January 28, 2020

3293 words 16 mins read

Paper Group ANR 1036

Learning Multi-Object Tracking and Segmentation from Automatic Annotations. Deep reinforcement learning in World-Earth system models to discover sustainable management strategies. Predicting Landslides Using Contour Aligning Convolutional Neural Networks. Image-Based Feature Representation for Insider Threat Classification. Improving a tf-idf weigh …

Learning Multi-Object Tracking and Segmentation from Automatic Annotations


Title	Learning Multi-Object Tracking and Segmentation from Automatic Annotations
Authors	Lorenzo Porzi, Markus Hofinger, Idoia Ruiz, Joan Serrat, Samuel Rota Bulò, Peter Kontschieder
Abstract	In this work we contribute a novel pipeline to automatically generate training data, and to improve over state-of-the-art multi-object tracking and segmentation (MOTS) methods. Our proposed track mining algorithm turns raw street-level videos into high-fidelity MOTS training data, is scalable and overcomes the need of expensive and time-consuming manual annotation approaches. We leverage state-of-the-art instance segmentation results in combination with optical flow predictions, also trained on automatically harvested training data. Our second major contribution is MOTSNet - a deep learning, tracking-by-detection architecture for MOTS - deploying a novel mask-pooling layer for improved object association over time. Training MOTSNet with our automatically extracted data leads to significantly improved sMOTSA scores on the novel KITTI MOTS dataset (+1.9%/+7.5% on cars/pedestrians), and MOTSNet improves by +4.1% over previously best methods on the MOTSChallenge dataset. Our most impressive finding is that we can improve over previous best-performing works, even in complete absence of manually annotated MOTS training data.
Tasks	Instance Segmentation, Multi-Object Tracking, Object Tracking, Optical Flow Estimation, Semantic Segmentation
Published	2019-12-04
URL	https://arxiv.org/abs/1912.02096v3
PDF	https://arxiv.org/pdf/1912.02096v3.pdf
PWC	https://paperswithcode.com/paper/learning-multi-object-tracking-and
Repo
Framework

Deep reinforcement learning in World-Earth system models to discover sustainable management strategies


Title	Deep reinforcement learning in World-Earth system models to discover sustainable management strategies
Authors	Felix M. Strnad, Wolfram Barfuss, Jonathan F. Donges, Jobst Heitzig
Abstract	Increasingly complex, non-linear World-Earth system models are used for describing the dynamics of the biophysical Earth system and the socio-economic and socio-cultural World of human societies and their interactions. Identifying pathways towards a sustainable future in these models for informing policy makers and the wider public, e.g. pathways leading to a robust mitigation of dangerous anthropogenic climate change, is a challenging and widely investigated task in the field of climate research and broader Earth system science. This problem is particularly difficult when constraints on avoiding transgressions of planetary boundaries and social foundations need to be taken into account. In this work, we propose to combine recently developed machine learning techniques, namely deep reinforcement learning (DRL), with classical analysis of trajectories in the World-Earth system. Based on the concept of the agent-environment interface, we develop an agent that is generally able to act and learn in variable manageable environment models of the Earth system. We demonstrate the potential of our framework by applying DRL algorithms to two stylized World-Earth system models. Conceptually, we explore thereby the feasibility of finding novel global governance policies leading into a safe and just operating space constrained by certain planetary and socio-economic boundaries. The artificially intelligent agent learns that the timing of a specific mix of taxing carbon emissions and subsidies on renewables is of crucial relevance for finding World-Earth system trajectories that are sustainable on the long term.
Tasks
Published	2019-08-15
URL	https://arxiv.org/abs/1908.05567v1
PDF	https://arxiv.org/pdf/1908.05567v1.pdf
PWC	https://paperswithcode.com/paper/deep-reinforcement-learning-in-world-earth
Repo
Framework

