arXiv subjects

Matthew Brown

Publications and source records attributed to Matthew Brown.

35 records · Page 2Linked to original sources

arXiv2020

AirSim Drone Racing Lab

Autonomous drone racing is a challenging research problem at the intersection of computer vision, planning, state estimation, and control. We introduce AirSim Drone Racing Lab, a simulation framework for enabling fast prototyping of algorithms for autonomy and enabling machine learning research in this domain, with the goal of reducing the time, money, and risks associated with field robotics. Our framework enables generation of racing tracks in multiple photo-realistic environments, orchestration of drone races, comes with a suite of gate assets, allows for multiple sensor modalities (monocular, depth, neuromorphic events, optical flow), different camera models, and benchmarking of planning, control, computer vision, and learning-based algorithms. We used our framework to host a simulation based drone racing competition at NeurIPS 2019. The competition binaries are available at our github repository.

cs.RO↗

arXiv2019

Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification

Federated Learning enables visual models to be trained in a privacy-preserving way using real-world data from mobile devices. Given their distributed nature, the statistics of the data across these devices is likely to differ significantly. In this work, we look at the effect such non-identical data distributions has on visual classification via Federated Learning. We propose a way to synthesize datasets with a continuous range of identicalness and provide performance measures for the Federated Averaging algorithm. We show that performance degrades as distributions differ more, and propose a mitigation strategy via server momentum. Experiments on CIFAR-10 demonstrate improved classification performance over a range of non-identicalness, with classification accuracy improved from 30.1% to 76.9% in the most skewed settings.

cs.LG↗

arXiv2019

Extreme Augmentation : Can deep learning based medical image segmentation be trained using a single manually delineated scan?

Yes, it can. Data augmentation is perhaps the oldest preprocessing step in computer vision literature. Almost every computer vision model trained on imaging data uses some form of augmentation. In this paper, we use the inter-vertebral disk segmentation task alongside a deep residual U-Net as the learning model, to explore the effectiveness of augmentation. In the extreme, we observed that a model trained on patches extracted from just one scan, with each patch augmented 50 times; achieved a Dice score of 0.73 in a validation set of 40 cases. Qualitative evaluation indicated a clinically usable segmentation algorithm, which appropriately segments regions of interest, alongside limited false positive specks. When the initial patches are extracted from nine scans the average Dice coefficient jumps to 0.86 and most of the false positives disappear. While this still falls short of state-of-the-art deep learning based segmentation of discs reported in literature, qualitative examination reveals that it does yield segmentation, which can be amended by expert clinicians with minimal effort to generate additional data for training improved deep models. Extreme augmentation of training data, should thus be construed as a strategy for training deep learning based algorithms, when very little manually annotated data is available to work with. Models trained with extreme augmentation can then be used to accelerate the generation of manually labelled data. Hence, we show that extreme augmentation can be a valuable tool in addressing scaling up small imaging data sets to address medical image segmentation tasks.

cs.CV↗

arXiv2019

Contingency Model Predictive Control for Automated Vehicles

We present Contingency Model Predictive Control (CMPC), a novel and implementable control framework which tracks a desired path while simultaneously maintaining a contingency plan -- an alternate trajectory to avert an identified potential emergency. In this way, CMPC anticipates events that might take place, instead of reacting when emergencies occur. We accomplish this by adding an additional prediction horizon in parallel to the classical receding MPC horizon. The contingency horizon is constrained to maintain a feasible avoidance solution; as such, CMPC is selectively robust to this emergency while tracking the desired path as closely as possible. After defining the framework mathematically, we demonstrate its effectiveness experimentally by comparing its performance to a state-of-the-art deterministic MPC. The controllers drive an automated research platform through a left-hand turn which may be covered by ice. Contingency MPC prepares for the potential loss of friction by purposefully and intuitively deviating from the prescribed path to approach the turn more conservatively; this deviation significantly mitigates the consequence of encountering ice.

