Paper Group ANR 1244
Robust Temporal Difference Learning for Critical Domains. $L^γ$-PageRank for Semi-Supervised Learning. FASTER: Fusion AnalyticS for public Transport Event Response. Adversarial Distillation for Ordered Top-k Attacks. Augment-Reinforce-Merge Policy Gradient for Binary Stochastic Policy. Sparse linear regression with compressed and low-precision data …
Robust Temporal Difference Learning for Critical Domains
| Title | Robust Temporal Difference Learning for Critical Domains |
| Authors | Richard Klima, Daan Bloembergen, Michael Kaisers, Karl Tuyls |
| Abstract | We present a new Q-function operator for temporal difference (TD) learning methods that explicitly encodes robustness against significant rare events (SRE) in critical domains. The operator, which we call the $\kappa$-operator, allows to learn a robust policy in a model-based fashion without actually observing the SRE. We introduce single- and multi-agent robust TD methods using the operator $\kappa$. We prove convergence of the operator to the optimal robust Q-function with respect to the model using the theory of Generalized Markov Decision Processes. In addition we prove convergence to the optimal Q-function of the original MDP given that the probability of SREs vanishes. Empirical evaluations demonstrate the superior performance of $\kappa$-based TD methods both in the early learning phase as well as in the final converged stage. In addition we show robustness of the proposed method to small model errors, as well as its applicability in a multi-agent context. |
| Tasks | |
| Published | 2019-01-23 |
| URL | http://arxiv.org/abs/1901.08021v2 |
| http://arxiv.org/pdf/1901.08021v2.pdf | |
| PWC | https://paperswithcode.com/paper/robust-temporal-difference-learning-for |
| Repo | |
| Framework | |
$L^γ$-PageRank for Semi-Supervised Learning
| Title | $L^γ$-PageRank for Semi-Supervised Learning |
| Authors | Esteban Bautista, Patrice Abry, Paulo Gonçalves |
| Abstract | PageRank for Semi-Supervised Learning has shown to leverage data structures and limited tagged examples to yield meaningful classification. Despite successes, classification performance can still be improved, particularly in cases of fuzzy graphs or unbalanced labeled data. To address such limitations, a novel approach based on powers of the Laplacian matrix $L^\gamma$ ($\gamma > 0$), referred to as $L^\gamma$-PageRank, is proposed. Its theoretical study shows that it operates on signed graphs, where nodes belonging to one same class are more likely to share positive edges while nodes from different classes are more likely to be connected with negative edges. It is shown that by selecting an optimal $\gamma$, classification performance can be significantly enhanced. A procedure for the automated estimation of the optimal $\gamma$, from a unique observation of data, is devised and assessed. Experiments on several datasets demonstrate the effectiveness of both $L^\gamma$-PageRank classification and the optimal $\gamma$ estimation. |
| Tasks | |
| Published | 2019-03-11 |
| URL | http://arxiv.org/abs/1903.06007v1 |
| http://arxiv.org/pdf/1903.06007v1.pdf | |
| PWC | https://paperswithcode.com/paper/l-pagerank-for-semi-supervised-learning |
| Repo | |
| Framework | |
FASTER: Fusion AnalyticS for public Transport Event Response
| Title | FASTER: Fusion AnalyticS for public Transport Event Response |
| Authors | Sebastien Blandin, Laura Wynter, Hasan Poonawala, Sean Laguna, Basile Dura |
| Abstract | Increasing urban concentration raises operational challenges that can benefit from integrated monitoring and decision support. Such complex systems need to leverage the full stack of analytical methods, from state estimation using multi-sensor fusion for situational awareness, to prediction and computation of optimal responses. The FASTER platform that we describe in this work, deployed at nation scale and handling 1.5 billion public transport trips a year, offers such a full stack of techniques for this large-scale, real-time problem. FASTER provides fine-grained situational awareness and real-time decision support with the objective of improving the public transport commuter experience. The methods employed range from statistical machine learning to agent-based simulation and mixed-integer optimization. In this work we present an overview of the challenges and methods involved, with details of the commuter movement prediction module, as well as a discussion of open problems. |