Predicting Landslides Using Contour Aligning Convolutional Neural Networks


Title	Predicting Landslides Using Contour Aligning Convolutional Neural Networks
Authors	Ainaz Hajimoradlou, Gioachino Roberti, David Poole
Abstract	Landslides, movement of soil and rock under the influence of gravity, are common phenomena that cause significant human and economic losses every year. Experts use heterogeneous features such as slope, elevation, land cover, lithology, rock age, and rock family to predict landslides. To work with such features, we adapted convolutional neural networks to consider relative spatial information for the prediction task. Traditional filters in these networks either have a fixed orientation or are rotationally invariant. Intuitively, the filters should orient uphill, but there is not enough data to learn the concept of uphill; instead, it can be provided as prior knowledge. We propose a model called Locally Aligned Convolutional Neural Network, LACNN, that follows the ground surface at multiple scales to predict possible landslide occurrence for a single point. To validate our method, we created a standardized dataset of georeferenced images consisting of the heterogeneous features as inputs, and compared our method to several baselines, including linear regression, a neural network, and a convolutional network, using log-likelihood error and Receiver Operating Characteristic curves on the test set. We show that our model performs better than the other proposed baselines.
Tasks
Published	2019-11-12
URL	https://arxiv.org/abs/1911.04651v2
PDF	https://arxiv.org/pdf/1911.04651v2.pdf
PWC	https://paperswithcode.com/paper/a-probabilistic-approach-for-predicting
Repo
Framework

Image-Based Feature Representation for Insider Threat Classification


Title	Image-Based Feature Representation for Insider Threat Classification
Authors	Gayathri R G, Atul Sajjanhar, Yong Xiang
Abstract	Insiders are the trusted entities in the organization, but poses threat to the with access to sensitive information network and resources. The insider threat detection is a well studied problem in security analytics. Identifying the features from data sources and using them with the right data analytics algorithms makes various kinds of threat analysis possible. The insider threat analysis is mainly done using the frequency based attributes extracted from the raw data available from data sources. In this paper, we propose an image-based feature representation of the daily resource usage pattern of users in the organization. The features extracted from the audit files of the organization are represented as gray scale images. Hence, these images are used to represent the resource access patterns and thereby the behavior of users. Classification models are applied to the representative images to detect anomalous behavior of insiders. The images are classified to malicious and non-malicious. The effectiveness of the proposed representation is evaluated using the CMU CERT data V4.2, and state-of-art image classification models like Mobilenet, VGG and ResNet. The experimental results showed improved accuracy. The comparison with existing works show a performance improvement in terms of high recall and precision values.
Tasks	Image Classification
Published	2019-11-13
URL	https://arxiv.org/abs/1911.05879v1
PDF	https://arxiv.org/pdf/1911.05879v1.pdf
PWC	https://paperswithcode.com/paper/image-based-feature-representation-for
Repo
Framework

Improving a tf-idf weighted document vector embedding


Title	Improving a tf-idf weighted document vector embedding
Authors	Craig W. Schmidt
Abstract	We examine a number of methods to compute a dense vector embedding for a document in a corpus, given a set of word vectors such as those from word2vec or GloVe. We describe two methods that can improve upon a simple weighted sum, that are optimal in the sense that they maximizes a particular weighted cosine similarity measure. We consider several weighting functions, including inverse document frequency (idf), smooth inverse frequency (SIF), and the sub-sampling function used in word2vec. We find that idf works best for our applications. We also use common component removal proposed by Arora et al. as a post-process and find it is helpful in most cases. We compare these embeddings variations to the doc2vec embedding on a new evaluation task using TripAdvisor reviews, and also on the CQADupStack benchmark from the literature.
Tasks
Published	2019-02-26
URL	http://arxiv.org/abs/1902.09875v1
PDF	http://arxiv.org/pdf/1902.09875v1.pdf
PWC	https://paperswithcode.com/paper/improving-a-tf-idf-weighted-document-vector
Repo
Framework

Rare Failure Prediction via Event Matching for Aerospace Applications


Title	Rare Failure Prediction via Event Matching for Aerospace Applications
Authors	Evgeny Burnaev
Abstract	In this paper, we consider a problem of failure prediction in the context of predictive maintenance applications. We present a new approach for rare failures prediction, based on a general methodology, which takes into account peculiar properties of technical systems. We illustrate the applicability of the method on the real-world test cases from aircraft operations.
Tasks
Published	2019-05-28
URL	https://arxiv.org/abs/1905.11586v1
PDF	https://arxiv.org/pdf/1905.11586v1.pdf
PWC	https://paperswithcode.com/paper/rare-failure-prediction-via-event-matching
Repo
Framework

