July 30, 2019

3201 words 16 mins read

Paper Group AWR 29

Bayesian fairness. Mask R-CNN. The Emergence of Canalization and Evolvability in an Open-Ended, Interactive Evolutionary System. eXpose: A Character-Level Convolutional Neural Network with Embeddings For Detecting Malicious URLs, File Paths and Registry Keys. SMILES Enumeration as Data Augmentation for Neural Network Modeling of Molecules. Online R …

Bayesian fairness


Title	Bayesian fairness
Authors	Christos Dimitrakakis, Yang Liu, David Parkes, Goran Radanovic
Abstract	We consider the problem of how decision making can be fair when the underlying probabilistic model of the world is not known with certainty. We argue that recent notions of fairness in machine learning need to explicitly incorporate parameter uncertainty, hence we introduce the notion of {\em Bayesian fairness} as a suitable candidate for fair decision rules. Using balance, a definition of fairness introduced by Kleinberg et al (2016), we show how a Bayesian perspective can lead to well-performing, fair decision rules even under high uncertainty.
Tasks	Decision Making
Published	2017-05-31
URL	http://arxiv.org/abs/1706.00119v3
PDF	http://arxiv.org/pdf/1706.00119v3.pdf
PWC	https://paperswithcode.com/paper/bayesian-fairness
Repo	https://github.com/madicooley/prob_mod_finalproj
Framework	none

Mask R-CNN


Title	Mask R-CNN
Authors	Kaiming He, Georgia Gkioxari, Piotr Dollár, Ross Girshick
Abstract	We present a conceptually simple, flexible, and general framework for object instance segmentation. Our approach efficiently detects objects in an image while simultaneously generating a high-quality segmentation mask for each instance. The method, called Mask R-CNN, extends Faster R-CNN by adding a branch for predicting an object mask in parallel with the existing branch for bounding box recognition. Mask R-CNN is simple to train and adds only a small overhead to Faster R-CNN, running at 5 fps. Moreover, Mask R-CNN is easy to generalize to other tasks, e.g., allowing us to estimate human poses in the same framework. We show top results in all three tracks of the COCO suite of challenges, including instance segmentation, bounding-box object detection, and person keypoint detection. Without bells and whistles, Mask R-CNN outperforms all existing, single-model entries on every task, including the COCO 2016 challenge winners. We hope our simple and effective approach will serve as a solid baseline and help ease future research in instance-level recognition. Code has been made available at: https://github.com/facebookresearch/Detectron
Tasks	Human Part Segmentation, Instance Segmentation, Keypoint Detection, Multi-Human Parsing, Nuclear Segmentation, Object Detection, Semantic Segmentation
Published	2017-03-20
URL	http://arxiv.org/abs/1703.06870v3
PDF	http://arxiv.org/pdf/1703.06870v3.pdf
PWC	https://paperswithcode.com/paper/mask-r-cnn
Repo	https://github.com/fdac18/ForensicImages
Framework	none

The Emergence of Canalization and Evolvability in an Open-Ended, Interactive Evolutionary System


Title	The Emergence of Canalization and Evolvability in an Open-Ended, Interactive Evolutionary System
Authors	Joost Huizinga, Kenneth O. Stanley, Jeff Clune
Abstract	Natural evolution has produced a tremendous diversity of functional organisms. Many believe an essential component of this process was the evolution of evolvability, whereby evolution speeds up its ability to innovate by generating a more adaptive pool of offspring. One hypothesized mechanism for evolvability is developmental canalization, wherein certain dimensions of variation become more likely to be traversed and others are prevented from being explored (e.g. offspring tend to have similarly sized legs, and mutations affect the length of both legs, not each leg individually). While ubiquitous in nature, canalization almost never evolves in computational simulations of evolution. Not only does that deprive us of in silico models in which to study the evolution of evolvability, but it also raises the question of which conditions give rise to this form of evolvability. Answering this question would shed light on why such evolvability emerged naturally and could accelerate engineering efforts to harness evolution to solve important engineering challenges. In this paper we reveal a unique system in which canalization did emerge in computational evolution. We document that genomes entrench certain dimensions of variation that were frequently explored during their evolutionary history. The genetic representation of these organisms also evolved to be highly modular and hierarchical, and we show that these organizational properties correlate with increased fitness. Interestingly, the type of computational evolutionary experiment that produced this evolvability was very different from traditional digital evolution in that there was no objective, suggesting that open-ended, divergent evolutionary processes may be necessary for the evolution of evolvability.
Tasks
Published	2017-04-17
URL	http://arxiv.org/abs/1704.05143v2
PDF	http://arxiv.org/pdf/1704.05143v2.pdf
PWC	https://paperswithcode.com/paper/the-emergence-of-canalization-and
Repo	https://github.com/JoostHuizinga/cppnx
Framework	none

eXpose: A Character-Level Convolutional Neural Network with Embeddings For Detecting Malicious URLs, File Paths and Registry Keys


