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

In this work we address the task of semantic image segmentation with Deep Learning and make three main contributions that are experimentally shown to have substantial practical merit. First , we highlight convolution with upsampled filters, or ‘atrous convolution’, as a powerful tool in dense prediction tasks. Atrous convolution allows us to explicitly control the resolution at which feature responses are computed within Deep Convolutional Neural Networks. It also allows us to effectively enlarge the field of view of filters to incorporate larger context without increasing the number of parameters or the amount of computation. Second , we propose atrous spatial pyramid pooling (ASPP) to robustly segment objects at multiple scales. ASPP probes an incoming convolutional feature layer with filters at multiple sampling rates and effective fields-of-views, thus capturing objects as well as image context at multiple scales. Third , we improve the localization of object boundaries by combining methods from DCNNs and probabilistic graphical models. The commonly deployed combination of max-pooling and downsampling in DCNNs achieves invariance but has a toll on localization accuracy. We overcome this by combining the responses at the final DCNN layer with a fully connected Conditional Random Field (CRF), which is shown both qualitatively and quantitatively to improve localization performance. Our proposed “DeepLab” system sets the new state-of-art at the PASCAL VOC-2012 semantic image segmentation task, reaching 79.7 percent mIOU in the test set, and advances the results on three other datasets: PASCAL-Context, PASCAL-Person-Part, and Cityscapes. All of our code is made publicly available online.

DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs

In this work we address the task of semantic image segmentation with Deep Learning and make three main contributions that are experimentally shown to have substantial practical merit. First, we highlight convolution with upsampled filters, or 'atrous convolution', as a powerful tool in dense prediction tasks. Atrous convolution allows us to explicitly control the resolution at which feature responses are computed within Deep Convolutional Neural Networks. It also allows us to effectively enlarge the field of view of filters to incorporate larger context without increasing the number of parameters or the amount of computation. Second, we propose atrous spatial pyramid pooling (ASPP) to robustly segment objects at multiple scales. ASPP probes an incoming convolutional feature layer with filters at multiple sampling rates and effective fields-of-views, thus capturing objects as well as image context at multiple scales. Third, we improve the localization of object boundaries by combining methods from DCNNs and probabilistic graphical models. The commonly deployed combination of max-pooling and downsampling in DCNNs achieves invariance but has a toll on localization accuracy. We overcome this by combining the responses at the final DCNN layer with a fully connected Conditional Random Field (CRF), which is shown both qualitatively and quantitatively to improve localization performance. Our proposed "DeepLab" system sets the new state-of-art at the PASCAL VOC-2012 semantic image segmentation task, reaching 79.7% mIOU in the test set, and advances the results on three other datasets: PASCAL-Context, PASCAL-Person-Part, and Cityscapes. All of our code is made publicly available online.

Deposits of clastic carbonate-dominated (calciclastic) sedimentary slope systems in the rock record have been identified mostly as linearly-consistent carbonate apron deposits, even though most ancient clastic carbonate slope deposits fit the submarine fan systems better. Calciclastic submarine fans are consequently rarely described and are poorly understood. Subsequently, very little is known especially in mud-dominated calciclastic submarine fan systems. Presented in this study are a sedimentological core and petrographic characterisation of samples from eleven boreholes from the Lower Carboniferous of Bowland Basin (Northwest England) that reveals a >250 m thick calciturbidite complex deposited in a calciclastic submarine fan setting. Seven facies are recognised from core and thin section characterisation and are grouped into three carbonate turbidite sequences. They include: 1) Calciturbidites, comprising mostly of highto low-density, wavy-laminated bioclast-rich facies; 2) low-density densite mudstones which are characterised by planar laminated and unlaminated muddominated facies; and 3) Calcidebrites which are muddy or hyper-concentrated debrisflow deposits occurring as poorly-sorted, chaotic, mud-supported floatstones. These

Phd by thesis

Computer vision applications have come to rely increasingly on superpixels in recent years, but it is not always clear what constitutes a good superpixel algorithm. In an effort to understand the benefits and drawbacks of existing methods, we empirically compare five state-of-the-art superpixel algorithms for their ability to adhere to image boundaries, speed, memory efficiency, and their impact on segmentation performance. We then introduce a new superpixel algorithm, simple linear iterative clustering (SLIC), which adapts a k-means clustering approach to efficiently generate superpixels. Despite its simplicity, SLIC adheres to boundaries as well as or better than previous methods. At the same time, it is faster and more memory efficient, improves segmentation performance, and is straightforward to extend to supervoxel generation.

