794 papers with code • 32 benchmarks • 55 datasets
Domain adaptation is the task of adapting models across domains.
( Image credit: Unsupervised Image-to-Image Translation Networks )
We propose to using high level semantic and contextual features including segmentation and detection masks obtained by off-the-shelf state-of-the-art vision as observations and use deep network to learn the navigation policy.
Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.
Ranked #2 on Semantic Object Interaction Classification on VLOG
Collecting well-annotated image datasets to train modern machine learning algorithms is prohibitively expensive for many tasks.
In this paper, we propose a new loss function called generalized end-to-end (GE2E) loss, which makes the training of speaker verification models more efficient than our previous tuple-based end-to-end (TE2E) loss function.
By contrast, humans can generally perform a new language task from only a few examples or from simple instructions - something which current NLP systems still largely struggle to do.
Ranked #1 on Question Answering on PIQA
Unsupervised image-to-image translation aims at learning a joint distribution of images in different domains by using images from the marginal distributions in individual domains.