We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14). The main hallmark of this architecture is the improved utilization of the computing resources inside the network. By a carefully crafted design, we increased the depth and width of the network while keeping the computational budget constant. To optimize quality, the architectural decisions were based on the Hebbian principle and the intuition of multi-scale processing. One particular incarnation used in our submission for ILSVRC14 is called GoogLeNet, a 22 layers deep network, the quality of which is assessed in the context of classification and detection.

/pdf/going-deeper-with-convolutions-1yobw2o2ds.pdf

Going deeper with convolutions

다중혈관 관상동맥 환자에서 y-문합을 이용하여 양쪽 내흉동맥만을 사용한 우회술의 조기 성적

This survey provides an overview of higher-order tensor decompositions, their applications, and available software. A tensor is a multidimensional or $N$-way array. Decompositions of higher-order tensors (i.e., $N$-way arrays with $N \geq 3$) have applications in psycho-metrics, chemometrics, signal processing, numerical linear algebra, computer vision, numerical analysis, data mining, neuroscience, graph analysis, and elsewhere. Two particular tensor decompositions can be considered to be higher-order extensions of the matrix singular value decomposition: CANDECOMP/PARAFAC (CP) decomposes a tensor as a sum of rank-one tensors, and the Tucker decomposition is a higher-order form of principal component analysis. There are many other tensor decompositions, including INDSCAL, PARAFAC2, CANDELINC, DEDICOM, and PARATUCK2 as well as nonnegative variants of all of the above. The N-way Toolbox, Tensor Toolbox, and Multilinear Engine are examples of software packages for working with tensors.

/pdf/tensor-decompositions-and-applications-46vl2ih5gn.pdf

Tensor Decompositions and Applications

The discriminative model learning for image denoising has been recently attracting considerable attentions due to its favorable denoising performance. In this paper, we take one step forward by investigating the construction of feed-forward denoising convolutional neural networks (DnCNNs) to embrace the progress in very deep architecture, learning algorithm, and regularization method into image denoising. Specifically, residual learning and batch normalization are utilized to speed up the training process as well as boost the denoising performance. Different from the existing discriminative denoising models which usually train a specific model for additive white Gaussian noise at a certain noise level, our DnCNN model is able to handle Gaussian denoising with unknown noise level (i.e., blind Gaussian denoising). With the residual learning strategy, DnCNN implicitly removes the latent clean image in the hidden layers. This property motivates us to train a single DnCNN model to tackle with several general image denoising tasks, such as Gaussian denoising, single image super-resolution, and JPEG image deblocking. Our extensive experiments demonstrate that our DnCNN model can not only exhibit high effectiveness in several general image denoising tasks, but also be efficiently implemented by benefiting from GPU computing.

Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising

We present an approach to interpret the major surfaces, objects, and support relations of an indoor scene from an RGBD image. Most existing work ignores physical interactions or is applied only to tidy rooms and hallways. Our goal is to parse typical, often messy, indoor scenes into floor, walls, supporting surfaces, and object regions, and to recover support relationships. One of our main interests is to better understand how 3D cues can best inform a structured 3D interpretation. We also contribute a novel integer programming formulation to infer physical support relations. We offer a new dataset of 1449 RGBD images, capturing 464 diverse indoor scenes, with detailed annotations. Our experiments demonstrate our ability to infer support relations in complex scenes and verify that our 3D scene cues and inferred support lead to better object segmentation.

/pdf/indoor-segmentation-and-support-inference-from-rgbd-images-1brf1o9jc3.pdf

Indoor segmentation and support inference from RGBD images

Using a new MC simulator, we study statistics of speckle fields in scattering media. This allows understanding the Memory Effect limits and using speckle correlations to improve our ability to see through random media

Exploiting speckle statistics in random media beyond the diffusion limit

Spatial light modulator (SLM) technology forms the centerpiece of digital holographic displays. However, an inherent limitation of these devices is that their ´etendue, defined as the product of the display’s eye box and field of view (FoV), is bounded by the number of pixel units. As a consequence, current SLMs are far from meeting the required FoV and eye box for the human visual system, which would require scaling the number of display units by a few orders of magnitude. Existing strategies for ´etendue-expansion rely on introducing a diffractive optical element (DOE), a fixed random phase mask whose pitch is much smaller than that of the original display, thereby spreading light over a wider angle. Displayed content is then optimized under perceptual constraints on the generated image. However, since the phase mask is fixed, the number of degrees of freedom does not increase and hence, the expansion in ´etendue necessarily comes with a loss of image quality. The trade-offs involved with such phase masks are not well understood. This paper studies the space of phase masks that can be attached to an SLM to increase its angular range. It attempts to characterize what trade-offs are involved in ´etendue-expansion, and whatever specific phase mask designs would support better holograms. We show that while pseudo random masks support wide-´etendue, they involve an inherent loss of contrast. Perhaps surprisingly, simple commonly-available phase masks like lenslet arrays provide near-optimal results that can largely outperform random masks.

Analysis of phase masks for wide étendue holographic displays

Methods of culturing T cells are provided. Accordingly there is provided a method of culturing T cells comprising culturing T cells in the presence of a T cell stimulator, an exogenous CCL21 and an exogenous ICAM1, thereby culturing the T cells. Also provided are cell cultures, isolated T cells and uses of same.

Methods of culturing t cells and uses of same

We are interested in measuring the volumetric scattering phase function of materials. While previous approaches have relied on computationally costly inverse rendering optimization, we suggest a simple closed-form approach, for acquiring scattering phase function from thick samples. We have built a prototype capable of measuring phase functions over a narrow angular cone. We test our approach using validation materials whose phase function is known; and we use it to capture a set of everyday materials.

Acquiring the phase function of volumetric scattering materials using speckle correlation

We introduce an interferometric technique for passive time-of-flight imaging and depth sensing at micrometer axial resolutions. Our technique uses a full-field Michelson interferometer, modified to use sunlight as the only light source. The large spectral bandwidth of sunlight makes it possible to acquire micrometer-resolution time-resolved scene responses, through a simple axial scanning operation. Additionally, the angular bandwidth of sunlight makes it possible to capture time-of-flight measurements insensitive to indirect illumination effects, such as interreflections and subsurface scattering. We build an experimental prototype that we operate outdoors, under direct sunlight, and in adverse environment conditions such as machine vibrations and vehicle traffic. We use this prototype to demonstrate, for the first time, passive imaging capabilities such as micrometer-scale depth sensing robust to indirect illumination, direct-only imaging, and imaging through diffusers.

Anat Levin

Papers

Exploiting speckle statistics in random media beyond the diffusion limit

Analysis of phase masks for wide étendue holographic displays

Methods of culturing t cells and uses of same

Acquiring the phase function of volumetric scattering materials using speckle correlation

Passive Micron-scale Time-of-Flight with Sunlight Interferometry