Topic Tag: COCO

home Forums Topic Tag: COCO

 Beyond Skip Connections: Top-Down Modulation for Object Detection

In recent years, we have seen tremendous progress in the field of object detection. Most of the recent improvements have been achieved by targeting deeper feedforward networks. However, many hard object categories such as bottle, remote, etc. require representation of fine details and not just coar…


 Fine-tuning deep CNN models on specific MS COCO categories

  

Fine-tuning of a deep convolutional neural network (CNN) is often desired. This paper provides an overview of our publicly available py-faster-rcnn-ft software library that can be used to fine-tune the VGG_CNN_M_1024 model on custom subsets of the Microsoft Common Objects in Context (MS COCO) datas…


 An Update to Open Images – Now with Bounding-Boxes

   

Posted by Vittorio Ferrari, Research Scientist, Machine Perception Last year we introduced Open Images, a collaborative release of ~9 million images annotated with labels spanning over 6000 object categories, designed to be a useful dataset for machine learning research. The initial release feature…