| Tasks | Sensor Fusion |
| Published | 2019-05-14 |
| URL | https://arxiv.org/abs/1906.03040v1 |
| https://arxiv.org/pdf/1906.03040v1.pdf | |
| PWC | https://paperswithcode.com/paper/faster-fusion-analytics-for-public-transport |
| Repo | |
| Framework | |
Adversarial Distillation for Ordered Top-k Attacks
| Title | Adversarial Distillation for Ordered Top-k Attacks |
| Authors | Zekun Zhang, Tianfu Wu |
| Abstract | Deep Neural Networks (DNNs) are vulnerable to adversarial attacks, especially white-box targeted attacks. One scheme of learning attacks is to design a proper adversarial objective function that leads to the imperceptible perturbation for any test image (e.g., the Carlini-Wagner (C&W) method). Most methods address targeted attacks in the Top-1 manner. In this paper, we propose to learn ordered Top-k attacks (k>= 1) for image classification tasks, that is to enforce the Top-k predicted labels of an adversarial example to be the k (randomly) selected and ordered labels (the ground-truth label is exclusive). To this end, we present an adversarial distillation framework: First, we compute an adversarial probability distribution for any given ordered Top-k targeted labels with respect to the ground-truth of a test image. Then, we learn adversarial examples by minimizing the Kullback-Leibler (KL) divergence together with the perturbation energy penalty, similar in spirit to the network distillation method. We explore how to leverage label semantic similarities in computing the targeted distributions, leading to knowledge-oriented attacks. In experiments, we thoroughly test Top-1 and Top-5 attacks in the ImageNet-1000 validation dataset using two popular DNNs trained with clean ImageNet-1000 train dataset, ResNet-50 and DenseNet-121. For both models, our proposed adversarial distillation approach outperforms the C&W method in the Top-1 setting, as well as other baseline methods. Our approach shows significant improvement in the Top-5 setting against a strong modified C&W method. |
| Tasks | Image Classification |
| Published | 2019-05-25 |
| URL | https://arxiv.org/abs/1905.10695v1 |
| https://arxiv.org/pdf/1905.10695v1.pdf | |
| PWC | https://paperswithcode.com/paper/adversarial-distillation-for-ordered-top-k |
| Repo | |
| Framework | |
Augment-Reinforce-Merge Policy Gradient for Binary Stochastic Policy
| Title | Augment-Reinforce-Merge Policy Gradient for Binary Stochastic Policy |
| Authors | Yunhao Tang, Mingzhang Yin, Mingyuan Zhou |
| Abstract | Due to the high variance of policy gradients, on-policy optimization algorithms are plagued with low sample efficiency. In this work, we propose Augment-Reinforce-Merge (ARM) policy gradient estimator as an unbiased low-variance alternative to previous baseline estimators on tasks with binary action space, inspired by the recent ARM gradient estimator for discrete random variable models. We show that the ARM policy gradient estimator achieves variance reduction with theoretical guarantees, and leads to significantly more stable and faster convergence of policies parameterized by neural networks. |
| Tasks | |
| Published | 2019-03-13 |
| URL | http://arxiv.org/abs/1903.05284v1 |
| http://arxiv.org/pdf/1903.05284v1.pdf | |
| PWC | https://paperswithcode.com/paper/augment-reinforce-merge-policy-gradient-for |
| Repo | |
| Framework | |
Sparse linear regression with compressed and low-precision data via concave quadratic programming
| Title | Sparse linear regression with compressed and low-precision data via concave quadratic programming |
| Authors | Vito Cerone, Sophie M. Fosson, Diego Regruto |
