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

TL;DR

This paper introduces CaT-FSCIL, a novel method for tactile few-shot class-incremental learning that models and mitigates context variations through a structured transform approach and prototype calibration, improving performance on standard benchmarks.

Contribution

It proposes a new framework that decomposes context into components and applies inverse-transform canonicalization and uncertainty-conditioned calibration to enhance FSCIL in tactile sensing.

Findings

Outperforms existing methods on HapTex and LMT108 benchmarks.

Effectively handles diverse tactile acquisition contexts.

Improves robustness against device and platform variations.

Abstract

Few-Shot Class-Incremental Learning (FSCIL) can be particularly susceptible to acquisition contexts with only a few labeled samples. A typical scenario is tactile sensing, where the acquisition context ({\it e.g.}, diverse devices, contact state, and interaction settings) degrades performance due to a lack of standardization. In this paper, we propose Context-as-Transform FSCIL (CaT-FSCIL) to tackle the above problem. We decompose the acquisition context into a structured low-dimensional component and a high-dimensional residual component. The former can be easily affected by tactile interaction features, which are modeled as an approximately invertible Context-as-Transform family and handled via inverse-transform canonicalization optimized with a pseudo-context consistency loss. The latter mainly arises from platform and device differences, which can be mitigated with an Uncertainty-Conditioned Prototype Calibration (UCPC) that calibrates biased prototypes and decision boundaries based on context uncertainty. Comprehensive experiments on the standard benchmarks HapTex and LMT108 have demonstrated the superiority of the proposed CaT-FSCIL.