/pdf/slic-superpixels-compared-to-state-of-the-art-superpixel-5d8sq04am9.pdf

SLIC Superpixels Compared to State-of-the-Art Superpixel Methods

We analyze the observability of 3-D pose from the fusion of visual and inertial sensors. Because the model contains unknown parameters, such as sensor biases, the problem is usually cast as a mixed filtering/identification, with the resulting observability analysis providing necessary conditions for convergence to a unique point estimate. Most models treat sensor bias rates as “noise,” independent of other states, including biases themselves, an assumption that is patently violated in practice. We show that, when this assumption is lifted, the resulting model is not observable, and therefore existing analyses cannot be used to conclude that the set of states that are indistinguishable from the measurements is a singleton. In other words, the resulting model is not observable. We therefore re-cast the analysis as one of sensitivity: Rather than attempting to prove that the set of indistinguishable trajectories is a singleton, we derive bounds on its volume, as a function of characteristics of the sensor and other sufficient excitation conditions. This provides an explicit characterization of the indistinguishable set that can be used for analysis and validation purposes.

Observability, identifiability and sensitivity of vision-aided inertial navigation

We cast the problem of inferring the 3D shape of a scene from a collection of defocused images in the framework of anisotropic diffusion We propose an algorithm that can estimate the shape of a scene by inferring the diffusion coefficient of a heat equation The method is optimal, as we pose it as the minimization of a certain cost functional based on the input images, and fast Furthermore, we also extend our algorithm to the case of multiple images, and derive a 3D scene segmentation algorithm that can work in the presence of pictorial camouflage

3D shape from anisotropic diffusion

The "visual motion estimation" problem concerns the reconstruction of the motion of an object viewed under projection. This paper addresses the feasibility of such a problem when the object is represented as a "rigid" set of point-features in the Euclidean 3D space. We represent rigid motion as a point on the so-called "essential manifold" and show that it is globally observable from perspective projections under some general position conditions. Such conditions hold when the path of the viewer and the visible objects cannot be embedded in a quadric surface of R/sup 3/. >

/pdf/observability-identifiability-of-rigid-motion-under-4dfr1b17b0.pdf

Observability/identifiability of rigid motion under perspective projection

We formulate the problem of reconstructing the shape and radiance of a scene as the minimization of the information divergence between blurred images, and propose an algorithm that is provably convergent and guarantees that the solution is admissible, in the sense of corresponding to a positive radiance and imaging kernel. The motivation for the use of information divergence comes from the work of Csiszar [5], while the fundamental elements of the proof of convergence come from work by Snyder et al. [14], extended to handle unknown imaging kernels (i.e. the shape of the scene).

/pdf/shape-and-radiance-estimation-from-the-information-1mdlsbovx9.pdf

Shape and Radiance Estimation from the Information-Divergence of Blurred Images

We propose a nonlinear filter for estimating the trajectory of a random walk on a matrix Lie group with constant computational complexity. It is based on a finite-dimensional approximation of the conditional distribution of the state-given past measurements-via a set of fair samples, which are updated at each step and proven to be consistent with the updated conditional distribution. The algorithm proposed, like other Monte Carlo methods, can in principle track arbitrary distributions evolving on arbitrarily large state spaces. However, several issues concerning sample impoverishment need to be taken into account when designing practical working systems.

Stefano Soatto

Papers

Observability, identifiability and sensitivity of vision-aided inertial navigation

3D shape from anisotropic diffusion

Observability/identifiability of rigid motion under perspective projection

Shape and Radiance Estimation from the Information-Divergence of Blurred Images

Monte Carlo filtering on Lie groups