%0 Generic %1 citeulike:14609092 %A xxx, %D 2018 %K arch attention regularization %T Global-and-local attention networks for visual recognition %U http://arxiv.org/abs/1805.08819 %X State-of-the-art deep convolutional networks (DCNs) such as squeeze-and- excitation (SE) residual networks implement a form of attention, also known as contextual guidance, which is derived from global image features. Here, we explore a complementary form of attention, known as visual saliency, which is derived from local image features. We extend the SE module with a novel global-and-local attention (GALA) module which combines both forms of attention -- resulting in state-of-the-art accuracy on ILSVRC. We further describe ClickMe.ai, a large-scale online experiment designed for human participants to identify diagnostic image regions to co-train a GALA network. Adding humans-in-the-loop is shown to significantly improve network accuracy, while also yielding visual features that are more interpretable and more similar to those used by human observers.

@misc{citeulike:14609092, abstract = {{State-of-the-art deep convolutional networks (DCNs) such as squeeze-and- excitation (SE) residual networks implement a form of attention, also known as contextual guidance, which is derived from global image features. Here, we explore a complementary form of attention, known as visual saliency, which is derived from local image features. We extend the SE module with a novel global-and-local attention (GALA) module which combines both forms of attention -- resulting in state-of-the-art accuracy on ILSVRC. We further describe ClickMe.ai, a large-scale online experiment designed for human participants to identify diagnostic image regions to co-train a GALA network. Adding humans-in-the-loop is shown to significantly improve network accuracy, while also yielding visual features that are more interpretable and more similar to those used by human observers.}}, added-at = {2019-02-27T22:23:29.000+0100}, archiveprefix = {arXiv}, author = {xxx}, biburl = {https://www.bibsonomy.org/bibtex/22416bcf7344923d04dff4f8a941fab7e/nmatsuk}, citeulike-article-id = {14609092}, citeulike-linkout-0 = {http://arxiv.org/abs/1805.08819}, citeulike-linkout-1 = {http://arxiv.org/pdf/1805.08819}, day = 25, eprint = {1805.08819}, interhash = {408aa6cbb79db8332eac2555210515a2}, intrahash = {2416bcf7344923d04dff4f8a941fab7e}, keywords = {arch attention regularization}, month = may, posted-at = {2018-06-28 15:14:33}, priority = {2}, timestamp = {2019-02-27T22:23:29.000+0100}, title = {{Global-and-local attention networks for visual recognition}}, url = {http://arxiv.org/abs/1805.08819}, year = 2018 }