| Abstract | We consider the problem of the recovery of a k-sparse vector from compressed linear measurements when data are corrupted by a quantization noise. When the number of measurements is not sufficiently large, different $k$-sparse solutions may be present in the feasible set, and the classical l1 approach may be unsuccessful. For this motivation, we propose a non-convex quadratic programming method, which exploits prior information on the magnitude of the non-zero parameters. This results in a more efficient support recovery. We provide sufficient conditions for successful recovery and numerical simulations to illustrate the practical feasibility of the proposed method. |
| Tasks | Quantization |
| Published | 2019-09-09 |
| URL | https://arxiv.org/abs/1909.03705v1 |
| https://arxiv.org/pdf/1909.03705v1.pdf | |
| PWC | https://paperswithcode.com/paper/sparse-linear-regression-with-compressed-and |
| Repo | |
| Framework | |
Distributionally Robust Counterfactual Risk Minimization
| Title | Distributionally Robust Counterfactual Risk Minimization |
| Authors | Louis Faury, Ugo Tanielian, Flavian Vasile, Elena Smirnova, Elvis Dohmatob |
| Abstract | This manuscript introduces the idea of using Distributionally Robust Optimization (DRO) for the Counterfactual Risk Minimization (CRM) problem. Tapping into a rich existing literature, we show that DRO is a principled tool for counterfactual decision making. We also show that well-established solutions to the CRM problem like sample variance penalization schemes are special instances of a more general DRO problem. In this unifying framework, a variety of distributionally robust counterfactual risk estimators can be constructed using various probability distances and divergences as uncertainty measures. We propose the use of Kullback-Leibler divergence as an alternative way to model uncertainty in CRM and derive a new robust counterfactual objective. In our experiments, we show that this approach outperforms the state-of-the-art on four benchmark datasets, validating the relevance of using other uncertainty measures in practical applications. |
| Tasks | Decision Making |
| Published | 2019-06-14 |
| URL | https://arxiv.org/abs/1906.06211v2 |
| https://arxiv.org/pdf/1906.06211v2.pdf | |
| PWC | https://paperswithcode.com/paper/distributionally-robust-counterfactual-risk |
| Repo | |
| Framework | |
Frame-wise Motion and Appearance for Real-time Multiple Object Tracking
| Title | Frame-wise Motion and Appearance for Real-time Multiple Object Tracking |
| Authors | Jimuyang Zhang, Sanping Zhou, Jinjun Wang, Dong Huang |
| Abstract | The main challenge of Multiple Object Tracking (MOT) is the efficiency in associating indefinite number of objects between video frames. Standard motion estimators used in tracking, e.g., Long Short Term Memory (LSTM), only deal with single object, while Re-IDentification (Re-ID) based approaches exhaustively compare object appearances. Both approaches are computationally costly when they are scaled to a large number of objects, making it very difficult for real-time MOT. To address these problems, we propose a highly efficient Deep Neural Network (DNN) that simultaneously models association among indefinite number of objects. The inference computation of the DNN does not increase with the number of objects. Our approach, Frame-wise Motion and Appearance (FMA), computes the Frame-wise Motion Fields (FMF) between two frames, which leads to very fast and reliable matching among a large number of object bounding boxes. As auxiliary information is used to fix uncertain matches, Frame-wise Appearance Features (FAF) are learned in parallel with FMFs. Extensive experiments on the MOT17 benchmark show that our method achieved real-time MOT with competitive results as the state-of-the-art approaches. |
| Tasks | Multiple Object Tracking, Object Tracking |
| Published | 2019-05-06 |
| URL | https://arxiv.org/abs/1905.02292v1 |
| https://arxiv.org/pdf/1905.02292v1.pdf | |
| PWC | https://paperswithcode.com/paper/frame-wise-motion-and-appearance-for-real |
| Repo | |
| Framework | |
Deep Multi-Magnification Networks for Multi-Class Breast Cancer Image Segmentation
| Title | Deep Multi-Magnification Networks for Multi-Class Breast Cancer Image Segmentation |
| Authors | David Joon Ho, Dig V. K. Yarlagadda, Timothy M. D’Alfonso, Matthew G. Hanna, Anne Grabenstetter, Peter Ntiamoah, Edi Brogi, Lee K. Tan, Thomas J. Fuchs |
