RIFLE: Backpropagation in Depth for Deep Transfer Learning through Re-Initializing the Fully-connected LayEr

by   Xingjian Li, et al.

Fine-tuning the deep convolution neural network(CNN) using a pre-trained model helps transfer knowledge learned from larger datasets to the target task. While the accuracy could be largely improved even when the training dataset is small, the transfer learning outcome is usually constrained by the pre-trained model with close CNN weights (Liu et al., 2019), as the backpropagation here brings smaller updates to deeper CNN layers. In this work, we propose RIFLE - a simple yet effective strategy that deepens backpropagation in transfer learning settings, through periodically Re-Initializing the Fully-connected LayEr with random scratch during the fine-tuning procedure. RIFLE brings meaningful updates to the weights of deep CNN layers and improves low-level feature learning, while the effects of randomization can be easily converged throughout the overall learning procedure. The experiments show that the use of RIFLE significantly improves deep transfer learning accuracy on a wide range of datasets, out-performing known tricks for the similar purpose, such as Dropout, DropConnect, StochasticDepth, Disturb Label and Cyclic Learning Rate, under the same settings with 0.5 ablation studies further indicate RIFLE brings meaningful updates to deep CNN layers with accuracy improved.



There are no comments yet.


page 1

page 2

page 3

page 4


CARTL: Cooperative Adversarially-Robust Transfer Learning

Transfer learning eases the burden of training a well-performed model fr...

SMILE: Self-Distilled MIxup for Efficient Transfer LEarning

To improve the performance of deep learning, mixup has been proposed to ...

Deep Transfer Learning for WiFi Localization

This paper studies a WiFi indoor localisation technique based on using a...

Backbone Can Not be Trained at Once: Rolling Back to Pre-trained Network for Person Re-Identification

In person re-identification (ReID) task, because of its shortage of trai...

AutoFCL: Automatically Tuning Fully Connected Layers for Transfer Learning

Deep Convolutional Neural Networks (CNN) have evolved as popular machine...

A Comprehensive Study on Torchvision Pre-trained Models for Fine-grained Inter-species Classification

This study aims to explore different pre-trained models offered in the T...

NetTailor: Tuning the Architecture, Not Just the Weights

Real-world applications of object recognition often require the solution...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.