arXiv:2507. 15958v5 Announce Type: replace-cross Abstract: On-device skin lesion analysis is constrained by the compute and energy cost of conventional CNN inference and by the need for lightweight calibration under clinical data shift.
arXiv:2607. 16296v1 Announce Type: cross Abstract: Continuous EEG monitoring for epilepsy is constrained by the limited power and memory budgets of wearable and implantable devices.
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...
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.
Modern deep neural networks achieve strong performance, but their scale makes them costly and slow, especially on resource-constrained edge devices. Pruning and quantization address this, but rely on manual, expert choices and on algorithms that are hard to apply across architectures.
arXiv:2608. 07066v1 Announce Type: new Abstract: Spiking neural networks (SNNs) enable sparse and event-driven computation, but their low-bit deployment remains incomplete because recurrent membrane states are commonly retained in floating point even after weight quantization.
arXiv:2609.28358v1 Announce Type: cross Abstract: Microscaling quantization techniques are increasingly used to represent neural network parameters with 8 bits or fewer while preserving near-full pre...
The paper introduces an uncertainty‑driven training framework for 3D CT lung nodule classification that uses validation‑based uncertainty estimates to reweight the loss, aiming to improve predictive performance and probability calibration. Two uncertainty quantification methods—Monte Carlo Dropout and Evidential Deep Learning—are evaluated across multiple backbone architectures (ResNet, DenseNet, EfficientNet, ViT, Swin) on the LIDC‑IDRI and NoduleMNIST3D datasets. The approach yields comparable classification accuracy to conventional training while substantially reducing expected calibration error, especially on convolutional backbones, and shows that simple temperature scaling can also achieve strong calibration.
arXiv:2608. 05499v1 Announce Type: cross Abstract: Modern deep neural networks achieve strong performance, but their scale makes them costly and slow, especially on resource-constrained edge devices.
The paper introduces the Quantization Analysis Tool, a system built on the ONNX framework that streamlines quantization workflows for deep learning models. It offers layer‑wise sensitivity analysis, visualizations of weight and activation distributions, and guidance for selecting precision levels to balance model size, latency, and accuracy. Experiments on various neural network architectures show that the tool improves quantized accuracy and overall deployment efficiency.
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.
arXiv:2506.11784v2 Announce Type: replace Abstract: Vision Transformers (ViTs) are essential in computer vision but are computationally intensive, too. Model quantization, particularly to low bit-wid...
arXiv:2509. 10334v2 Announce Type: replace-cross Abstract: Vision Transformers (ViTs) have recently achieved strong results in semantic segmentation, yet their deployment on resource-constrained devices remains limited due to their high memory footprint and computational cost.