Rank-one Convexification for Sparse Regression


Title	Rank-one Convexification for Sparse Regression
Authors	Alper Atamturk, Andres Gomez
Abstract	Sparse regression models are increasingly prevalent due to their ease of interpretability and superior out-of-sample performance. However, the exact model of sparse regression with an $\ell_0$ constraint restricting the support of the estimators is a challenging non-convex optimization problem. In this paper, we derive new strong convex relaxations for sparse regression. These relaxations are based on the ideal (convex-hull) formulations for rank-one quadratic terms with indicator variables. The new relaxations can be formulated as semidefinite optimization problems in an extended space and are stronger and more general than the state-of-the-art formulations, including the perspective reformulation and formulations with the reverse Huber penalty and the minimax concave penalty functions. Furthermore, the proposed rank-one strengthening can be interpreted as a non-separable, non-convex sparsity-inducing regularizer, which dynamically adjusts its penalty according to the shape of the error function. In our computational experiments with benchmark datasets, the proposed conic formulations are solved within seconds and result in near-optimal solutions (with 0.4% optimality gap) for non-convex $\ell_0$-problems. Moreover, the resulting estimators also outperform alternative convex approaches from a statistical viewpoint, achieving high prediction accuracy and good interpretability.
Tasks
Published	2019-01-29
URL	http://arxiv.org/abs/1901.10334v1
PDF	http://arxiv.org/pdf/1901.10334v1.pdf
PWC	https://paperswithcode.com/paper/rank-one-convexification-for-sparse
Repo
Framework

When and Why is Document-level Context Useful in Neural Machine Translation?


Title	When and Why is Document-level Context Useful in Neural Machine Translation?
Authors	Yunsu Kim, Duc Thanh Tran, Hermann Ney
Abstract	Document-level context has received lots of attention for compensating neural machine translation (NMT) of isolated sentences. However, recent advances in document-level NMT focus on sophisticated integration of the context, explaining its improvement with only a few selected examples or targeted test sets. We extensively quantify the causes of improvements by a document-level model in general test sets, clarifying the limit of the usefulness of document-level context in NMT. We show that most of the improvements are not interpretable as utilizing the context. We also show that a minimal encoding is sufficient for the context modeling and very long context is not helpful for NMT.
Tasks	Machine Translation
Published	2019-10-01
URL	https://arxiv.org/abs/1910.00294v1
PDF	https://arxiv.org/pdf/1910.00294v1.pdf
PWC	https://paperswithcode.com/paper/when-and-why-is-document-level-context-useful
Repo
Framework

A Structured Distributional Model of Sentence Meaning and Processing


Title	A Structured Distributional Model of Sentence Meaning and Processing
Authors	Emmanuele Chersoni, Enrico Santus, Ludovica Pannitto, Alessandro Lenci, Philippe Blache, Chu-Ren Huang
Abstract	Most compositional distributional semantic models represent sentence meaning with a single vector. In this paper, we propose a Structured Distributional Model (SDM) that combines word embeddings with formal semantics and is based on the assumption that sentences represent events and situations. The semantic representation of a sentence is a formal structure derived from Discourse Representation Theory and containing distributional vectors. This structure is dynamically and incrementally built by integrating knowledge about events and their typical participants, as they are activated by lexical items. Event knowledge is modeled as a graph extracted from parsed corpora and encoding roles and relationships between participants that are represented as distributional vectors. SDM is grounded on extensive psycholinguistic research showing that generalized knowledge about events stored in semantic memory plays a key role in sentence comprehension. We evaluate SDM on two recently introduced compositionality datasets, and our results show that combining a simple compositional model with event knowledge constantly improves performances, even with different types of word embeddings.
Tasks	Word Embeddings
Published	2019-06-17
URL	https://arxiv.org/abs/1906.07280v1
PDF	https://arxiv.org/pdf/1906.07280v1.pdf
PWC	https://paperswithcode.com/paper/a-structured-distributional-model-of-sentence
Repo
Framework

Spatiotemporal Recurrent Convolutional Networks for Recognizing Spontaneous Micro-expressions


Title	Spatiotemporal Recurrent Convolutional Networks for Recognizing Spontaneous Micro-expressions
Authors	Zhaoqiang Xia, Xiaopeng Hong, Xingyu Gao, Xiaoyi Feng, Guoying Zhao
Abstract	Recently, the recognition task of spontaneous facial micro-expressions has attracted much attention with its various real-world applications. Plenty of handcrafted or learned features have been employed for a variety of classifiers and achieved promising performances for recognizing micro-expressions. However, the micro-expression recognition is still challenging due to the subtle spatiotemporal changes of micro-expressions. To exploit the merits of deep learning, we propose a novel deep recurrent convolutional networks based micro-expression recognition approach, capturing the spatial-temporal deformations of micro-expression sequence. Specifically, the proposed deep model is constituted of several recurrent convolutional layers for extracting visual features and a classificatory layer for recognition. It is optimized by an end-to-end manner and obviates manual feature design. To handle sequential data, we exploit two types of extending the connectivity of convolutional networks across temporal domain, in which the spatiotemporal deformations are modeled in views of facial appearance and geometry separately. Besides, to overcome the shortcomings of limited and imbalanced training samples, temporal data augmentation strategies as well as a balanced loss are jointly used for our deep network. By performing the experiments on three spontaneous micro-expression datasets, we verify the effectiveness of our proposed micro-expression recognition approach compared to the state-of-the-art methods.
Tasks	Data Augmentation
Published	2019-01-15
URL	http://arxiv.org/abs/1901.04656v1
PDF	http://arxiv.org/pdf/1901.04656v1.pdf
PWC	https://paperswithcode.com/paper/spatiotemporal-recurrent-convolutional
Repo
Framework

