Learning Grouped Convolution for Efficient Domain Adaptation

11/23/2018
by   Ruizhe Zhao, et al.
0

This paper presents Dokei, an effective supervised domain adaptation method to transform a pre-trained CNN model to one involving efficient grouped convolution. The basis of this approach is formalised as a novel optimisation problem constrained by group sparsity pattern (GSP), and a practical solution based on structured regularisation and maximal bipartite matching is provided. We show that it is vital to keep the connections specified by GSP when mapping pre-trained weights to grouped convolution. We evaluate Dokei on various domains and hardware platforms to demonstrate its effectiveness. The models resulting from Dokei are shown to be more accurate and slimmer than prior work targeting grouped convolution, and more regular and easier to deploy than other pruning techniques.

READ FULL TEXT

page 3

page 5

page 6

research
09/04/2018

Towards Efficient Convolutional Neural Network for Domain-Specific Applications on FPGA

FPGA becomes a popular technology for implementing Convolutional Neural ...
research
07/20/2023

Feed-Forward Source-Free Domain Adaptation via Class Prototypes

Source-free domain adaptation has become popular because of its practica...
research
08/05/2021

Visual Domain Adaptation for Monocular Depth Estimation on Resource-Constrained Hardware

Real-world perception systems in many cases build on hardware with limit...
research
03/26/2023

Δ-Networks for Efficient Model Patching

Models pre-trained on large-scale datasets are often finetuned to suppor...
research
03/31/2022

PADA: Pruning Assisted Domain Adaptation for Self-Supervised Speech Representations

While self-supervised speech representation learning (SSL) models serve ...

Please sign up or login with your details

Forgot password? Click here to reset