arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2603.25115cs.AI
收藏

当感知随情境变化时:情境作为变换的触觉少样本类增量学习

When Sensing Varies with Contexts: Context Probing for Tactile Few-Shot Class-Incremental Learning

Fujian Key Laboratory for Intelligent Processing and Wireless Transmission of Media Information, College of Physics and Information Engineering, Fuzhou University(福建省媒体信息智能处理与无线传输重点实验室,物理与信息工程学院,福州大学);College of Computer and Data Science, Fuzhou University(计算机与数据科学学院,福州大学);School of Computer Science and Engineering, South China University of Technology(计算机科学与工程学院,华南理工大学);MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition, University of Science and Technology of China(教育部类脑智能感知与认知重点实验室,中国科学技术大学)

Yifeng Lin, Aiping Huang, Wenxi Liu, Si Wu, Tiesong Zhao, Zechao Li, Zheng-Jun Zha

AI总结:

本文提出CaT-FSCIL方法,通过分解触觉感知情境为低维结构成分和高维残差成分,利用伪情境一致性损失和UCPC缓解设备差异影响,在HapTex和LMT108上验证了其优越性。

摘要:

少样本类增量学习(FSCIL)尤其容易受到仅少量标记样本的获取情境影响。典型场景是触觉感知,其中获取情境(例如,多样设备、接触状态和交互设置)由于缺乏标准化而降低性能。本文提出Context-as-Transform FSCIL(CaT-FSCIL)以解决上述问题。我们将获取情境分解为一个结构化的低维成分和一个高维残差成分。前者容易受触觉交互特征影响,将其建模为近可逆的Context-as-Transform家族,并通过逆变换规范优化,利用伪情境一致性损失进行处理。后者主要源于平台和设备差异,可通过Uncertainty-Conditioned Prototype Calibration(UCPC)缓解,该方法基于情境不确定性校准偏差的原型和决策边界。在标准基准HapTex和LMT108上的全面实验表明,所提出的CaT-FSCIL具有优越性。

英文摘要:

Few-shot class-incremental learning (FSCIL) aims to recognize novel classes from only a few labeled samples while retaining previously learned knowledge. Although recent FSCIL methods have achieved substantial progress on visual benchmarks, they remain limited in tactile sensing, where the same material may produce markedly different observations under different acquisition contexts, such as sensing devices, contact states, scanning trajectories, and interaction conditions. In tactile FSCIL, the challenges of few-shot learning and class-incremental learning are further amplified by acquisition context: the limited support samples may not only be scarce, but also carry context-induced biases. Once the resulting biased prototypes are inserted into the classifier, they may affect the decision boundaries in subsequent sessions. To address this problem, we propose Context-Probing Few-Shot Class-Incremental Learning (CoP-FSCIL), a context-aware framework for tactile FSCIL. CoP-FSCIL first employs Context-Probing Intervention (CPI) to diagnose local context-sensitive variations in tactile representations. It then introduces a Probe-Conditioned Quotient Adapter (PCQA) to suppress context-sensitive components identified by the probes. Finally, Probe-Stability Prototype Calibration (PSPC) estimates support sample reliability from probe-induced embedding fluctuations and calibrates stochastic prototypes accordingly. Experiments on HapTex and LMT108 show that CoP-FSCIL consistently outperforms representative FSCIL baselines, and extended experiments on audio FSCIL further demonstrate the generality of the proposed context probing mechanism. The source code is currently being prepared and will be released soon.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