No abstract

Large-scale labeled datasets are generally necessary for successfully training a deep neural network in the computer vision domain. In order to avoid the costly and tedious work of manually annotating image datasets, self-supervised learning methods have been proposed to learn general visual features automatically. In this paper, we first focus on image colorization with generative adversarial networks (GANs) because of their ability to generate the most realistic colorization results. Then, via transfer learning, we use this as a proxy task for visual understanding. Particularly, we propose to use conditional GANs (cGANs) for image colorization and transfer the gained knowledge to two other downstream tasks, namely, multilabel image classification and semantic segmentation. This is the first time that GANs have been used for self-supervised feature learning through image colorization. Through extensive experiments with the COCO and Pascal datasets, we show an increase of 5% for the classification task and 2.5% for the segmentation task. This demonstrates that image colorization with conditional GANs can boost other downstream tasks’ performance without the need for manual annotation.

No abstract

This paper presents a framework that helps in selecting the most appropriate timing for interruption as a way to mediate human interruptions by the computer. The conceptual framework is based on the new Interruption Taxonomy and uses Bayesian Belief Networks as a decision-support aid. A proof-of-concept model was constructed for the experimental setting used in the exploratory study that was also part of this research. The steps in constructing the model that was built into the first version of the interruption mediator will be presented to show, in detail, how one might use the proposed framework for mediating interruptions.

No abstract

No abstract

No abstract

No abstract