aiqbench analysis
This research introduces OD-TTA, a resource-efficient framework for embodied visual systems that adapts models only when necessary to reduce energy and memory overhead on edge devices. By combining lightweight domain shift detection with decoupled Batch Normalization updates, the approach achieves robust accuracy while significantly lowering computational costs compared to continuous adaptation methods. These innovations address critical deployment challenges in real-world scenarios where power and storage are constrained.
EmbodiTTA: Resource-Efficient Test-Time Adaptation for Embodied Visual Systems
arXiv:2505.00986v3 Announce Type: replace Abstract: 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.
Abstract: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.
Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV)
arXiv:2505.00986 [cs.LG]
(or arXiv:2505.00986v3 [cs.LG] for this version)
Full text under the publisher's open licence · 181 words
Related coverage
EmbodiTTA: Resource-Efficient Test-Time Adaptation for Embodied Visual Systems
arXiv · Oct 12, 2026
Amazon Research Awards recipients announced
Amazon Science · May 27, 2026
Build a Physical AI model factory with NVIDIA Cosmos 3 on SageMaker HyperPod
AWS · Sep 4, 2026
Humanity’s Last Invention — Richard Socher of Recursive
Latent Space · Sep 14, 2026