Fashion Style in 128 Floats: Joint Ranking and Classification Using Weak Data for Feature Extraction

We propose a novel approach for learning features from weakly-supervised data by joint ranking and classification. In order to exploit data with weak labels, we jointly train a feature extraction network with a ranking loss and a classification network with a cross-entropy loss. We obtain high-quali...

Full description

Saved in:
Bibliographic Details
Published in2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) pp. 298 - 307
Main Authors Simo-Serra, Edgar, Ishikawa, Hiroshi
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.06.2016
Subjects
Computer vision
Feature extraction
Image segmentation
Internet
Noise measurement
Training
Online AccessGet full text

Cover

More Information
Summary:We propose a novel approach for learning features from weakly-supervised data by joint ranking and classification. In order to exploit data with weak labels, we jointly train a feature extraction network with a ranking loss and a classification network with a cross-entropy loss. We obtain high-quality compact discriminative features with few parameters, learned on relatively small datasets without additional annotations. This enables us to tackle tasks with specialized images not very similar to the more generic ones in existing fully-supervised datasets. We show that the resulting features in combination with a linear classifier surpass the state-of-the-art on the Hipster Wars dataset despite using features only 0.3% of the size. Our proposed features significantly outperform those obtained from networks trained on ImageNet, despite being 32 times smaller (128 single-precision floats), trained on noisy and weakly-labeled data, and using only 1.5% of the number of parameters.
ISSN:1063-6919
DOI:10.1109/CVPR.2016.39