The goal of this paper is to serve as a guide for selecting a detection architecture that achieves the right speed/memory/accuracy balance for a given application and platform.
#68 best model for Object Detection on COCO test-dev
The adversarial loss pushes our solution to the natural image manifold using a discriminator network that is trained to differentiate between the super-resolved images and original photo-realistic images.
#10 best model for Image Super-Resolution on BSD100 - 4x upscaling
With recent progress in graphics, it has become more tractable to train models on synthetic images, potentially avoiding the need for expensive annotations.
#4 best model for Image-to-Image Translation on Cityscapes Photo-to-Labels
The accumulated belief of the world enables the agent to track visited regions of the environment.
Collecting well-annotated image datasets to train modern machine learning algorithms is prohibitively expensive for many tasks.
As far as we know, this is the first neural network architecture that is able to outperform JPEG at image compression across most bitrates on the rate-distortion curve on the Kodak dataset images, with and without the aid of entropy coding.
We investigate conditional adversarial networks as a general-purpose solution to image-to-image translation problems.