Unsupervised object discovery and co-localization by deep descriptor transformation

Reusable model design becomes desirable with the rapid expansion of computer vision and pattern recognition applications. In this paper, we focus on the reusability of pre-trained deep convolutional models. Specifically, different from treating pre-trained models as feature extractors, we reveal more treasures beneath convolutional layers, i.e., the convolutional activations could act as a detector for the common object in the object...