![]() In the last years, Deep Neural Networks (DNNs) have become popular for computer vision and pattern recognition tasks such as image classification, semantic segmentation, or object detection. Experimental results show that known attention mechanisms in DNNs work pretty much as human visual attention, but still the proposed approach allows a faster convergence and better performance in image classification tasks. We add visual attention maps as new data alongside images, thus introducing human visual attention into the DNNs training and compare it with both global and local automatic attention mechanisms. We use human visual attention maps obtained independently with psycho-visual experiments, both in task-driven or in free viewing conditions, or powerful models for prediction of visual attention maps. In this paper, we present a study and propose a method with a different approach, adding supplementary visual data next to training images. Channel and feature importance are learnt in the global end-to-end DNNs training process. ![]() Such attention mechanisms perform both globally by reinforcing feature channels and locally by stressing features in each feature map. The so-called “attention mechanisms” in Deep Neural Networks (DNNs) denote an automatic adaptation of DNNs to capture representative features given a specific classification task and related data. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |