竹子:一个新的会话意识框架与等角的紧框架原型为少数镜头的班级增量学习.
IEEE transactions on neural networks and learning systems
|November 10, 2025
概括
我们介绍了Bamboo,这是为少数人群阶级增量学习 (FSCIL) 提供了一个新的框架. 竹子可以在没有事先知识的情况下推断会话ID,从而能够准确地分类所有过去的类别,并获得最先进的结果.
科学领域:
- 机器学习 机器学习
- 计算机视觉 计算机视觉
- 人工智能的人工智能
背景情况:
- 短暂的班级增量学习 (FSCIL) 具有挑战性,因为需要在不知道会话标识符的情况下对所有之前的会议的样本进行分类.
- 现有的方法难以在未知会话中对样本进行分类,这阻碍了动态学习环境中的表现.
研究的目的:
- 提出一个新的框架,竹子,为少数射击类增量学习 (FSCIL),解决会议ID推理的挑战.
- 为了能够准确地分类所有先前学习的类别的样本,而无需事先了解会话标识符.
主要方法:
- 竹子使用一个级联推断机制来明确推断每个输入样本的会话ID.
- 引入了一种新的特定于会话的等角紧框架原型 (ETF-P) 分类器,该分类器可自适应地融合非会话和特定于会话的语义.
- 该框架将增量学习模型作为一连串的会话分类器,类似于竹子生长,每个样本连续穿越以确定其会话.
主要成果:
- 在级联机制中,ETF-P分类器可靠地确定每个样本的正确会话.
- 竹子成功地感知会话ID,而不需要事先的知识,这是有效的FSCIL的关键步骤.
- 拟议的框架在FSCIL任务的多个基准数据集中实现了最先进的性能.
结论:
- 竹子提供了一种强大的解决方案,可以通过有效推断会话ID来进行短暂的类增量学习.
- 级联推断机制和ETF-P分类器可以在动态的,会话意识的学习场景中进行准确的分类.
- 这一框架提升了人工智能系统在处理具有不断变化的类分布的顺序数据方面的能力.
相关概念视频
Frames: Problem Solving I
919
Consider a jib crane with an external load suspended from the pulley. The dimensions of the crane members are shown in the figure. A systematic analysis of the frame structure is required to determine the reaction forces at the pin joints, assuming that the pulleys are frictionless.
919
Frames: Problem Solving II
465
Consider a hydraulic hoist supporting a load of 1 kN. Assuming a simplified schematic representation of this frame structure, the force acting on BD and BF members can be determined.
465
Aggregates Classification
960
Aggregate classification is generally based on its size, petrographic characteristics, weight, and source. Size classification ranges from coarse to fine aggregates, defined by the size of the particles. Coarse aggregates are particles that do not pass through ASTM sieve No. 4, and aggregates that pass through the sieve are fine aggregates.
Petrographic classification groups aggregates based on common mineralogical characteristics. Some of the common mineral groups found in aggregates are...
Petrographic classification groups aggregates based on common mineralogical characteristics. Some of the common mineral groups found in aggregates are...
960
Introduction to Learning
912
Learning is the process of acquiring knowledge or skills through practice or experience, leading to long-lasting behavioral changes. This acquisition occurs through interaction with the environment and requires practice or experience. For instance, mastering a skill such as surfing requires considerable practice and experience, highlighting the essential role of repeated interactions with the environment in learning.
In contrast to learned behaviors, unlearned behaviors such as crying, sexual...
In contrast to learned behaviors, unlearned behaviors such as crying, sexual...
912
Associative Learning
1.2K
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...
1.2K
Observational Learning
804
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...
804