Title	eXpose: A Character-Level Convolutional Neural Network with Embeddings For Detecting Malicious URLs, File Paths and Registry Keys
Authors	Joshua Saxe, Konstantin Berlin
Abstract	For years security machine learning research has promised to obviate the need for signature based detection by automatically learning to detect indicators of attack. Unfortunately, this vision hasn’t come to fruition: in fact, developing and maintaining today’s security machine learning systems can require engineering resources that are comparable to that of signature-based detection systems, due in part to the need to develop and continuously tune the “features” these machine learning systems look at as attacks evolve. Deep learning, a subfield of machine learning, promises to change this by operating on raw input signals and automating the process of feature design and extraction. In this paper we propose the eXpose neural network, which uses a deep learning approach we have developed to take generic, raw short character strings as input (a common case for security inputs, which include artifacts like potentially malicious URLs, file paths, named pipes, named mutexes, and registry keys), and learns to simultaneously extract features and classify using character-level embeddings and convolutional neural network. In addition to completely automating the feature design and extraction process, eXpose outperforms manual feature extraction based baselines on all of the intrusion detection problems we tested it on, yielding a 5%-10% detection rate gain at 0.1% false positive rate compared to these baselines.
Tasks	Intrusion Detection
Published	2017-02-27
URL	http://arxiv.org/abs/1702.08568v1
PDF	http://arxiv.org/pdf/1702.08568v1.pdf
PWC	https://paperswithcode.com/paper/expose-a-character-level-convolutional-neural
Repo	https://github.com/ruchikagargdiwakar/ml_cyber_security_usecases
Framework	none

SMILES Enumeration as Data Augmentation for Neural Network Modeling of Molecules


Title	SMILES Enumeration as Data Augmentation for Neural Network Modeling of Molecules
Authors	Esben Jannik Bjerrum
Abstract	Simplified Molecular Input Line Entry System (SMILES) is a single line text representation of a unique molecule. One molecule can however have multiple SMILES strings, which is a reason that canonical SMILES have been defined, which ensures a one to one correspondence between SMILES string and molecule. Here the fact that multiple SMILES represent the same molecule is explored as a technique for data augmentation of a molecular QSAR dataset modeled by a long short term memory (LSTM) cell based neural network. The augmented dataset was 130 times bigger than the original. The network trained with the augmented dataset shows better performance on a test set when compared to a model built with only one canonical SMILES string per molecule. The correlation coefficient R2 on the test set was improved from 0.56 to 0.66 when using SMILES enumeration, and the root mean square error (RMS) likewise fell from 0.62 to 0.55. The technique also works in the prediction phase. By taking the average per molecule of the predictions for the enumerated SMILES a further improvement to a correlation coefficient of 0.68 and a RMS of 0.52 was found.
Tasks	Data Augmentation
Published	2017-03-21
URL	http://arxiv.org/abs/1703.07076v2
PDF	http://arxiv.org/pdf/1703.07076v2.pdf
PWC	https://paperswithcode.com/paper/smiles-enumeration-as-data-augmentation-for
Repo	https://github.com/Ebjerrum/SMILES-enumeration
Framework	tf

Online Robust Principal Component Analysis with Change Point Detection


Title	Online Robust Principal Component Analysis with Change Point Detection
Authors	Wei Xiao, Xiaolin Huang, Jorge Silva, Saba Emrani, Arin Chaudhuri
Abstract	Robust PCA methods are typically batch algorithms which requires loading all observations into memory before processing. This makes them inefficient to process big data. In this paper, we develop an efficient online robust principal component methods, namely online moving window robust principal component analysis (OMWRPCA). Unlike existing algorithms, OMWRPCA can successfully track not only slowly changing subspace but also abruptly changed subspace. By embedding hypothesis testing into the algorithm, OMWRPCA can detect change points of the underlying subspaces. Extensive simulation studies demonstrate the superior performance of OMWRPCA compared with other state-of-art approaches. We also apply the algorithm for real-time background subtraction of surveillance video.
Tasks	Change Point Detection
Published	2017-02-19
URL	http://arxiv.org/abs/1702.05698v2
PDF	http://arxiv.org/pdf/1702.05698v2.pdf
PWC	https://paperswithcode.com/paper/online-robust-principal-component-analysis
Repo	https://github.com/wxiao0421/onlineRPCA
Framework	none

