Florent Perronnin, Zaid Harchaoui, Zeynep Akata, Schmid Cordelia
IEEE Conference on Computer Vision and Pattern Recognition, Providence, Rhode Island, June, USA, 18-20, 2012.
We propose a benchmark of several objective functions
for large-scale image classification: we compare the one vs-rest, multiclass, ranking and weighted average ranking
SVMs. Using stochastic gradient descent optimization, we
can scale the learning to millions of images and thousands
of classes. Our experimental evaluation shows that ranking
based algorithms do not outperform a one-vs-rest strategy
and that the gap between the different algorithms reduces
in case of high-dimensional data. We also show that for
one-vs-rest, learning through cross-validation the optimal
degree of imbalance between the positive and the negative
samples can have a significant impact. Furthermore, early
stopping can be used as an effective regularization strategy
when training with stochastic gradient algorithms. Following
these “good practices�, we were able to improve the
state-of-the-art on a large subset of 10K classes and 9M of
images of ImageNet from 16.7% accuracy to 19.1%.
Report number: