# BIDETA: Brain-Inspired Data-Efficient Tactile Adaptation for Unseen Sensors

arXiv: https://arxiv.org/abs/2609.08673 · HTML: https://mlsanity.com/paper/2609.08673/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 44 references that are in the map.
- First posted on arXiv 8 Sep 2026.

## Builds on (most cited first, 25 of 25)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances](https://mlsanity.com/paper/1306.0895/) (2013)
- [Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classification](https://mlsanity.com/paper/2207.09519/) (2022)
- [SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learning](https://mlsanity.com/paper/1911.04623/) (2019)
- [DIGIT: A Novel Design for a Low-Cost Compact High-Resolution Tactile Sensor with Application to In-Hand Manipulation](https://mlsanity.com/paper/2005.14679/) (2020)
- [Efficient Test-Time Adaptation of Vision-Language Models](https://mlsanity.com/paper/2403.18293/) (2024)
- [Binding Touch to Everything: Learning Unified Multimodal Tactile Representations](https://mlsanity.com/paper/2401.18084/) (2024)
- [Laplacian Regularized Few-Shot Learning](https://mlsanity.com/paper/2006.15486/) (2020)
- [Touch and Go: Learning from Human-Collected Vision and Touch](https://mlsanity.com/paper/2211.12498/) (2022)
- [Toward Next-Generation Artificial Intelligence: Catalyzing the NeuroAI Revolution](https://mlsanity.com/paper/2210.08340/) (2022)
- [A Touch, Vision, and Language Dataset for Multimodal Alignment](https://mlsanity.com/paper/2402.13232/) (2024)
- [Sparsh: Self-supervised touch representations for vision-based tactile sensing](https://mlsanity.com/paper/2410.24090/) (2024)
- [Attractor and integrator networks in the brain](https://mlsanity.com/paper/2112.03978/) (2021)
- [AnyTouch: Learning Unified Static-Dynamic Representation across Multiple Visuo-tactile Sensors](https://mlsanity.com/paper/2502.12191/) (2025)
- [Transductive Zero-Shot and Few-Shot CLIP](https://mlsanity.com/paper/2405.18437/) (2024)
- [ViT-Lens: Towards Omni-modal Representations](https://mlsanity.com/paper/2311.16081/) (2023)
- [Tactile Beyond Pixels: Multisensory Touch Representations for Robot Manipulation](https://mlsanity.com/paper/2506.14754/) (2025)
- [Sensor-Invariant Tactile Representation](https://mlsanity.com/paper/2502.19638/) (2025)
- [Tactile Robotics: An Outlook](https://mlsanity.com/paper/2508.11261/) (2025)
- [Self-supervised perception for tactile skin covered dexterous hands](https://mlsanity.com/paper/2505.11420/) (2025)
- [Seeing Through Touch: Tactile-Driven Visual Localization of Material Regions](https://mlsanity.com/paper/2604.11579/) (2026)
- [TacVerse: A Multi-Sensor Dataset and Benchmark for Cross-Sensor Vision-Based Tactile Perception](https://mlsanity.com/paper/2606.25877/) (2026)
- [TacEva: A Performance Evaluation Framework For Vision-Based Tactile Sensors](https://mlsanity.com/paper/2509.19037/) (2025)
- [Multimodality as Supervision: Self-Supervised Specialization to the Test Environment via Multimodality](https://mlsanity.com/paper/2607.14721/) (2026)

## Abstract (arXiv)

Vision-based tactile sensors provide high-resolution contact information for robotic perception and contact-rich manipulation, advancing embodied intelligence through more reliable physical interaction. However, device-specific sensing mechanisms cause tactile foundation models to degrade on unfamiliar hardware. Existing cross-sensor methods often require calibration data, paired observations, or iterative training. To address this problem, we propose Brain-Inspired Data-Efficient Tactile Adaptation (BIDETA), a gradient-free framework that uses a frozen tactile encoder and a few labeled target contacts to jointly predict labels for an unlabeled query batch. Inspired by the brain's rapid sensory adaptation, BIDETA combines rapid support memory, support-conditioned spectral graphs, and reliability-gated recurrence to preserve pretrained representations, repair sensor-dependent feature neighborhoods, and integrate reliable cross-query evidence. Experiments on SITR, TacVerse Shape, and TacQuad show that BIDETA substantially improves adaptation to unknown sensors: with only 10% labeled target data on SITR, it raises mean Sparsh accuracy from 6.86% for the frozen source classifier to 87.09%, exceeding the strongest implemented prior comparison by 47.22 percentage points, and these gains generalize across datasets, pretrained backbones, and tactile tasks. In the SITR timing benchmark with TVL, BIDETA also achieves approximately 20x faster target-sensor adaptation than the best baseline. BIDETA thus offers a gradient-free, data-efficient route to deploying tactile models on new hardware.