arXiv subjects

Robert P. Dick

Publications and source records attributed to Robert P. Dick.

27 records · Page 2Linked to original sources

arXiv2021

Beyond BatchNorm: Towards a Unified Understanding of Normalization in Deep Learning

Inspired by BatchNorm, there has been an explosion of normalization layers in deep learning. Recent works have identified a multitude of beneficial properties in BatchNorm to explain its success. However, given the pursuit of alternative normalization layers, these properties need to be generalized so that any given layer's success/failure can be accurately predicted. In this work, we take a first step towards this goal by extending known properties of BatchNorm in randomly initialized deep neural networks (DNNs) to several recently proposed normalization layers. Our primary findings follow: (i) similar to BatchNorm, activations-based normalization layers can prevent exponential growth of activations in ResNets, but parametric techniques require explicit remedies; (ii) use of GroupNorm can ensure an informative forward propagation, with different samples being assigned dissimilar activations, but increasing group size results in increasingly indistinguishable activations for different samples, explaining slow convergence speed in models with LayerNorm; and (iii) small group sizes result in large gradient norm in earlier layers, hence explaining training instability issues in Instance Normalization and illustrating a speed-stability tradeoff in GroupNorm. Overall, our analysis reveals a unified set of mechanisms that underpin the success of normalization methods in deep learning, providing us with a compass to systematically explore the vast design space of DNN normalization layers.

cs.LG↗

arXiv2021

HVAQ: A High-Resolution Vision-Based Air Quality Dataset

Air pollutants, such as particulate matter, negatively impact human health. Most existing pollution monitoring techniques use stationary sensors, which are typically sparsely deployed. However, real-world pollution distributions vary rapidly with position and the visual effects of air pollution can be used to estimate concentration, potentially at high spatial resolution. Accurate pollution monitoring requires either densely deployed conventional point sensors, at-a-distance vision-based pollution monitoring, or a combination of both. The main contribution of this paper is that to the best of our knowledge, it is the first publicly available, high temporal and spatial resolution air quality dataset containing simultaneous point sensor measurements and corresponding images. The dataset enables, for the first time, high spatial resolution evaluation of image-based air pollution estimation algorithms. It contains PM2.5, PM10, temperature, and humidity data. We evaluate several state-of-art vision-based PM concentration estimation algorithms on our dataset and quantify the increase in accuracy resulting from higher point sensor density and the use of images. It is our intent and belief that this dataset can enable advances by other research teams working on air quality estimation. Our dataset is available at https://github.com/implicitDeclaration/HVAQ-dataset/tree/master.

cs.CV↗

arXiv2021

MemX: An Attention-Aware Smart Eyewear System for Personalized Moment Auto-capture

This work presents MemX: a biologically-inspired attention-aware eyewear system developed with the goal of pursuing the long-awaited vision of a personalized visual Memex. MemX captures human visual attention on the fly, analyzes the salient visual content, and records moments of personal interest in the form of compact video snippets. Accurate attentive scene detection and analysis on resource-constrained platforms is challenging because these tasks are computation and energy intensive. We propose a new temporal visual attention network that unifies human visual attention tracking and salient visual content analysis. Attention tracking focuses computation-intensive video analysis on salient regions, while video analysis makes human attention detection and tracking more accurate. Using the YouTube-VIS dataset and 30 participants, we experimentally show that MemX significantly improves the attention tracking accuracy over the eye-tracking-alone method, while maintaining high system energy efficiency. We have also conducted 11 in-field pilot studies across a range of daily usage scenarios, which demonstrate the feasibility and potential benefits of MemX.

cs.CV↗

arXiv2021

A Gradient Flow Framework For Analyzing Network Pruning

Recent network pruning methods focus on pruning models early-on in training. To estimate the impact of removing a parameter, these methods use importance measures that were originally designed to prune trained models. Despite lacking justification for their use early-on in training, such measures result in surprisingly low accuracy loss. To better explain this behavior, we develop a general framework that uses gradient flow to unify state-of-the-art importance measures through the norm of model parameters. We use this framework to determine the relationship between pruning measures and evolution of model parameters, establishing several results related to pruning models early-on in training: (i) magnitude-based pruning removes parameters that contribute least to reduction in loss, resulting in models that converge faster than magnitude-agnostic methods; (ii) loss-preservation based pruning preserves first-order model evolution dynamics and is therefore appropriate for pruning minimally trained models; and (iii) gradient-norm based pruning affects second-order model evolution dynamics, such that increasing gradient norm via pruning can produce poorly performing models. We validate our claims on several VGG-13, MobileNet-V1, and ResNet-56 models trained on CIFAR-10/CIFAR-100. Code available at https://github.com/EkdeepSLubana/flowandprune.

cs.LG↗

arXiv2021

A Reinforcement-Learning-Based Energy-Efficient Framework for Multi-Task Video Analytics Pipeline

