology and history, expecting similar results. Generalization shows how learning in one setting can influence behavior in...
563
Nonconscious Mimicry
4.6K
Nonconscious mimicry occurs when individuals alter their mannerisms to match the behaviors and expressions of those nearby, without intention.
4.6K
Deconvolution
160
Deconvolution, also known as inverse filtering, is the process of extracting the impulse response from known input and output signals. This technique is vital in scenarios where the system's characteristics are unknown, and they must be inferred from the observable signals.
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...
160


