Cardiff University | Prifysgol Caerdydd ORCA
Online Research @ Cardiff 
WelshClear Cookie - decide language by browser settings

Recognition from web data: A progressive filtering approach

Yang, Jufeng, Sun, Xiaoxiao, Lai, Yukun, Zheng, Liang and Cheng, Ming-Ming 2018. Recognition from web data: A progressive filtering approach. IEEE Transactions on Image Processing 27 (11) , pp. 5303-5315. 10.1109/TIP.2018.2855449

[img]
Preview
PDF - Accepted Post-Print Version
Download (4MB) | Preview

Abstract

Leveraging the abundant number of web data is a promising strategy in addressing the problem of data lacking when training convolutional neural networks (CNNs). However, web images often contain incorrect tags, which may compromise the learned CNN model. To address this problem, this paper focuses on image classification and proposes to iterate between filtering out noisy web labels and fine-tuning the CNN model using the crawled web images. Overall, the proposed method benefits from the growing modeling capability of the learned model to correct labels for web images and learning from such new data to produce a more effective model. Our contribution is two-fold. First, we propose an iterative method that progressively improves the discriminative ability of CNNs and the accuracy of web image selection. This method is beneficial towards selecting high-quality web training images and expanding the training set as the model gets ameliorated. Second, since web images are usually complex and may not be accurately described by a single tag, we propose to assign a web image multiple labels to reduce the impact of hard label assignment. This labeling strategy mines more training samples to improve the CNN model. In the experiments, we crawl 0.5 million web images covering all categories of four public image classification datasets. Compared with the baseline which has no web images for training, we show that the proposed method brings notable improvement. We also report competitive recognition accuracy compared with the state of the art.

Item Type: Article
Date Type: Publication
Status: Published
Schools: Computer Science & Informatics
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
ISSN: 1057-7149
Date of First Compliant Deposit: 30 June 2018
Date of Acceptance: 18 June 2018
Last Modified: 28 Jun 2019 16:49
URI: http://orca-mwe.cf.ac.uk/id/eprint/112900

Citation Data

Cited 2 times in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item Edit Item

Downloads

Downloads per month over past year

View more statistics