| Abstract | Breast carcinoma is one of the most common cancers for women in the United States. Pathologic analysis of surgical excision specimens for breast carcinoma is important to evaluate the completeness of surgical excision and has implications for future treatment. This analysis is performed manually by pathologists reviewing histologic slides prepared from formalin-fixed tissue. Digital pathology has provided means to digitize the glass slides and generate whole slide images. Computational pathology enables whole slide images to be automatically analyzed to assist pathologists, especially with the advancement of deep learning. The whole slide images generally contain giga-pixels of data, so it is impractical to process the images at the whole-slide-level. Most of the current deep learning techniques process the images at the patch-level, but they may produce poor results by looking at individual patches with a narrow field-of-view at a single magnification. In this paper, we present Deep Multi-Magnification Networks (DMMNs) to resemble how pathologists analyze histologic slides using microscopes. Our multi-class tissue segmentation architecture processes a set of patches from multiple magnifications to make more accurate predictions. For our supervised training, we use partial annotations to reduce the burden of annotators. Our segmentation architecture with multi-encoder, multi-decoder, and multi-concatenation outperforms other segmentation architectures on breast datasets and can be used to facilitate pathologists’ assessments of breast cancer. |
| Tasks | |
| Published | 2019-10-29 |
| URL | https://arxiv.org/abs/1910.13042v1 |
| https://arxiv.org/pdf/1910.13042v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-multi-magnification-networks-for-multi |
| Repo | |
| Framework | |
Streaming 1.9 Billion Hypersparse Network Updates per Second with D4M
| Title | Streaming 1.9 Billion Hypersparse Network Updates per Second with D4M |
| Authors | Jeremy Kepner, Vijay Gadepally, Lauren Milechin, Siddharth Samsi, William Arcand, David Bestor, William Bergeron, Chansup Byun, Matthew Hubbell, Michael Houle, Michael Jones, Anne Klein, Peter Michaleas, Julie Mullen, Andrew Prout, Antonio Rosa, Charles Yee, Albert Reuther |
| Abstract | The Dynamic Distributed Dimensional Data Model (D4M) library implements associative arrays in a variety of languages (Python, Julia, and Matlab/Octave) and provides a lightweight in-memory database implementation of hypersparse arrays that are ideal for analyzing many types of network data. D4M relies on associative arrays which combine properties of spreadsheets, databases, matrices, graphs, and networks, while providing rigorous mathematical guarantees, such as linearity. Streaming updates of D4M associative arrays put enormous pressure on the memory hierarchy. This work describes the design and performance optimization of an implementation of hierarchical associative arrays that reduces memory pressure and dramatically increases the update rate into an associative array. The parameters of hierarchical associative arrays rely on controlling the number of entries in each level in the hierarchy before an update is cascaded. The parameters are easily tunable to achieve optimal performance for a variety of applications. Hierarchical arrays achieve over 40,000 updates per second in a single instance. Scaling to 34,000 instances of hierarchical D4M associative arrays on 1,100 server nodes on the MIT SuperCloud achieved a sustained update rate of 1,900,000,000 updates per second. This capability allows the MIT SuperCloud to analyze extremely large streaming network data sets. |
| Tasks | |
| Published | 2019-07-06 |
| URL | https://arxiv.org/abs/1907.04217v1 |
| https://arxiv.org/pdf/1907.04217v1.pdf | |
| PWC | https://paperswithcode.com/paper/streaming-19-billion-hypersparse-network |
| Repo | |
| Framework | |
Spatial-Temporal Relation Networks for Multi-Object Tracking
| Title | Spatial-Temporal Relation Networks for Multi-Object Tracking |
| Authors | Jiarui Xu, Yue Cao, Zheng Zhang, Han Hu |