eess.SY↗

arXiv2018

Low-Shot Learning with Imprinted Weights

Human vision is able to immediately recognize novel visual categories after seeing just one or a few training examples. We describe how to add a similar capability to ConvNet classifiers by directly setting the final layer weights from novel training examples during low-shot learning. We call this process weight imprinting as it directly sets weights for a new category based on an appropriately scaled copy of the embedding layer activations for that training example. The imprinting process provides a valuable complement to training with stochastic gradient descent, as it provides immediate good classification performance and an initialization for any further fine-tuning in the future. We show how this imprinting process is related to proxy-based embeddings. However, it differs in that only a single imprinted weight vector is learned for each novel category, rather than relying on a nearest-neighbor distance to training instances as typically used with embedding methods. Our experiments show that using averaging of imprinted weights provides better generalization than using nearest-neighbor instance embeddings.

cs.CV↗

arXiv2018

Frame-Recurrent Video Super-Resolution

Recent advances in video super-resolution have shown that convolutional neural networks combined with motion compensation are able to merge information from multiple low-resolution (LR) frames to generate high-quality images. Current state-of-the-art methods process a batch of LR frames to generate a single high-resolution (HR) frame and run this scheme in a sliding window fashion over the entire video, effectively treating the problem as a large number of separate multi-frame super-resolution tasks. This approach has two main weaknesses: 1) Each input frame is processed and warped multiple times, increasing the computational cost, and 2) each output frame is estimated independently conditioned on the input frames, limiting the system's ability to produce temporally consistent results. In this work, we propose an end-to-end trainable frame-recurrent video super-resolution framework that uses the previously inferred HR estimate to super-resolve the subsequent frame. This naturally encourages temporally consistent results and reduces the computational cost by warping only one image in each step. Furthermore, due to its recurrent nature, the proposed method has the ability to assimilate a large number of previous frames without increased computational demands. Extensive evaluations and comparisons with previous methods validate the strengths of our approach and demonstrate that the proposed framework is able to significantly outperform the current state of the art.

cs.CV↗

arXiv2018

Learning to Segment via Cut-and-Paste

This paper presents a weakly-supervised approach to object instance segmentation. Starting with known or predicted object bounding boxes, we learn object masks by playing a game of cut-and-paste in an adversarial learning setup. A mask generator takes a detection box and Faster R-CNN features, and constructs a segmentation mask that is used to cut-and-paste the object into a new image location. The discriminator tries to distinguish between real objects, and those cut and pasted via the generator, giving a learning signal that leads to improved object masks. We verify our method experimentally using Cityscapes, COCO, and aerial image datasets, learning to segment objects without ever having seen a mask in training. Our method exceeds the performance of existing weakly supervised methods, without requiring hand-tuned segment proposals, and reaches 90% of supervised performance.

cs.CV↗

arXiv2017

Deep Reinforcement Learning for Dexterous Manipulation with Concept Networks

Deep reinforcement learning yields great results for a large array of problems, but models are generally retrained anew for each new problem to be solved. Prior learning and knowledge are difficult to incorporate when training new models, requiring increasingly longer training as problems become more complex. This is especially problematic for problems with sparse rewards. We provide a solution to these problems by introducing Concept Network Reinforcement Learning (CNRL), a framework which allows us to decompose problems using a multi-level hierarchy. Concepts in a concept network are reusable, and flexible enough to encapsulate feature extractors, skills, or other concept networks. With this hierarchical learning approach, deep reinforcement learning can be used to solve complex tasks in a modular way, through problem decomposition. We demonstrate the strength of CNRL by training a model to grasp a rectangular prism and precisely stack it on top of a cube using a gripper on a Kinova JACO arm, simulated in MuJoCo. Our experiments show that our use of hierarchy results in a 45x reduction in environment interactions compared to the state-of-the-art on this task.

cs.AI↗

arXiv2017

Unsupervised Learning of Depth and Ego-Motion from Video

We present an unsupervised learning framework for the task of monocular depth and camera motion estimation from unstructured video sequences. We achieve this by simultaneously training depth and camera pose estimation networks using the task of view synthesis as the supervisory signal. The networks are thus coupled via the view synthesis objective during training, but can be applied independently at test time. Empirical evaluation on the KITTI dataset demonstrates the effectiveness of our approach: 1) monocular depth performing comparably with supervised methods that use either ground-truth pose or depth for training, and 2) pose estimation performing favorably with established SLAM systems under comparable input settings.

