Deep CNN-based object detection systems have achieved remarkable success on several large-scale object detection benchmarks. However, training such detectors requires a large number of labeled bounding boxes, which are more difficult to obtain than image-level annotations. Previous work addresses this issue by transforming image-level classifiers into object detectors. This is done by modeling the differences between the two on categories with both imagelevel and bounding box annotations, and transferring this information to convert classifiers to detectors for categories without bounding box annotations. We improve this previous work by incorporating knowledge about object similarities from visual and semantic domains during the transfer process. The intuition behind our proposed method is that visually and semantically similar categories should exhibit more common transferable properties than dissimilar categories, e.g. a better detector would result by transforming the differences between a dog classifier and a dog detector onto the cat class, than would by transforming from the violin class. Experimental results on the challenging ILSVRC2013 detection dataset demonstrate that each of our proposed object similarity based knowledge transfer methods outperforms the baseline methods. We found strong evidence that visual similarity and semantic relatedness are complementary for the task, and when combined notably improve detection, achieving state-of-the-art detection performance in a semi-supervised setting.

No abstract

An international consensus is emerging around the Belt and Road Initiative (BRI) proposed by the Chinese government, with a growing number of countries seeing it as a way of jointly exploring new international economic governance mechanisms. Meanwhile, with the crisis of neo-liberalism, economic globalization has arrived at a crossroad. In particular, incessant voices speak out against globalization, making the quest for a new way of promoting global development a major challenge. In this context, more and more political elites and scholars consider that the BRI opens up a possible new globalization path, amongst which inclusive globalization warrants exploration. On the basis of a brief analysis of the course and mechanism of global economic expansion and the limitations of neo-liberal globalization, along with the putting into practice of the BRI, this paper outlines some of the core features of inclusive globalization, i.e., inclusive growth with effective and efficient government regulation; inclusive infrastructure development; inclusive development paths chosen nationally that suit national conditions; inclusive participation; and cultural inclusiveness. Although these features are not sufficient to characterize fully inclusive globalization, they do identify some directions for future research, and provide elements of a discursive construction of the BRI.

Deep CNN-based object detection systems have achieved remarkable success on several large-scale object detection benchmarks. However, training such detectors requires a large number of labeled bounding boxes, which are more difficult to obtain than image-level annotations. Previous work addresses this issue by transforming image-level classifiers into object detectors. This is done by modeling the differences between the two on categories with both image-level and bounding box annotations, and transferring this information to convert classifiers to detectors for categories without bounding box annotations. We improve this previous work by incorporating knowledge about object similarities from visual and semantic domains during the transfer process. The intuition behind our proposed method is that visually and semantically similar categories should exhibit more common transferable properties than dissimilar categories, e.g. a better detector would result by transforming the differences between a dog classifier and a dog detector onto the cat class, than would by transforming from the violin class. Experimental results on the challenging ILSVRC2013 detection dataset demonstrate that each of our proposed object similarity based knowledge transfer methods outperforms the baseline methods. We found strong evidence that visual similarity and semantic relatedness are complementary for the task, and when combined notably improve detection, achieving state-of-the-art detection performance in a semi-supervised setting.