| Abstract | Recent progress in multiple object tracking (MOT) has shown that a robust similarity score is key to the success of trackers. A good similarity score is expected to reflect multiple cues, e.g. appearance, location, and topology, over a long period of time. However, these cues are heterogeneous, making them hard to be combined in a unified network. As a result, existing methods usually encode them in separate networks or require a complex training approach. In this paper, we present a unified framework for similarity measurement which could simultaneously encode various cues and perform reasoning across both spatial and temporal domains. We also study the feature representation of a tracklet-object pair in depth, showing a proper design of the pair features can well empower the trackers. The resulting approach is named spatial-temporal relation networks (STRN). It runs in a feed-forward way and can be trained in an end-to-end manner. The state-of-the-art accuracy was achieved on all of the MOT15-17 benchmarks using public detection and online settings. |
| Tasks | Multi-Object Tracking, Multiple Object Tracking, Object Tracking |
| Published | 2019-04-25 |
| URL | http://arxiv.org/abs/1904.11489v1 |
| http://arxiv.org/pdf/1904.11489v1.pdf | |
| PWC | https://paperswithcode.com/paper/spatial-temporal-relation-networks-for-multi |
| Repo | |
| Framework | |
Intelligent Intersection: Two-Stream Convolutional Networks for Real-time Near Accident Detection in Traffic Video
| Title | Intelligent Intersection: Two-Stream Convolutional Networks for Real-time Near Accident Detection in Traffic Video |
| Authors | Xiaohui Huang, Pan He, Anand Rangarajan, Sanjay Ranka |
| Abstract | In Intelligent Transportation System, real-time systems that monitor and analyze road users become increasingly critical as we march toward the smart city era. Vision-based frameworks for Object Detection, Multiple Object Tracking, and Traffic Near Accident Detection are important applications of Intelligent Transportation System, particularly in video surveillance and etc. Although deep neural networks have recently achieved great success in many computer vision tasks, a uniformed framework for all the three tasks is still challenging where the challenges multiply from demand for real-time performance, complex urban setting, highly dynamic traffic event, and many traffic movements. In this paper, we propose a two-stream Convolutional Network architecture that performs real-time detection, tracking, and near accident detection of road users in traffic video data. The two-stream model consists of a spatial stream network for Object Detection and a temporal stream network to leverage motion features for Multiple Object Tracking. We detect near accidents by incorporating appearance features and motion features from two-stream networks. Using aerial videos, we propose a Traffic Near Accident Dataset (TNAD) covering various types of traffic interactions that is suitable for vision-based traffic analysis tasks. Our experiments demonstrate the advantage of our framework with an overall competitive qualitative and quantitative performance at high frame rates on the TNAD dataset. |
| Tasks | Multiple Object Tracking, Object Detection, Object Tracking |
| Published | 2019-01-04 |
| URL | http://arxiv.org/abs/1901.01138v1 |
| http://arxiv.org/pdf/1901.01138v1.pdf | |
| PWC | https://paperswithcode.com/paper/intelligent-intersection-two-stream |
| Repo | |
| Framework | |
Twitter Job/Employment Corpus: A Dataset of Job-Related Discourse Built with Humans in the Loop
| Title | Twitter Job/Employment Corpus: A Dataset of Job-Related Discourse Built with Humans in the Loop |
| Authors | Tong Liu, Christopher M. Homan |
| Abstract | We present the Twitter Job/Employment Corpus, a collection of tweets annotated by a humans-in-the-loop supervised learning framework that integrates crowdsourcing contributions and expertise on the local community and employment environment. Previous computational studies of job-related phenomena have used corpora collected from workplace social media that are hosted internally by the employers, and so lacks independence from latent job-related coercion and the broader context that an open domain, general-purpose medium such as Twitter provides. Our new corpus promises to be a benchmark for the extraction of job-related topics and advanced analysis and modeling, and can potentially benefit a wide range of research communities in the future. |
