Filter-Invariant Image Classification on Social Media Photos by Using Siamese Network
Date Issued
2015
Date
2015
Author(s)
Chen, Yu-Hsiu
Abstract
With the popularity of social media nowadays, tons of photos are uploaded everyday. To understand the image content, image classification becomes a very essential technique for plenty of applications (e.g., object detection, image caption generation). Convolutional Neural Network (CNN) has been shown as the state-of-the-art approach for image classification. However, one of the characteristics in social media photos is that they are often applied with photo filters, especially on Instagram. We find that prior works do not aware of this trend in social media photos and fail on filtered images. Thus, we propose a novel CNN architecture that utilizes the power of pairwise constraint by combining Siamese network and the proposed adaptive margin contrastive loss with our discriminative pair sampling method to solve the problem of filter bias. To the best of our knowledge, this is the first work to tackle filter bias on CNN and achieve state-of-the-art performance on a filtered subset of ILSVRC2012.
Subjects
Deep learning
Convolutional Neural Network
Image Classificaiton
Type
thesis
File(s)![Thumbnail Image]()
Loading...
Name
ntu-104-R02922130-1.pdf
Size
23.32 KB
Format
Adobe PDF
Checksum
(MD5):0117a0f279c7862ec834948049b9a5f3