Adaptive Test-Time Augmentation for Low-Power CPU

by   Luca Mocerino, et al.

Convolutional Neural Networks (ConvNets) are trained offline using the few available data and may therefore suffer from substantial accuracy loss when ported on the field, where unseen input patterns received under unpredictable external conditions can mislead the model. Test-Time Augmentation (TTA) techniques aim to alleviate such common side effect at inference-time, first running multiple feed-forward passes on a set of altered versions of the same input sample, and then computing the main outcome through a consensus of the aggregated predictions. Unfortunately, the implementation of TTA on embedded CPUs introduces latency penalties that limit its adoption on edge applications. To tackle this issue, we propose AdapTTA, an adaptive implementation of TTA that controls the number of feed-forward passes dynamically, depending on the complexity of the input. Experimental results on state-of-the-art ConvNets for image classification deployed on a commercial ARM Cortex-A CPU demonstrate AdapTTA reaches remarkable latency savings, from 1.49X to 2.21X, and hence a higher frame rate compared to static TTA, still preserving the same accuracy gain.


page 1

page 2

page 3

page 4


When and Why Test-Time Augmentation Works

Test-time augmentation (TTA)—the aggregation of predictions across trans...

Neuro-Modulated Hebbian Learning for Fully Test-Time Adaptation

Fully test-time adaptation aims to adapt the network model based on sequ...

Improved Text Classification via Test-Time Augmentation

Test-time augmentation – the aggregation of predictions across transform...

SC-wLS: Towards Interpretable Feed-forward Camera Re-localization

Visual re-localization aims to recover camera poses in a known environme...

Learning to infer: RL-based search for DNN primitive selection on Heterogeneous Embedded Systems

Deep Learning is increasingly being adopted by industry for computer vis...

Please sign up or login with your details

Forgot password? Click here to reset