No abstract

Self-supervised learning approaches for unsupervised domain adaptation (UDA) of semantic segmentation models suffer from challenges of predicting and selecting reasonable good quality pseudo labels. In this paper, we propose a novel approach of exploiting scale-invariance property of the semantic segmentation model for self-supervised domain adaptation. Our algorithm is based on a reasonable assumption that, in general, regardless of the size of the object and stuff (given context) the semantic labeling should be unchanged. We show that this constraint is violated over the images of the target domain, and hence could be used to transfer labels in-between differently scaled patches. Specifically, we show that semantic segmentation model produces output with high entropy when presented with scaled-up patches of target domain, in comparison to when presented original size images. These scale-invariant examples are extracted from the most confident images of the target domain. Dynamic class specific entropy thresholding mechanism is presented to filter out unreliable pseudo-labels. Furthermore, we also incorporate the focal loss to tackle the problem of class imbalance in self-supervised learning. Extensive experiments have been performed, and results indicate that exploiting the scale-invariant labeling, we outperform existing selfsupervised based state-of-the-art domain adaptation methods. Specifically, we achieve 1.3% and 3.8% of lead for GTA5 to Cityscapes and SYNTHIA to Cityscapes with VGG16-FCN8 baseline network.

Many educators would like to believe they are helping their students prepare to become intelligent, skilled, responsible -and ethical --workers as they move into adult life. Most research has concluded that few schools have serious, well-designed programs to assess the ethical competence of their students and to ensure that the desired outcomes are met. Educators agree that it is desirable to measure the outcomes of our educational processes. But to measure, one must first identify the desired competencies. This has proven difficult. We will report on a multi-university research program designed to develop measure(s) of ethical "competence", in order to identify best practices in developing those competencies. We will report on the three measures we are currently designing to measure ethical competence in these settings.