From the March 2014 issue
Good Practice in Large-Scale Learning for Image Classification
By Zeynep Akata, Florent Perronnin, Zaid Harchaoui, Cordelia Schmid
We benchmark several SVM objective functions for large-scale image classification. We consider one-versus-rest, multiclass, ranking, and weighted approximate ranking SVMs. A comparison of online and batch methods for optimizing the objectives shows that online methods perform as well as batch methods in terms of classification accuracy, but with a significant gain in training speed. Using stochastic gradient descent, we can scale the training to millions of images and thousands of classes. Our experimental evaluation shows that ranking-based algorithms do not outperform the one-versus-rest strategy when a large number of training examples are used. Furthermore, the gap in accuracy between the different algorithms shrinks as the dimension of the features increases. We also show that learning through cross-validation the optimal rebalancing of positive and negative examples can result in a significant improvement for the one-versus-rest strategy. Finally, early stopping can be used as an effective regularization strategy when training with online algorithms. Following these "good practices," we were able to improve the state of the art on a large subset of 10K classes and 9M images of ImageNet from 16.7 percent Top-1 accuracy to 19.1 percent.
Editorials and Announcements
- Get Your Journals as eBooks for Free
- We are pleased to announce that David Forsyth, a professor at the University of Illinois at Urbana-Champaign, is the new Editor in Chief of IEEE Transactions on Pattern and Machine Intelligence starting in 2013. He was previously a member of the advisory board of TPAMI.
- Print on Demand is Now Available for OnlinePlus Titles
- eBooks of issues of TPAMI can now be downloaded from the Computer Society Digital Library
- TPAMI Essential Set now available
- Editor's Note (June 2013)
- Farewall State of the Journal (Jan 2013)
- Editor's Note (Jan 2013)
- Editor's Note (May 2012)
- Editor's Note (February 2012)
- State of the Journal (January 2012)
- TPAMI CVPR Special Section (Dec 2013)
- Special Section on Learning Deep Architectures (Aug 2013)
- In Memoriam: Mark Everingham (Nov 2012)
- Introduction to the Special Section on IEEE Conference on Computer Vision and Pattern Recognition (September 2012)
Access recently published TPAMI articles
Subscribe to the RSS feed of latest TPAMI content added to the digital library
Sign up for the Transactions Connection newsletter.
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) is a scholarly archival journal published monthly. This journal covers traditional areas of computer vision and image understanding, all traditional areas of pattern analysis and recognition, and selected areas of machine intelligence.
Read the full scope of TPAMI