The 10 coolest papers from CVPR 2018The 2018 Conference on Computer Vision and Pattern Recognition (CVPR) took place last week in Salt Lake City, USA. It’s the world’s top conference in the field of computer vision. This year, CVPR received 3,300 main conference paper submissions and accepted 979. Over 6,500 attended the conference and boy was it epic! 6500 people were packed into this room:CVPR 2018 Grand BallroomEvery year, CVPR brings in great people and their great research; there’s always something new to see and learn. Of course, there’s always those papers that publish new ground breaking results and bring in some great new knowledge into the field. These papers often shape the new state-of-the-art across many of the sub-domains of computer vision.Lately though, what’s been really fun to see is those out-of-the-box and creative papers! With this fairly recent rush of deep learning in computer vision, we’re still discovering all the possibilities. Many papers will present totally new applications of deep networks in vision. They may not be the most fundamentally ground-breaking works, but they’re fun to see and offer a creative and enlightening perspective to the field, often sparking new ideas from the new angle they present. All in all, they’re pretty cool!Here, I’m going to show you what I thought were the 10 coolest papers at CVPR 2018. We’ll see new applications that have only recently been made possible by using deep networks, and others that offer a new twist on how to use them. You might just pick up some new ideas yourself along the way ;)..Without further adieu, let’s dive in!Training Deep Networks with Synthetic Data: Bridging the Reality Gap by Domain RandomizationThis paper comes from Nvidia and goes full throttle on using synthetic data to train Convolutional Neural Networks (CNNs)..They created a plugin for Unreal Engine 4 which will generate synthetic training data..It may shed some light on how to go about generating and using synthetic data if you’re short on that important resource.Figure from the paper: Training Deep Networks with Synthetic Data: Bridging the Reality Gap by Domain RandomizationWESPE: Weakly Supervised Photo Enhancer for Digital CamerasThis one’s clever!.But for many sub-domains in computer vision, weak supervision seems like a promising and profitable direction.Figure from the paper: WESPE: Weakly Supervised Photo Enhancer for Digital CamerasEfficient Interactive Annotation of Segmentation Datasets with Polygon-RNN++One of the main reasons deep networks work so well is the availability of large and fully annotated datasets..Hopefully it can inspire future research creativity with the way we collect data and apply deep learning techniques.Figure from the paper: Who Let The Dogs Out?.Overall, it’s definitely a step in the right direction of how we can think to get the most out of our deep network models.Figure from the paper: Learning to Segment Every ThingSoccer on Your TabletopThis paper should win the award for best timing with it being publishing right when the FIFA World Cup is on!.The network is trained using video game data from which the 3D meshes can fairly easily be extracted..In my view, it’s sort of a clever way of using synthetic data for training..Either way it’s a fun application!Figure from the paper: Soccer on Your TabletopLayoutNet: Reconstructing the 3D Room Layout from a Single RGB ImageThis one is a computer vision application that many of us have likely thought of at one time or another: use a camera to take a picture of something, and then reconstruct that thing in digital 3D..It’s an interesting and fun application that you don’t see too many researchers working on in computer vision, so it’s nice to see.Figure from the paper: LayoutNet: Reconstructing the 3D Room Layout from a Single RGB ImageLearning Transferable Architectures for Scalable Image RecognitionLast but not least is what many consider to be the future of deep learning: Neural Architecture Search (NAS).. More details