This paper is an extension of our previous work on No-reference IQA [“Rankiqa: Learning from rankings for no-reference image quality assessment”] and crowd counting [L2R : “Leveraging unlabeled data for crowd counting by learning to rank”].
Beyond these previous works, here we propose a general framework for training from self-supervised rankings.
In addition, we apply the multi-task approach from [L2R] to the IQA problem, improving the results of our previous IQA method.
We also include results on two new datasets for crowd counting, UCSD and WorldExpo’10.
Finally, we show that self-supervised ranking tasks can also be used as a criterion for active learning. In this case the aim is to select which images to label from a large pool of unlabeled data. In experiments we show that this can significantly reduce the required labeling effort.
**
Goal:
**
In this work we study the use of ranking as a self-supervised proxy task to leverage unlabeled data and improve the training of deep networks for regression problems.
**
Contributions:
**
-
We show that ranking tasks can be used as self-supervised proxy tasks, and how this can be exploited to leverage unlabeled data for applications suffering from a shortage of labeled data.
-
We propose a method for fast Siamese backpropagation which avoids the redundant computation common to training multi-branch Siamese network architectures.
In addition, we proposed a method for fast backpropagation for the ranking loss. This method removes the redundant computation which is introduced by the multiple branches of Siamese networks, and instead uses a single branch after which all possible pairs of the minibatch are combined (rather than just a selection of pairs).
(我懒得看细节了。。。)