# EmbodiTTA: Resource-Efficient Test-Time Adaptation for Embodied Visual Systems

arXiv: https://arxiv.org/abs/2505.00986 · HTML: https://mlsanity.com/paper/2505.00986/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 42 references that are in the map.
- First posted on arXiv 2 May 2025.

## Builds on (most cited first, 28 of 28)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [Do ImageNet Classifiers Generalize to ImageNet?](https://mlsanity.com/paper/1902.10811/) (2019)
- [Generalizing to Unseen Domains: A Survey on Domain Generalization](https://mlsanity.com/paper/2103.03097/) (2021)
- [MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer](https://mlsanity.com/paper/2110.02178/) (2021)
- [Continual Test-Time Domain Adaptation](https://mlsanity.com/paper/2203.13591/) (2022)
- [Efficient Test-Time Model Adaptation without Forgetting](https://mlsanity.com/paper/2204.02610/) (2022)
- [Towards Stable Test-Time Adaptation in Dynamic Wild World](https://mlsanity.com/paper/2302.12400/) (2023)
- [A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts](https://mlsanity.com/paper/2303.15361/) (2023)
- [CORe50: a New Dataset and Benchmark for Continuous Object Recognition](https://mlsanity.com/paper/1705.03550/) (2017)
- [Generalisation in humans and deep neural networks](https://mlsanity.com/paper/1808.08750/) (2018)
- [The EPIC-KITCHENS Dataset: Collection, Challenges and Baselines](https://mlsanity.com/paper/2005.00343/) (2020)
- [Where are we in the search for an Artificial Visual Cortex for Embodied Intelligence?](https://mlsanity.com/paper/2303.18240/) (2023)
- [SHIFT: A Synthetic Driving Dataset for Continuous Multi-Task Domain Adaptation](https://mlsanity.com/paper/2206.08367/) (2022)
- [Universal Test-time Adaptation through Weight Ensembling, Diversity Weighting, and Prior Correction](https://mlsanity.com/paper/2306.00650/) (2023)
- [SoTTA: Robust Test-Time Adaptation on Noisy Data Streams](https://mlsanity.com/paper/2310.10074/) (2023)
- [Beyond Model Adaptation at Test Time: A Survey](https://mlsanity.com/paper/2411.03687/) (2024)
- [Revisiting Batch Normalization for Improving Corruption Robustness](https://mlsanity.com/paper/2010.03630/) (2020)
- [In Search of Lost Online Test-time Adaptation: A Survey](https://mlsanity.com/paper/2310.20199/) (2023)
- [Addressing Appearance Change in Outdoor Robotics with Adversarial Domain Adaptation](https://mlsanity.com/paper/1703.01461/) (2017)
- [Artificial Intelligence for Long-Term Robot Autonomy: A Survey](https://mlsanity.com/paper/1807.05196/) (2018)
- [Uncertainty-Calibrated Test-Time Model Adaptation without Forgetting](https://mlsanity.com/paper/2403.11491/) (2024)
- [Effective Restoration of Source Knowledge in Continual Test Time Adaptation](https://mlsanity.com/paper/2311.04991/) (2023)
- [SURGEON: Memory-Adaptive Fully Test-Time Adaptation via Dynamic Activation Sparsity](https://mlsanity.com/paper/2503.20354/) (2025)
- [Online Distribution Shift Detection via Recency Prediction](https://mlsanity.com/paper/2211.09916/) (2022)
- [Window-Based Distribution Shift Detection for Deep Neural Networks](https://mlsanity.com/paper/2210.10897/) (2022)

## Built on by (most cited first, 1 of 1)

- [When to Adapt: Multi-Signal Domain Shift Detection for Efficient Training-Free Adaptation in Open-Vocabulary Segmentation](https://mlsanity.com/paper/2609.37602/) (2026)

## Abstract (arXiv)

Continual Test-time adaptation (CTTA) continuously adapts the deployed model on every incoming batch of data. While achieving optimal accuracy, existing CTTA approaches present poor real-world applicability on resource-constrained edge devices, due to the substantial memory overhead and energy consumption. In this work, we first introduce a novel paradigm -- on-demand TTA -- which triggers adaptation only when a significant domain shift is detected. Then, we present OD-TTA, an on-demand TTA framework for accurate and efficient adaptation on edge devices. OD-TTA comprises three innovative techniques: 1) a lightweight domain shift detection mechanism to activate TTA only when it is needed, drastically reducing the overall computation overhead, 2) a source domain selection module that chooses an appropriate source model for adaptation, ensuring high and robust accuracy, 3) a decoupled Batch Normalization (BN) update scheme to enable memory-efficient adaptation with small batch sizes. Extensive experiments show that OD-TTA achieves comparable and even better performance while reducing the energy and computation overhead remarkably, making TTA a practical reality.