Partial Weight Adaptation for Robust DNN Inference

by   Xiufeng Xie, et al.
Hewlett Packard Enterprise

Mainstream video analytics uses a pre-trained DNN model with an assumption that inference input and training data follow the same probability distribution. However, this assumption does not always hold in the wild: autonomous vehicles may capture video with varying brightness; unstable wireless bandwidth calls for adaptive bitrate streaming of video; and, inference servers may serve inputs from heterogeneous IoT devices/cameras. In such situations, the level of input distortion changes rapidly, thus reshaping the probability distribution of the input. We present GearNN, an adaptive inference architecture that accommodates heterogeneous DNN inputs. GearNN employs an optimization algorithm to identify a small set of "distortion-sensitive" DNN parameters, given a memory budget. Based on the distortion level of the input, GearNN then adapts only the distortion-sensitive parameters, while reusing the rest of constant parameters across all input qualities. In our evaluation of DNN inference with dynamic input distortions, GearNN improves the accuracy (mIoU) by an average of 18.12 over a DNN trained with the undistorted dataset and 4.84 training from Google, with only 1.8


page 4

page 5


Adaptive Selection of Deep Learning Models on Embedded Systems

The recent ground-breaking advances in deep learning networks ( DNNs ) m...

Enabling Inference Privacy with Adaptive Noise Injection

User-facing software services are becoming increasingly reliant on remot...

RL-DistPrivacy: Privacy-Aware Distributed Deep Inference for low latency IoT systems

Although Deep Neural Networks (DNN) have become the backbone technology ...

Towards Characterizing and Limiting Information Exposure in DNN Layers

Pre-trained Deep Neural Network (DNN) models are increasingly used in sm...

SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size

Recent research on deep neural networks has focused primarily on improvi...

A Serverless Cloud-Fog Platform for DNN-Based Video Analytics with Incremental Learning

DNN-based video analytics have empowered many new applications (e.g., au...

MIMO Detection under Hardware Impairments: Learning with Noisy Labels

This paper considers a data detection problem in multiple-input multiple...

Please sign up or login with your details

Forgot password? Click here to reset