A Classification approach towards Unsupervised Learning of Visual Representations
This addresses the problem of learning visual representations without supervision for computer vision researchers, but it is incremental as it builds on existing unsupervised techniques.
The paper tackles unsupervised learning of visual representations by training a model for foreground and background classification using patches mined from unlabeled videos, achieving 45.3 mAP on PASCAL VOC 2007, which is competitive with top unsupervised methods.
In this paper, we present a technique for unsupervised learning of visual representations. Specifically, we train a model for foreground and background classification task, in the process of which it learns visual representations. Foreground and background patches for training come af- ter mining for such patches from hundreds and thousands of unlabelled videos available on the web which we ex- tract using a proposed patch extraction algorithm. With- out using any supervision, with just using 150, 000 unla- belled videos and the PASCAL VOC 2007 dataset, we train a object recognition model that achieves 45.3 mAP which is close to the best performing unsupervised feature learn- ing technique whereas better than many other proposed al- gorithms. The code for patch extraction is implemented in Matlab and available open source at the following link .