Monocular depth estimation, which plays a crucial role in understanding 3D scene geometry, is an ill-posed problem. Recent methods have gained significant improvement by exploring image-level information and hierarchical features from deep convolutional neural networks (DCNNs). These methods model depth estimation as a regression problem and train the regression networks by minimizing mean squared error, which suffers from slow convergence and unsatisfactory local solutions. Besides, existing depth estimation networks employ repeated spatial pooling operations, resulting in undesirable low-resolution feature maps. To obtain high-resolution depth maps, skip-connections or multilayer deconvolution networks are required, which complicates network training and consumes much more computations. To eliminate or at least largely reduce these problems, we introduce a spacing-increasing discretization (SID) strategy to discretize depth and recast depth network learning as an ordinal regression problem. By training the network using an ordinary regression loss, our method achieves much higher accuracy and faster convergence in synch. Furthermore, we adopt a multi-scale network structure which avoids unnecessary spatial pooling and captures multi-scale information in parallel. The proposed deep ordinal regression network (DORN) achieves state-of-the-art results on three challenging benchmarks, i.e., KITTI [16], Make3D [49], and NYU Depth v2 [41], and outperforms existing methods by a large margin.

MRI patterns were examined together with cerebrospinal fluid (CSF) biomarkers in serial scans of ADNI participants with mild cognitive impairment (MCI). The SPARE-AD score, summarizing brain atrophy patterns, was tested as predictor of short-term conversion to AD. MCI individuals that converted to AD (MCI-C) had mostly positive baseline SPARE-AD and atrophy in temporal lobe grey (GM) and white (WM) matter, posterior cingulate/precuneous, insula. MCI-C had mostly AD-like baseline CSF biomarkers. MCI non-converters (MCI-NC) had mixed baseline SPARE-AD and CSF values, suggesting that some MCI-NC subjects may later convert. Those MCI-NC with most negative baseline SPARE-AD scores (normal brain structure) had significantly higher baseline MMSE scores (28.67) than others, and relatively low annual rate of MMSE decrease (−0.25). MCI-NC with mid-level baseline SPARE-AD displayed faster annual rates of SPARE-AD increase (indicating progressing atrophy). SPARE-AD and CSF combination improved prediction over individual values. In summary, both SPARE-AD and CSF biomarkers showed high baseline sensitivity, however, many MCI-NC had abnormal baseline SPARE-AD and CSF biomarkers. Longer follow-up will elucidate the specificity of baseline measurements.

Unsupervised domain mapping aims to learn a function to translate domain X to Y by a function G XY in the absence of paired examples. Finding the optimal G XY without paired data is an ill-posed problem, so appropriate constraints are required to obtain reasonable solutions. One of the most prominent constraints is cycle consistency, which enforces the translated image by G XY to be translated back to the input image by an inverse mapping G Y X . While cycle consistency requires the simultaneous training of G XY and G Y X , recent studies have shown that one-sided domain mapping can be achieved by preserving pairwise distances between images. Although cycle consistency and distance preservation successfully constrain the solution space, they overlook the special properties of images that simple geometric transformations do not change the image's semantic structure. Based on this special property, we develop a geometry-consistent generative adversarial network (GcGAN), which enables one-sided unsupervised domain mapping. GcGAN takes the original image and its counterpart image transformed by a predefined geometric transformation as inputs and generates two images in the new domain coupled with the corresponding geometry-consistency constraint. The geometryconsistency constraint reduces the space of possible solutions while keep the correct solutions in the search space. Quantitative and qualitative comparisons with the baseline (GAN alone) and the state-of-the-art methods including CycleGAN [62] and DistanceGAN [5] demonstrate the effectiveness of our method. * equal contribution arXiv:1809.05852v2 [cs.CV] 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970

Traditional topic models do not account for semantic regularities in language. Recent distributional representations of words exhibit semantic consistency over directional metrics such as cosine similarity. However, neither categorical nor Gaussian observational distributions used in existing topic models are appropriate to leverage such correlations. In this paper, we propose to use the von Mises-Fisher distribution to model the density of words over a unit sphere. Such a representation is well-suited for directional data. We use a Hierarchical Dirichlet Process for our base topic model and propose an efficient inference algorithm based on Stochastic Variational Inference. This model enables us to naturally exploit the semantic structures of word embeddings while flexibly discovering the number of topics. Experiments demonstrate that our method outperforms competitive approaches in terms of topic coherence on two different text corpora while offering efficient inference.

We propose novel finite-dimensional spaces of R n → R n transformations, n ∈ {1, 2, 3}, derived from (continuouslydefined)