相反的蒙面自动编码器是更强的视觉学习者
IEEE transactions on pattern analysis and machine intelligence
|November 28, 2023
概括
对比的蒙面自动编码器 (CMAE) 增强了计算机视觉的自我监督学习. 这种方法统一了对比学习和蒙面图像建模,以创建更有能力的视觉表示,提高各种任务的性能.
科学领域:
- 计算机视觉 计算机视觉
- 机器学习 机器学习
- 人工智能的人工智能
背景情况:
- 蒙面图像建模 (MIM) 在视觉任务中显示出希望,但在表示可区分性方面存在局限性.
- 现有的方法需要进一步改进,以培养更强的视觉学习者.
研究的目的:
- 引入对比面具自动编码器 (CMAE),一种新的自我监督预训方法.
- 通过结合对比学习 (CL) 和MIM,学习更全面,更有能力的视觉表示.
主要方法:
- CMAE采用一个不对称的编码器解码器 (在线分支) 和一个动量更新的编码器 (动量分支).
- 在线编码器重建蒙面图像,而动量编码器通过对比学习增强功能可辨别性,使用完整图像.
- 新的组件包括像素转移用于正视图生成和功能解码器用于对比对的功能补充.
主要成果:
- 与标准MIM方法相比,CMAE显著提高了表示质量和转移性能.
- 在图像分类,语义细分和对象检测基准方面取得了最先进的结果.
- 在ImageNet上,CMAE-Base达到了85.3%的top-1准确度,在ADE20k上达到了52.5%的mIoU,超过了之前的最佳.
结论:
- CMAE有效地统一了CL和MIM,利用它们的优势实现了高级视觉表示学习.
- 拟议的方法证明了增强的实例可区分性和本地可感知性.
- CMAE制定了新的绩效基准,突出了其在推进计算机视觉方面的潜力.
相关概念视频
01:12Observational Learning
182
Albert Bandura's observational learning, also known as imitation or modeling, occurs when a person observes and imitates another's behavior. It is a quicker process than operant conditioning. A well-known example is the Bobo doll study, where children who saw an adult acting aggressively towards the doll were more likely to act aggressively when left alone, compared to those who observed a nonaggressive adult. Many psychologists view observational learning as a form of latent learning...
182
01:19Masking 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
01:24Vision
53.5K
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.
53.5K
01:27Associative Learning
404
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...
404
01:13Nonconscious Mimicry
4.6K
Nonconscious mimicry occurs when individuals alter their mannerisms to match the behaviors and expressions of those nearby, without intention.
4.6K
01:24Facial Feedback Hypothesis
165
Charles Darwin proposed that facial expressions are an evolutionary adaptation for communication. He argued that these expressions are not influenced by culture but are universal across species. For example, a snarling expression with exposed teeth signals a threat in many animals, including humans. Darwin also suggested that displaying an emotion can intensify the feeling. Smiling, for example, could enhance one's sense of happiness. This idea laid the foundation for understanding the role...
165