Intrinsic motivations and open-ended learning


Title	Intrinsic motivations and open-ended learning
Authors	Gianluca Baldassarre
Abstract	There is a growing interest and literature on intrinsic motivations and open-ended learning in both cognitive robotics and machine learning on one side, and in psychology and neuroscience on the other. This paper aims to review some relevant contributions from the two literature threads and to draw links between them. To this purpose, the paper starts by defining intrinsic motivations and by presenting a computationally-driven theoretical taxonomy of their different types. Then it presents relevant contributions from the psychological and neuroscientific literature related to intrinsic motivations, interpreting them based on the grid, and elucidates the mechanisms and functions they play in animals and humans. Endowed with such concepts and their biological underpinnings, the paper next presents a selection of models from cognitive robotics and machine learning that computationally operationalise the concepts of intrinsic motivations and links them to biology concepts. The contribution finally presents some of the open challenges of the field from both the psychological/neuroscientific and computational perspectives.
Tasks
Published	2019-12-31
URL	https://arxiv.org/abs/1912.13263v1
PDF	https://arxiv.org/pdf/1912.13263v1.pdf
PWC	https://paperswithcode.com/paper/intrinsic-motivations-and-open-ended-learning
Repo
Framework

Fast and Accurate Gaussian Kernel Ridge Regression Using Matrix Decompositions for Preconditioning


Title	Fast and Accurate Gaussian Kernel Ridge Regression Using Matrix Decompositions for Preconditioning
Authors	Gil Shabat, Era Choshen, Dvir Ben-Or, Nadav Carmel
Abstract	This paper presents a method for building a preconditioner for a kernel ridge regression problem, where the preconditioner is not only effective in its ability to reduce the condition number substantially, but also efficient in its application in terms of computational cost and memory consumption. The suggested approach is based on randomized matrix decomposition methods, combined with the fast multipole method to achieve an algorithm that can process large datasets in complexity linear to the number of data points. In addition, a detailed theoretical analysis is provided, including an upper bound to the condition number. Finally, for Gaussian kernels, the analysis shows that the required rank for a desired condition number can be determined directly from the dataset itself without performing any analysis on the kernel matrix.
Tasks
Published	2019-05-25
URL	https://arxiv.org/abs/1905.10587v1
PDF	https://arxiv.org/pdf/1905.10587v1.pdf
PWC	https://paperswithcode.com/paper/fast-and-accurate-gaussian-kernel-ridge
Repo
Framework

Fully Convolutional Networks for Chip-wise Defect Detection Employing Photoluminescence Images


Title	Fully Convolutional Networks for Chip-wise Defect Detection Employing Photoluminescence Images
Authors	Maike Lorena Stern, Martin Schellenberger
Abstract	Efficient quality control is inevitable in the manufacturing of light-emitting diodes (LEDs). Because defective LED chips may be traced back to different causes, a time and cost-intensive electrical and optical contact measurement is employed. Fast photoluminescence measurements, on the other hand, are commonly used to detect wafer separation damages but also hold the potential to enable an efficient detection of all kinds of defective LED chips. On a photoluminescence image, every pixel corresponds to an LED chip’s brightness after photoexcitation, revealing performance information. But due to unevenly distributed brightness values and varying defect patterns, photoluminescence images are not yet employed for a comprehensive defect detection. In this work, we show that fully convolutional networks can be used for chip-wise defect detection, trained on a small data-set of photoluminescence images. Pixel-wise labels allow us to classify each and every chip as defective or not. Being measurement-based, labels are easy to procure and our experiments show that existing discrepancies between training images and labels do not hinder network training. Using weighted loss calculation, we were able to equalize our highly unbalanced class categories. Due to the consistent use of skip connections and residual shortcuts, our network is able to predict a variety of structures, from extensive defect clusters up to single defective LED chips.
Tasks
Published	2019-10-06
URL	https://arxiv.org/abs/1910.02451v1
PDF	https://arxiv.org/pdf/1910.02451v1.pdf
PWC	https://paperswithcode.com/paper/fully-convolutional-networks-for-chip-wise
Repo
Framework

