Calibrated estimates of uncertainty are critical for many real-world computer vision applications of deep learning. While there are several widely-used uncertainty estimation methods, dropout inference stands out for its simplicity and efficacy. This
technique, however, requires multiple forward passes through the network during inference and therefore can be too resource-intensive to be deployed in real-time applications. We propose a simple, easy-to-optimize distillation method for learning the conditional predictive distribution of a pre-trained dropout model for fast, sample-free uncertainty estimation in computer vision tasks. We empirically test the effectiveness of the proposed method on both semantic segmentation and depth estimation tasks and demonstrate our method can significantly reduce the inference time, enabling real-time uncertainty quantification, while achieving improved quality of both the uncertainty estimates and predictive performance over the regular dropout model.
We introduce an interactive Soft Shadow Network (SSN) to generates controllable soft shadows for image compositing. SSN takes a 2D object mask as input and thus is agnostic to image types such as painting and vector art. An environment light map is u
sed to control the shadows characteristics, such as angle and softness. SSN employs an Ambient Occlusion Prediction module to predict an intermediate ambient occlusion map, which can be further refined by the user to provides geometric cues to modulate the shadow generation. To train our model, we design an efficient pipeline to produce diverse soft shadow training data using 3D object models. In addition, we propose an inverse shadow map representation to improve model training. We demonstrate that our model produces realistic soft shadows in real-time. Our user studies show that the generated shadows are often indistinguishable from shadows calculated by a physics-based renderer and users can easily use SSN through an interactive application to generate specific shadow effects in minutes.
Conventional computing architectures have no known efficient algorithms for combinatorial optimization tasks, which are encountered in fundamental areas and real-world practical problems including logistics, social networks, and cryptography. Physica
l machines have recently been proposed and implemented as an alternative to conventional exact and heuristic solvers for the Ising problem, one such optimization task that requires finding the ground state spin configuration of an arbitrary Ising graph. However, these physical approaches usually suffer from decreased ground state convergence probability or universality for high edge-density graphs or arbitrary graph weights, respectively. We experimentally demonstrate a proof-of-principle integrated nanophotonic recurrent Ising sampler (INPRIS) capable of converging to the ground state of various 4-spin graphs with high probability. The INPRIS exploits experimental physical noise as a resource to speed up the ground state search. By injecting additional extrinsic noise during the algorithm iterations, the INPRIS explores larger regions of the phase space, thus allowing one to probe noise-dependent physical observables. Since the recurrent photonic transformation that our machine imparts is a fixed function of the graph problem, and could thus be implemented with optoelectronic architectures that enable GHz clock rates (such as passive or non-volatile photonic circuits that do not require reprogramming at each iteration), our work paves a way for orders-of-magnitude speedups in exploring the solution space of combinatorially hard problems.
Convolutional Neural Networks (CNNs) are a class of Artificial Neural Networks(ANNs) that employ the method of convolving input images with filter-kernels for object recognition and classification purposes. In this paper, we propose a photonics circu
it architecture which could consume a fraction of energy per inference compared with state of the art electronics.
We propose a frequency selective light trapping scheme that enables the creation of more visually-transparent and yet simultaneously more efficient semitransparent solar cells. A nanoparticle scattering layer and photonic stack back reflector create
a selective trapping effect by total internal reflection within a medium, increasing absorption of IR light. We propose a strong frequency selective scattering layer using spherical TiO2 nanoparticles with radius of 255 nm and area density of 1.1% in a medium with index of refraction of 1.5. Using detailed numerical simulations for this configuration, we find that it is possible to create a semitransparent silicon solar cell that has a Shockley Queisser efficiency of 12.0%pm0.4% with a visible transparency of 60.2%pm1.3%, 13.3%pm1.3 more visibly-transparent than a bare silicon cell at the same efficiency.
We demonstrate how broadband angular selectivity can be achieved with stacks of one-dimensionally periodic photonic crystals, each consisting of alternating isotropic layers and effective anisotropic layers, where each effective anisotropic layer is
constructed from a multilayered metamaterial. We show that by simply changing the structure of the metamaterials, the selective angle can be tuned to a broad range of angles; and, by increasing the number of stacks, the angular transmission window can be made as narrow as desired. As a proof of principle, we realize the idea experimentally in the microwave regime. The angular selectivity and tunability we report here can have various applications such as in directional control of electromagnetic emitters and detectors.