Deep High Dynamic Range Imaging with Large Foreground Motions


Title	Deep High Dynamic Range Imaging with Large Foreground Motions
Authors	Shangzhe Wu, Jiarui Xu, Yu-Wing Tai, Chi-Keung Tang
Abstract	This paper proposes the first non-flow-based deep framework for high dynamic range (HDR) imaging of dynamic scenes with large-scale foreground motions. In state-of-the-art deep HDR imaging, input images are first aligned using optical flows before merging, which are still error-prone due to occlusion and large motions. In stark contrast to flow-based methods, we formulate HDR imaging as an image translation problem without optical flows. Moreover, our simple translation network can automatically hallucinate plausible HDR details in the presence of total occlusion, saturation and under-exposure, which are otherwise almost impossible to recover by conventional optimization approaches. Our framework can also be extended for different reference images. We performed extensive qualitative and quantitative comparisons to show that our approach produces excellent results where color artifacts and geometric distortions are significantly reduced compared to existing state-of-the-art methods, and is robust across various inputs, including images without radiometric calibration.
Tasks	Calibration
Published	2017-11-24
URL	http://arxiv.org/abs/1711.08937v3
PDF	http://arxiv.org/pdf/1711.08937v3.pdf
PWC	https://paperswithcode.com/paper/deep-high-dynamic-range-imaging-with-large
Repo	https://github.com/elliottwu/DeepHDR
Framework	tf

Cascade R-CNN: Delving into High Quality Object Detection


Title	Cascade R-CNN: Delving into High Quality Object Detection
Authors	Zhaowei Cai, Nuno Vasconcelos
Abstract	In object detection, an intersection over union (IoU) threshold is required to define positives and negatives. An object detector, trained with low IoU threshold, e.g. 0.5, usually produces noisy detections. However, detection performance tends to degrade with increasing the IoU thresholds. Two main factors are responsible for this: 1) overfitting during training, due to exponentially vanishing positive samples, and 2) inference-time mismatch between the IoUs for which the detector is optimal and those of the input hypotheses. A multi-stage object detection architecture, the Cascade R-CNN, is proposed to address these problems. It consists of a sequence of detectors trained with increasing IoU thresholds, to be sequentially more selective against close false positives. The detectors are trained stage by stage, leveraging the observation that the output of a detector is a good distribution for training the next higher quality detector. The resampling of progressively improved hypotheses guarantees that all detectors have a positive set of examples of equivalent size, reducing the overfitting problem. The same cascade procedure is applied at inference, enabling a closer match between the hypotheses and the detector quality of each stage. A simple implementation of the Cascade R-CNN is shown to surpass all single-model object detectors on the challenging COCO dataset. Experiments also show that the Cascade R-CNN is widely applicable across detector architectures, achieving consistent gains independently of the baseline detector strength. The code will be made available at https://github.com/zhaoweicai/cascade-rcnn.
Tasks	Object Detection
Published	2017-12-03
URL	http://arxiv.org/abs/1712.00726v1
PDF	http://arxiv.org/pdf/1712.00726v1.pdf
PWC	https://paperswithcode.com/paper/cascade-r-cnn-delving-into-high-quality
Repo	https://github.com/tkuanlun350/Kaggle_Ship_Detection_2018
Framework	tf

Focal Loss for Dense Object Detection


Title	Focal Loss for Dense Object Detection
Authors	Tsung-Yi Lin, Priya Goyal, Ross Girshick, Kaiming He, Piotr Dollár
Abstract	The highest accuracy object detectors to date are based on a two-stage approach popularized by R-CNN, where a classifier is applied to a sparse set of candidate object locations. In contrast, one-stage detectors that are applied over a regular, dense sampling of possible object locations have the potential to be faster and simpler, but have trailed the accuracy of two-stage detectors thus far. In this paper, we investigate why this is the case. We discover that the extreme foreground-background class imbalance encountered during training of dense detectors is the central cause. We propose to address this class imbalance by reshaping the standard cross entropy loss such that it down-weights the loss assigned to well-classified examples. Our novel Focal Loss focuses training on a sparse set of hard examples and prevents the vast number of easy negatives from overwhelming the detector during training. To evaluate the effectiveness of our loss, we design and train a simple dense detector we call RetinaNet. Our results show that when trained with the focal loss, RetinaNet is able to match the speed of previous one-stage detectors while surpassing the accuracy of all existing state-of-the-art two-stage detectors. Code is at: https://github.com/facebookresearch/Detectron.
Tasks	Dense Object Detection, Object Detection
Published	2017-08-07
URL	http://arxiv.org/abs/1708.02002v2
PDF	http://arxiv.org/pdf/1708.02002v2.pdf
PWC	https://paperswithcode.com/paper/focal-loss-for-dense-object-detection
Repo	https://github.com/yuliani29/yolotraining
Framework	none

