LeanTTA is a backpropagation-free, stateless framework for quantized test-time adaptation designed for edge devices. It updates normalization statistics on the fly, avoiding large batches and historical data, and combines partial adaptation with quantized module fusion to reduce computational costs. Experiments across sensor modalities show a 15.7% error reduction, peak memory usage of only 11.2 MB for ResNet18, and fast adaptation within an order of magnitude of normal inference speeds on-device.
arXiv:2607. 18101v1 Announce Type: new Abstract: On-device model adaptation is essential to enable lifelong personalization on resource-constrained hardware, but compute, power, and memory limitations of such devices make end-to-end backpropagation impractical for modern deep neural networks.
FORGE is a forward‑only test‑time adaptation technique designed for integer‑only vision models running on microcontrollers. It restores batch‑normalization statistics after BN folding by re‑normalizing each convolution’s per‑channel output using only forward‑pass estimates, enabling adaptation on deployed, folded integer models. The method achieves accuracy gains comparable to gradient‑based TENT, requires adapting only a few layers, works with single‑sample streaming, and has been validated on an ESP32‑S3 with minimal energy and latency overhead.
The paper introduces RAMP, a method for robust adaptive mixed‑precision quantization of vision models on edge CPUs. It evaluates 13 sensitivity metrics across four neural networks, finding that Jensen‑Shannon Divergence consistently identifies layers that can be safely quantized. Using K‑Means clustering on these metrics, RAMP achieves near‑lossless accuracy with an average 1.81× speed‑up, while cautioning against excluding low‑speed‑up layers that can fragment the computational graph.
The paper introduces Quantizer‑Aligned Recalibration (QuAR), a single‑pass test‑time adaptation technique for quantized vision transformers that does not require backpropagation or parameter updates. QuAR recalibrates activations at the input of frozen quantizers by aligning per‑channel statistics with the source calibration, thereby correcting the distorted code distribution caused by distribution shift. On ImageNet‑C, QuAR outperforms state‑of‑the‑art backprop‑free methods across 3‑, 4‑, 6‑, and 8‑bit precisions, achieving higher accuracy, lower latency, and minimal memory overhead while maintaining performance across diverse shift scenarios.
Deploying deep learning models on edge CPUs is bottlenecked by computational and memory constraints. Mixed-precision quantization promises to reduce inference latency while preserving accuracy. Howeve...
arXiv:2603.14254v2 Announce Type: replace Abstract: Test-time adaptation (TTA) aims to improve model robustness under distribution shifts by adapting to unlabeled test data, but most existing methods...
The paper presents a rapid pipeline for training and deploying machine‑learning models on the WeBe Band, a wrist‑worn wearable device. It automates the creation of hardware‑efficient models, integrates with the Piccolo AI ecosystem, and supports OTA deployment while profiling latency and memory usage. Experimental results show trade‑offs between classical models and lightweight neural networks for real‑time performance on a microcontroller.
arXiv:2608. 06916v1 Announce Type: new Abstract: Quantized Neural Networks~(QNN) with low-bitwidth data have proven promising in efficient storage and computation on edge devices.
arXiv:2607. 29659v1 Announce Type: new Abstract: Deploying state-of-the-art deep neural networks (DNNs) at the wireless edge is severely bottlenecked by the strict energy and resource constraints of mobile devices.
The paper introduces GQ-FSL, a green quantized federated split learning framework designed for wireless edge networks. It uses stochastic quantization for both local training and wireless transmissions, allowing asymmetric precision between client and server submodels to balance device energy limits with global convergence. The authors develop energy models and a convergence bound for heterogeneous data, then formulate an optimization problem to set the DNN split point and precision levels, achieving lower energy consumption while meeting latency and accuracy targets.
Q-PACE is a dynamic precision allocation method for quantization-aware training that uses a second-order sensitivity model to predict loss increases from quantization noise. By periodically recalculating per-layer curvature coefficients and reassigning precision, it improves mixed-precision training for large language models up to 4 B parameters, achieving comparable loss with lower memory usage. The approach shows that quantization sensitivity is predictable by depth and layer type, enabling infrequent, inexpensive recalibration.
arXiv:2607. 18540v1 Announce Type: cross Abstract: Robotic perception pipelines increasingly rely on large vision backbones deployed on SWaP-constrained edge platforms, making post-training quantization (PTQ) attractive for real-time inference.