cs.CV↗

arXiv2017

Efficient generalized Golub-Kahan based methods for dynamic inverse problems

We consider efficient methods for computing solutions to and estimating uncertainties in dynamic inverse problems, where the parameters of interest may change during the measurement procedure. Compared to static inverse problems, incorporating prior information in both space and time in a Bayesian framework can become computationally intensive, in part, due to the large number of unknown parameters. In these problems, explicit computation of the square root and/or inverse of the prior covariance matrix is not possible. In this work, we develop efficient, iterative, matrix-free methods based on the generalized Golub-Kahan bidiagonalization that allow automatic regularization parameter and variance estimation. We demonstrate that these methods can be more flexible than standard methods and develop efficient implementations that can exploit structure in the prior, as well as possible structure in the forward model. Numerical examples from photoacoustic tomography, deblurring, and passive seismic tomography demonstrate the range of applicability and effectiveness of the described approaches. Specifically, in passive seismic tomography, we demonstrate our approach on both synthetic and real data. To demonstrate the scalability of our algorithm, we solve a dynamic inverse problem with approximately $43,000$ measurements and $7.8$ million unknowns in under $40$ seconds on a standard desktop.

math.NA↗

arXiv2017

Pose2Instance: Harnessing Keypoints for Person Instance Segmentation

Human keypoints are a well-studied representation of people.We explore how to use keypoint models to improve instance-level person segmentation. The main idea is to harness the notion of a distance transform of oracle provided keypoints or estimated keypoint heatmaps as a prior for person instance segmentation task within a deep neural network. For training and evaluation, we consider all those images from COCO where both instance segmentation and human keypoints annotations are available. We first show how oracle keypoints can boost the performance of existing human segmentation model during inference without any training. Next, we propose a framework to directly learn a deep instance segmentation model conditioned on human pose. Experimental results show that at various Intersection Over Union (IOU) thresholds, in a constrained environment with oracle keypoints, the instance segmentation accuracy achieves 10% to 12% relative improvements over a strong baseline of oracle bounding boxes. In a more realistic environment, without the oracle keypoints, the proposed deep person instance segmentation model conditioned on human pose achieves 3.8% to 10.5% relative improvements comparing with its strongest baseline of a deep network trained only for segmentation.

cs.CV↗

arXiv2016

Nonrigid Optical Flow Ground Truth for Real-World Scenes with Time-Varying Shading Effects

In this paper we present a dense ground truth dataset of nonrigidly deforming real-world scenes. Our dataset contains both long and short video sequences, and enables the quantitatively evaluation for RGB based tracking and registration methods. To construct ground truth for the RGB sequences, we simultaneously capture Near-Infrared (NIR) image sequences where dense markers - visible only in NIR - represent ground truth positions. This allows for comparison with automatically tracked RGB positions and the formation of error metrics. Most previous datasets containing nonrigidly deforming sequences are based on synthetic data. Our capture protocol enables us to acquire real-world deforming objects with realistic photometric effects - such as blur and illumination change - as well as occlusion and complex deformations. A public evaluation website is constructed to allow for ranking of RGB image based optical flow and other dense tracking algorithms, with various statistical measures. Furthermore, we present an RGB-NIR multispectral optical flow model allowing for energy optimization by adoptively combining featured information from both the RGB and the complementary NIR channels. In our experiments we evaluate eight existing RGB based optical flow methods on our new dataset. We also evaluate our hybrid optical flow algorithm by comparing to two existing multispectral approaches, as well as varying our input channels across RGB, NIR and RGB-NIR.

cs.CV↗

arXiv2016

Drift Robust Non-rigid Optical Flow Enhancement for Long Sequences

It is hard to densely track a nonrigid object in long term, which is a fundamental research issue in the computer vision community. This task often relies on estimating pairwise correspondences between images over time where the error is accumulated and leads to a drift issue. In this paper, we introduce a novel optimization framework with an Anchor Patch constraint. It is supposed to significantly reduce overall errors given long sequences containing non-rigidly deformable objects. Our framework can be applied to any dense tracking algorithm, e.g. optical flow. We demonstrate the success of our approach by showing significant error reduction on 6 popular optical flow algorithms applied to a range of real-world nonrigid benchmarks. We also provide quantitative analysis of our approach given synthetic occlusions and image noise.

