When Sensing Varies with Contexts: Context-as-Transform for Tactile Few-Shot Class-Incremental Learning
This addresses a domain-specific issue in tactile sensing for robotics or human-computer interaction, with incremental improvements in handling context variations.
The paper tackles the problem of tactile sensing performance degradation in Few-Shot Class-Incremental Learning due to varying acquisition contexts, achieving state-of-the-art results on benchmarks like HapTex and LMT108.
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.