Cell Tracking via Proposal Generation and Selection


Title	Cell Tracking via Proposal Generation and Selection
Authors	Saad Ullah Akram, Juho Kannala, Lauri Eklund, Janne Heikkilä
Abstract	Microscopy imaging plays a vital role in understanding many biological processes in development and disease. The recent advances in automation of microscopes and development of methods and markers for live cell imaging has led to rapid growth in the amount of image data being captured. To efficiently and reliably extract useful insights from these captured sequences, automated cell tracking is essential. This is a challenging problem due to large variation in the appearance and shapes of cells depending on many factors including imaging methodology, biological characteristics of cells, cell matrix composition, labeling methodology, etc. Often cell tracking methods require a sequence-specific segmentation method and manual tuning of many tracking parameters, which limits their applicability to sequences other than those they are designed for. In this paper, we propose 1) a deep learning based cell proposal method, which proposes candidates for cells along with their scores, and 2) a cell tracking method, which links proposals in adjacent frames in a graphical model using edges representing different cellular events and poses joint cell detection and tracking as the selection of a subset of cell and edge proposals. Our method is completely automated and given enough training data can be applied to a wide variety of microscopy sequences. We evaluate our method on multiple fluorescence and phase contrast microscopy sequences containing cells of various shapes and appearances from ISBI cell tracking challenge, and show that our method outperforms existing cell tracking methods. Code is available at: https://github.com/SaadUllahAkram/CellTracker
Tasks
Published	2017-05-09
URL	http://arxiv.org/abs/1705.03386v1
PDF	http://arxiv.org/pdf/1705.03386v1.pdf
PWC	https://paperswithcode.com/paper/cell-tracking-via-proposal-generation-and
Repo	https://github.com/SaadUllahAkram/CellTracker
Framework	none

Person Search with Natural Language Description


Title	Person Search with Natural Language Description
Authors	Shuang Li, Tong Xiao, Hongsheng Li, Bolei Zhou, Dayu Yue, Xiaogang Wang
Abstract	Searching persons in large-scale image databases with the query of natural language description has important applications in video surveillance. Existing methods mainly focused on searching persons with image-based or attribute-based queries, which have major limitations for a practical usage. In this paper, we study the problem of person search with natural language description. Given the textual description of a person, the algorithm of the person search is required to rank all the samples in the person database then retrieve the most relevant sample corresponding to the queried description. Since there is no person dataset or benchmark with textual description available, we collect a large-scale person description dataset with detailed natural language annotations and person samples from various sources, termed as CUHK Person Description Dataset (CUHK-PEDES). A wide range of possible models and baselines have been evaluated and compared on the person search benchmark. An Recurrent Neural Network with Gated Neural Attention mechanism (GNA-RNN) is proposed to establish the state-of-the art performance on person search.
Tasks	Person Search
Published	2017-02-19
URL	http://arxiv.org/abs/1702.05729v2
PDF	http://arxiv.org/pdf/1702.05729v2.pdf
PWC	https://paperswithcode.com/paper/person-search-with-natural-language
Repo	https://github.com/ShuangLI59/Person-Search-with-Natural-Language-Description
Framework	torch

Diagonal RNNs in Symbolic Music Modeling


Title	Diagonal RNNs in Symbolic Music Modeling
Authors	Y. Cem Subakan, Paris Smaragdis
Abstract	In this paper, we propose a new Recurrent Neural Network (RNN) architecture. The novelty is simple: We use diagonal recurrent matrices instead of full. This results in better test likelihood and faster convergence compared to regular full RNNs in most of our experiments. We show the benefits of using diagonal recurrent matrices with popularly used LSTM and GRU architectures as well as with the vanilla RNN architecture, on four standard symbolic music datasets.
Tasks	Music Modeling
Published	2017-04-18
URL	http://arxiv.org/abs/1704.05420v2
PDF	http://arxiv.org/pdf/1704.05420v2.pdf
PWC	https://paperswithcode.com/paper/diagonal-rnns-in-symbolic-music-modeling
Repo	https://github.com/ycemsubakan/diagonal_rnns
Framework	tf