Deep-learning-based video processing has yielded transformative results in recent years. However, the video analytics pipeline is energy-intensive due to high data rates and reliance on complex inference algorithms, which limits its adoption in energy-constrained applications. Motivated by the observation of high and variable spatial redundancy and temporal dynamics in video data streams, we design and evaluate an adaptive-resolution optimization framework to minimize the energy use of multi-task video analytics pipelines. Instead of heuristically tuning the input data resolution of individual tasks, our framework utilizes deep reinforcement learning to dynamically govern the input resolution and computation of the entire video analytics pipeline. By monitoring the impact of varying resolution on the quality of high-dimensional video analytics features, hence the accuracy of video analytics results, the proposed end-to-end optimization framework learns the best non-myopic policy for dynamically controlling the resolution of input video streams to globally optimize energy efficiency. Governed by reinforcement learning, optical flow is incorporated into the framework to minimize unnecessary spatio-temporal redundancy that leads to re-computation, while preserving accuracy. The proposed framework is applied to video instance segmentation which is one of the most challenging computer vision tasks, and achieves better energy efficiency than all baseline methods of similar accuracy on the YouTube-VIS dataset.

cs.CV↗

arXiv2020

OrthoReg: Robust Network Pruning Using Orthonormality Regularization

Network pruning in Convolutional Neural Networks (CNNs) has been extensively investigated in recent years. To determine the impact of pruning a group of filters on a network's accuracy, state-of-the-art pruning methods consistently assume filters of a CNN are independent. This allows the importance of a group of filters to be estimated as the sum of importances of individual filters. However, overparameterization in modern networks results in highly correlated filters that invalidate this assumption, thereby resulting in incorrect importance estimates. To address this issue, we propose OrthoReg, a principled regularization strategy that enforces orthonormality on a network's filters to reduce inter-filter correlation, thereby allowing reliable, efficient determination of group importance estimates, improved trainability of pruned networks, and efficient, simultaneous pruning of large groups of filters. When used for iterative pruning on VGG-13, MobileNet-V1, and ResNet-34, OrthoReg consistently outperforms five baseline techniques, including the state-of-the-art, on CIFAR-100 and Tiny-ImageNet. For the recently proposed Early-Bird Ticket hypothesis, which claims networks become amenable to pruning early-on in training and can be pruned after a few epochs to minimize training expenditure, we find OrthoReg significantly outperforms prior work. Code available at https://github.com/EkdeepSLubana/OrthoReg.

cs.CV↗

arXiv2014

The Mason Test: A Defense Against Sybil Attacks in Wireless Networks Without Trusted Authorities

Wireless networks are vulnerable to Sybil attacks, in which a malicious node poses as many identities in order to gain disproportionate influence. Many defenses based on spatial variability of wireless channels exist, but depend either on detailed, multi-tap channel estimation - something not exposed on commodity 802.11 devices - or valid RSSI observations from multiple trusted sources, e.g., corporate access points - something not directly available in ad hoc and delay-tolerant networks with potentially malicious neighbors. We extend these techniques to be practical for wireless ad hoc networks of commodity 802.11 devices. Specifically, we propose two efficient methods for separating the valid RSSI observations of behaving nodes from those falsified by malicious participants. Further, we note that prior signalprint methods are easily defeated by mobile attackers and develop an appropriate challenge-response defense. Finally, we present the Mason test, the first implementation of these techniques for ad hoc and delay-tolerant networks of commodity 802.11 devices. We illustrate its performance in several real-world scenarios.

cs.CR↗

arXiv2014

Performance Analysis of Location Profile Routing

We propose using the predictability of human motion to eliminate the overhead of distributed location services in human-carried MANETs, dubbing the technique location profile routing. This method outperforms the Geographic Hashing Location Service when nodes change locations 2x more frequently than they initiate connections (e.g., start new TCP streams), as in applications like text- and instant-messaging. Prior characterizations of human mobility are used to show that location profile routing achieves a 93% delivery ratio with a 1.75x first-packet latency increase relative to an oracle location service.

cs.NI↗

arXiv2014

Aggregate Characterization of User Behavior in Twitter and Analysis of the Retweet Graph

Most previous analysis of Twitter user behavior is focused on individual information cascades and the social followers graph. We instead study aggregate user behavior and the retweet graph with a focus on quantitative descriptions. We find that the lifetime tweet distribution is a type-II discrete Weibull stemming from a power law hazard function, the tweet rate distribution, although asymptotically power law, exhibits a lognormal cutoff over finite sample intervals, and the inter-tweet interval distribution is power law with exponential cutoff. The retweet graph is small-world and scale-free, like the social graph, but is less disassortative and has much stronger clustering. These differences are consistent with it better capturing the real-world social relationships of and trust between users. Beyond just understanding and modeling human communication patterns and social networks, applications for alternative, decentralized microblogging systems-both predicting real-word performance and detecting spam-are discussed.

cs.SI↗