cs.CV↗

arXiv2016

Decision Forests, Convolutional Networks and the Models in-Between

This paper investigates the connections between two state of the art classifiers: decision forests (DFs, including decision jungles) and convolutional neural networks (CNNs). Decision forests are computationally efficient thanks to their conditional computation property (computation is confined to only a small region of the tree, the nodes along a single branch). CNNs achieve state of the art accuracy, thanks to their representation learning capabilities. We present a systematic analysis of how to fuse conditional computation with representation learning and achieve a continuum of hybrid models with different ratios of accuracy vs. efficiency. We call this new family of hybrid models conditional networks. Conditional networks can be thought of as: i) decision trees augmented with data transformation operators, or ii) CNNs, with block-diagonal sparse weight matrices, and explicit data routing functions. Experimental validation is performed on the common task of image classification on both the CIFAR and Imagenet datasets. Compared to state of the art CNNs, our hybrid models yield the same accuracy with a fraction of the compute cost and much smaller number of parameters.

cs.CV↗

arXiv2013

Discovering Minimal Universal Extra Dimensions (MUED) at the LHC

In this work we discuss our consistent implementation of the minimal model of Universal Extra Dimensions in CalcHEP. We pay special attention to the gauge invariance issues that arise due to the incorporation of 5D quantum corrections. After validating the implementation we perform a complete study of the tri-lepton signature, including a realistic estimate of the backgrounds, for the present LHC energy and luminosity. We also derive the expected LHC discovery reach for different luminosities, at centre-of-mass energies of both 7 TeV and 8 TeV.

hep-ph↗

arXiv2012

Testing Minimal Universal Extra Dimensions Using Higgs Boson Searches at the LHC

Large Hadron Collider (LHC) searches for the SM Higgs boson provide a powerful limit on models involving Universal Extra Dimensions (UED) where the Higgs production is enhanced. We have evaluated all one-loop diagrams for Higgs production from gluon fusion and decay to two photons within "minimal" UED (mUED), independently confirming previous results, and we have evaluated enhancement factors for Higgs boson production and decay over the mUED parameter space. Using these we have derived limits on the parameter space, combining data from both ATLAS and CMS collaborations for the most recent 7 TeV and 8 TeV LHC data. We have performed a rigorous statistical combination of several Higgs boson search channels which is important because mUED signatures from the Higgs boson are not universally enhanced. We have found that 1/R < 500 GeV is excluded at 95% CL, while for larger 1/R only a very narrow (\pm1-4 GeV) mass window around m_h = 125 GeV and another window (up to 2 GeV wide for 1/R > 1000 GeV) around m_h = 118 GeV are left. The latter is likely to be excluded as more data becomes available whereas the region around 125 GeV is where the recently discovered Higgs-like particle was observed and therefore where the exclusion limit is weaker. It is worth stressing that mUED predicts an enhancement for all channels for Higgs production by gluon fusion and decay while the vector boson fusion process WW/ZZ -> h -> AA is generically suppressed and WW/ZZ -> h -> WW*/ZZ* is standard. Therefore, as more 8 TeV LHC data becomes available, the information on individual Higgs boson production and decay processes provided by the CMS and ATLAS experiments can be effectively used to favour mUED or exclude it further.

hep-ph↗

arXiv2010

Energies of the first row atoms from quantum Monte Carlo

All-electron variational and diffusion quantum Monte Carlo calculations of the ground state energies of the first row atoms (Li to Ne) are reported. We use trial wavefunctions of four types: single determinant Slater-Jastrow wavefunctions; multi-determinant Slater-Jastrow wavefunctions; single determinant Slater-Jastrow wavefunctions with backflow transformations; multi-determinant Slater-Jastrow wavefunctions with backflow transformations. At the diffusion quantum Monte Carlo level and using our best trial wavefunctions we recover 99% or more of the correlation energy for Li, Be, B, C, N, and Ne, 97% for O, and 98% for F.

cond-mat.mtrl-sci↗