DeepAI AI Chat
Log In Sign Up

Learning More Universal Representations for Transfer-Learning

by   Youssef Tamaazousti, et al.

Transfer learning is commonly used to address the problem of the prohibitive need in annotated data when one want to classify visual content with a Convolutional Neural Network (CNN). We address the problem of the universality of the CNN-based representation of images in such a context. The state-of-the-art consists in diversifying the source problem on which the CNN is learned. It reduces the cost for the target problem but still requires a large amount of efforts to satisfy the source problem needs in annotated data. We propose an unified framework of the methods that improve the universality by diversifying the source problem. We also propose two methods that improve the universality but pay special attention to limit the need of annotated data. Finally, we propose a new evaluation protocol to compare the ability of CNN-based representation to tackle the problem of universality. It demonstrates the interest of our work on 10 publicly available benchmarks, relating to a variety of visual classification problems.


page 1

page 4

page 10

page 14


Learning Finer-class Networks for Universal Representations

Many real-world visual recognition use-cases can not directly benefit fr...

Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles

In this paper we study the problem of image representation learning with...

Target Aware Network Architecture Search and Compression for Efficient Knowledge Transfer

Transfer Learning enables Convolutional Neural Networks (CNN) to acquire...

CNN-based Survival Model for Pancreatic Ductal Adenocarcinoma in Medical Imaging

Cox proportional hazard model (CPH) is commonly used in clinical researc...

Return of the Devil in the Details: Delving Deep into Convolutional Nets

The latest generation of Convolutional Neural Networks (CNN) have achiev...

Scalable Full Flow with Learned Binary Descriptors

We propose a method for large displacement optical flow in which local m...