Dragon: A Computation Graph Virtual Machine Based Deep Learning Framework


Title	Dragon: A Computation Graph Virtual Machine Based Deep Learning Framework
Authors	Ting Pan
Abstract	Deep Learning has made a great progress for these years. However, it is still difficult to master the implement of various models because different researchers may release their code based on different frameworks or interfaces. In this paper, we proposed a computation graph based framework which only aims to introduce well-known interfaces. It will help a lot when reproducing a newly model or transplanting models that were implemented by other frameworks. Additionally, we implement numerous recent models covering both Computer Vision and Nature Language Processing. We demonstrate that our framework will not suffer from model-starving because it is much easier to make full use of the works that are already done.
Tasks
Published	2017-07-26
URL	http://arxiv.org/abs/1707.08265v1
PDF	http://arxiv.org/pdf/1707.08265v1.pdf
PWC	https://paperswithcode.com/paper/dragon-a-computation-graph-virtual-machine
Repo	https://github.com/seetaresearch/DragonLair
Framework	none

A Deep Structured Learning Approach Towards Automating Connectome Reconstruction from 3D Electron Micrographs


Title	A Deep Structured Learning Approach Towards Automating Connectome Reconstruction from 3D Electron Micrographs
Authors	Jan Funke, Fabian David Tschopp, William Grisaitis, Arlo Sheridan, Chandan Singh, Stephan Saalfeld, Srinivas C. Turaga
Abstract	We present a deep structured learning method for neuron segmentation from 3D electron microscopy (EM) which improves significantly upon the state of the art in terms of accuracy and scalability. Our method consists of a 3D U-Net classifier predicting affinity graphs on voxels, followed by iterative region agglomeration. We train the U-Net using a new structured loss based on MALIS that encourages topological correctness. Our extension consists of two parts: First, an $O(n\log(n))$ method to compute the loss gradient, improving over the originally proposed $O(n^2)$ algorithm. Second, we compute the gradient in two separate passes to avoid spurious contributions in early training stages. Our affinity predictions are accurate enough that simple agglomeration outperforms more involved methods used earlier on inferior predictions. We present results on three datasets (CREMI, FIB, and SegEM) of different imaging techniques and animals and achieve improvements over previous results of 27%, 15%, and 250%. Our findings suggest that a single 3D segmentation strategy can be applied to both isotropic and anisotropic EM data. The runtime of our method scales with $O(n)$ in the size of the volume and achieves a throughput of about 2.6 seconds per megavoxel, allowing processing of very large datasets.
Tasks
Published	2017-09-09
URL	http://arxiv.org/abs/1709.02974v3
PDF	http://arxiv.org/pdf/1709.02974v3.pdf
PWC	https://paperswithcode.com/paper/a-deep-structured-learning-approach-towards
Repo	https://github.com/funkey/mala
Framework	tf

Answering Complex Questions Using Open Information Extraction


Title	Answering Complex Questions Using Open Information Extraction
Authors	Tushar Khot, Ashish Sabharwal, Peter Clark
Abstract	While there has been substantial progress in factoid question-answering (QA), answering complex questions remains challenging, typically requiring both a large body of knowledge and inference techniques. Open Information Extraction (Open IE) provides a way to generate semi-structured knowledge for QA, but to date such knowledge has only been used to answer simple questions with retrieval-based methods. We overcome this limitation by presenting a method for reasoning with Open IE knowledge, allowing more complex questions to be handled. Using a recently proposed support graph optimization framework for QA, we develop a new inference model for Open IE, in particular one that can work effectively with multiple short facts, noise, and the relational structure of tuples. Our model significantly outperforms a state-of-the-art structured solver on complex questions of varying difficulty, while also removing the reliance on manually curated knowledge.
Tasks	Open Information Extraction, Question Answering
Published	2017-04-19
URL	http://arxiv.org/abs/1704.05572v1
PDF	http://arxiv.org/pdf/1704.05572v1.pdf
PWC	https://paperswithcode.com/paper/answering-complex-questions-using-open
Repo	https://github.com/allenai/semanticilp
Framework	none