| Tasks | |
| Published | 2019-01-30 |
| URL | http://arxiv.org/abs/1901.10619v1 |
| http://arxiv.org/pdf/1901.10619v1.pdf | |
| PWC | https://paperswithcode.com/paper/twitter-jobemployment-corpus-a-dataset-of-job |
| Repo | |
| Framework | |
Person-in-WiFi: Fine-grained Person Perception using WiFi
| Title | Person-in-WiFi: Fine-grained Person Perception using WiFi |
| Authors | Fei Wang, Sanping Zhou, Stanislav Panev, Jinsong Han, Dong Huang |
| Abstract | Fine-grained person perception such as body segmentation and pose estimation has been achieved with many 2D and 3D sensors such as RGB/depth cameras, radars (e.g., RF-Pose) and LiDARs. These sensors capture 2D pixels or 3D point clouds of person bodies with high spatial resolution, such that the existing Convolutional Neural Networks can be directly applied for perception. In this paper, we take one step forward to show that fine-grained person perception is possible even with 1D sensors: WiFi antennas. To our knowledge, this is the first work to perceive persons with pervasive WiFi devices, which is cheaper and power efficient than radars and LiDARs, invariant to illumination, and has little privacy concern comparing to cameras. We used two sets of off-the-shelf WiFi antennas to acquire signals, i.e., one transmitter set and one receiver set. Each set contains three antennas lined-up as a regular household WiFi router. The WiFi signal generated by a transmitter antenna, penetrates through and reflects on human bodies, furniture and walls, and then superposes at a receiver antenna as a 1D signal sample (instead of 2D pixels or 3D point clouds). We developed a deep learning approach that uses annotations on 2D images, takes the received 1D WiFi signals as inputs, and performs body segmentation and pose estimation in an end-to-end manner. Experimental results on over 100000 frames under 16 indoor scenes demonstrate that Person-in-WiFi achieved person perception comparable to approaches using 2D images. |
| Tasks | Pose Estimation, RF-based Pose Estimation |
| Published | 2019-03-30 |
| URL | http://arxiv.org/abs/1904.00276v1 |
| http://arxiv.org/pdf/1904.00276v1.pdf | |
| PWC | https://paperswithcode.com/paper/person-in-wifi-fine-grained-person-perception |
| Repo | |
| Framework | |
Dynamics of Pedestrian Crossing Decisions Based on Vehicle Trajectories in Large-Scale Simulated and Real-World Data
| Title | Dynamics of Pedestrian Crossing Decisions Based on Vehicle Trajectories in Large-Scale Simulated and Real-World Data |
| Authors | Jack Terwilliger, Michael Glazer, Henri Schmidt, Josh Domeyer, Heishiro Toyoda, Bruce Mehler, Bryan Reimer, Lex Fridman |
| Abstract | Humans, as both pedestrians and drivers, generally skillfully navigate traffic intersections. Despite the uncertainty, danger, and the non-verbal nature of communication commonly found in these interactions, there are surprisingly few collisions considering the total number of interactions. As the role of automation technology in vehicles grows, it becomes increasingly critical to understand the relationship between pedestrian and driver behavior: how pedestrians perceive the actions of a vehicle/driver and how pedestrians make crossing decisions. The relationship between time-to-arrival (TTA) and pedestrian gap acceptance (i.e., whether a pedestrian chooses to cross under a given window of time to cross) has been extensively investigated. However, the dynamic nature of vehicle trajectories in the context of non-verbal communication has not been systematically explored. Our work provides evidence that trajectory dynamics, such as changes in TTA, can be powerful signals in the non-verbal communication between drivers and pedestrians. Moreover, we investigate these effects in both simulated and real-world datasets, both larger than have previously been considered in literature to the best of our knowledge. |
| Tasks | |
| Published | 2019-04-08 |
| URL | http://arxiv.org/abs/1904.04202v1 |
| http://arxiv.org/pdf/1904.04202v1.pdf | |
| PWC | https://paperswithcode.com/paper/dynamics-of-pedestrian-crossing-decisions |
| Repo | |
| Framework | |
