Abstract: One important field of study that combines language processing and computer vision to produce descriptive text from images is image captioning, which uses deep learning and natural language ...
In this example we compress torchvision's object detection models - FasterRCNN / MaskRCNN / KeypointRCNN. We've modified the reference code for object detection to allow easy compression scheduling ...
Abstract: Agricultural productivity often suffers due to plant diseases, causing major financial losses for farmers. Traditionally, spotting these diseases has been a slow process that relies on ...
# Detectron1 uses smooth L1 loss with some magic beta values. # The defaults are changed to L1 loss in Detectron2.
Some results have been hidden because they may be inaccessible to you
Show inaccessible results