The development of online economics arouses the demand of generating images of models on product clothes, to display new clothes and promote sales.
Existing 2D image-based virtual try-on methods aim to transfer a target clothing image onto a reference person, which has two main disadvantages: cannot control the size and length precisely; unable to accurately estimate the user's figure in the case of users wearing thick clothes, resulting in inaccurate dressing effect.
Many well-trained Convolutional Neural Network(CNN) models have now been released online by developers for the sake of effortless reproducing.
In this paper, we investigate a novel deep-model reusing task.
We propose a selective zero-shot classifier based on both the human defined and the automatically discovered residual attributes.