Weakly- and Self-Supervised Learning for Content-Aware Deep Image Retargeting
This work addresses image retargeting for applications like media adaptation, but it appears incremental as it builds on existing deep learning methods with weak and self-supervision.
The paper tackles the problem of content-aware image retargeting by proposing a weakly- and self-supervised deep convolutional neural network that outputs retargeted images while preserving discriminative parts and adjusting background regions seamlessly.
This paper proposes a weakly- and self-supervised deep convolutional neural network (WSSDCNN) for content-aware image retargeting. Our network takes a source image and a target aspect ratio, and then directly outputs a retargeted image. Retargeting is performed through a shift map, which is a pixel-wise mapping from the source to the target grid. Our method implicitly learns an attention map, which leads to a content-aware shift map for image retargeting. As a result, discriminative parts in an image are preserved, while background regions are adjusted seamlessly. In the training phase, pairs of an image and its image-level annotation are used to compute content and structure losses. We demonstrate the effectiveness of our proposed method for a retargeting application with insightful analyses.