We present a highly accurate single-image superresolution (SR) method. Our method uses a very deep convolutional network inspired by VGG-net used for ImageNet classification [19]. We find increasing our network depth shows a significant improvement in accuracy. Our final model uses 20 weight layers. By cascading small filters many times in a deep network structure, contextual information over large image regions is exploited in an efficient way. With very deep networks, however, convergence speed becomes a critical issue during training. We propose a simple yet effective training procedure. We learn residuals only and use extremely high learning rates (10 4 times higher than SRCNN [6]) enabled by adjustable gradient clipping. Our proposed method performs better than existing methods in accuracy and visual improvements in our results are easily noticeable.

We propose an image super-resolution method (SR) using a deeply-recursive convolutional network (DRCN). Our network has a very deep recursive layer (up to 16 recursions). Increasing recursion depth can improve performance without introducing new parameters for additional convolutions. Albeit advantages, learning a DRCN is very hard with a standard gradient descent method due to exploding/vanishing gradients. To ease the difficulty of training, we propose two extensions: recursive-supervision and skip-connection. Our method outperforms previous methods by a large margin.

Innate immune cells recruited to inflammatory sites have short life spans and originate from the marrow, which is distributed throughout the long and flat bones. While bone marrow production and release of leukocyte increases after stroke, it is currently unknown whether its activity rises homogeneously throughout the entire hematopoietic system. To address this question, we employed spectrally resolved in vivo cell labeling in the murine skull and tibia. We show that in murine models of stroke and aseptic meningitis, skull bone marrow-derived neutrophils are more likely to migrate to the adjacent brain tissue than cells that reside in the tibia. Confocal microscopy of the skull-dura interface revealed myeloid cell migration through microscopic vascular channels crossing the inner skull cortex. These observations point to a direct local interaction between the brain and the skull bone marrow through the meninges.

No abstract

While humans easily recognize relations between data from different domains without any supervision, learning to automatically discover them is in general very challenging and needs many ground-truth pairs that illustrate the relations. To avoid costly pairing, we address the task of discovering cross-domain relations given unpaired data. We propose a method based on generative adversarial networks that learns to discover relations between different domains (DiscoGAN). Using the discovered relations, our proposed network successfully transfers style from one domain to another while preserving key attributes such as orientation and face identity.