A New Stereo Benchmarking Dataset for Satellite Images


Title	A New Stereo Benchmarking Dataset for Satellite Images
Authors	Sonali Patil, Bharath Comandur, Tanmay Prakash, Avinash C. Kak
Abstract	In order to facilitate further research in stereo reconstruction with multi-date satellite images, the goal of this paper is to provide a set of stereo-rectified images and the associated groundtruthed disparities for 10 AOIs (Area of Interest) drawn from two sources: 8 AOIs from IARPA’s MVS Challenge dataset and 2 AOIs from the CORE3D-Public dataset. The disparities were groundtruthed by first constructing a fused DSM from the stereo pairs and by aligning 30 cm LiDAR with the fused DSM. Unlike the existing benckmarking datasets, we have also carried out a quantitative evaluation of our groundtruthed disparities using human annotated points in two of the AOIs. Additionally, the rectification accuracy in our dataset is comparable to the same in the existing state-of-the-art stereo datasets. In general, we have used the WorldView-3 (WV3) images for the dataset, the exception being the UCSD area for which we have used both WV3 and WorldView-2 (WV2) images. All of the dataset images are now in the public domain. Since multi-date satellite images frequently include images acquired in different seasons (which creates challenges in finding corresponding pairs of pixels for stereo), our dataset also includes for each image a building mask over which the disparities estimated by stereo should prove reliable. Additional metadata included in the dataset includes information about each image’s acquisition date and time, the azimuth and elevation angles of the camera, and the intersection angles for the two views in a stereo pair. Also included in the dataset are both quantitative and qualitative analyses of the accuracy of the groundtruthed disparity maps. Our dataset is available for download at \url{https://engineering.purdue.edu/RVL/Database/SatStereo/index.html}
Tasks
Published	2019-07-09
URL	https://arxiv.org/abs/1907.04404v1
PDF	https://arxiv.org/pdf/1907.04404v1.pdf
PWC	https://paperswithcode.com/paper/a-new-stereo-benchmarking-dataset-for
Repo
Framework

Pan-Cancer Diagnostic Consensus Through Searching Archival Histopathology Images Using Artificial Intelligence


Title	Pan-Cancer Diagnostic Consensus Through Searching Archival Histopathology Images Using Artificial Intelligence
Authors	Shivam Kalra, H. R. Tizhoosh, Sultaan Shah, Charles Choi, Savvas Damaskinos, Amir Safarpoor, Sobhan Shafiei, Morteza Babaie, Phedias Diamandis, Clinton JV Campbell, Liron Pantanowitz
Abstract	The emergence of digital pathology has opened new horizons for histopathology and cytology. Artificial-intelligence algorithms are able to operate on digitized slides to assist pathologists with diagnostic tasks. Whereas machine learning involving classification and segmentation methods have obvious benefits for image analysis in pathology, image search represents a fundamental shift in computational pathology. Matching the pathology of new patients with already diagnosed and curated cases offers pathologist a novel approach to improve diagnostic accuracy through visual inspection of similar cases and computational majority vote for consensus building. In this study, we report the results from searching the largest public repository (The Cancer Genome Atlas [TCGA] program by National Cancer Institute, USA) of whole slide images from almost 11,000 patients depicting different types of malignancies. For the first time, we successfully indexed and searched almost 30,000 high-resolution digitized slides constituting 16 terabytes of data comprised of 20 million 1000x1000 pixels image patches. The TCGA image database covers 25 anatomic sites and contains 32 cancer subtypes. High-performance storage and GPU power were employed for experimentation. The results were assessed with conservative “majority voting” to build consensus for subtype diagnosis through vertical search and demonstrated high accuracy values for both frozen sections slides (e.g., bladder urothelial carcinoma 93%, kidney renal clear cell carcinoma 97%, and ovarian serous cystadenocarcinoma 99%) and permanent histopathology slides (e.g., prostate adenocarcinoma 98%, skin cutaneous melanoma 99%, and thymoma 100%). The key finding of this validation study was that computational consensus appears to be possible for rendering diagnoses if a sufficiently large number of searchable cases are available for each cancer subtype.
Tasks	Image Retrieval
Published	2019-11-20
URL	https://arxiv.org/abs/1911.08736v1
PDF	https://arxiv.org/pdf/1911.08736v1.pdf
PWC	https://paperswithcode.com/paper/pan-cancer-diagnostic-consensus-through
Repo
Framework