Paper Group ANR 950
XCMRC: Evaluating Cross-lingual Machine Reading Comprehension. Lung CT Imaging Sign Classification through Deep Learning on Small Data. Probabilistic Decoupling of Labels in Classification. Age and gender bias in pedestrian detection algorithms. Confidence regions and minimax rates in outlier-robust estimation on the probability simplex. Egocentric …
XCMRC: Evaluating Cross-lingual Machine Reading Comprehension
| Title | XCMRC: Evaluating Cross-lingual Machine Reading Comprehension |
| Authors | Pengyuan Liu, Yuning Deng, Chenghao Zhu, Han Hu |
| Abstract | We present XCMRC, the first public cross-lingual language understanding (XLU) benchmark which aims to test machines on their cross-lingual reading comprehension ability. To be specific, XCMRC is a Cross-lingual Cloze-style Machine Reading Comprehension task which requires the reader to fill in a missing word (we additionally provide ten noun candidates) in a sentence written in target language (English / Chinese) by reading a given passage written in source language (Chinese / English). Chinese and English are rich-resource language pairs, in order to study low-resource cross-lingual machine reading comprehension (XMRC), besides defining the common XCMRC task which has no restrictions on use of external language resources, we also define the pseudo low-resource XCMRC task by limiting the language resources to be used. In addition, we provide two baselines for common XCMRC task and two for pseudo XCMRC task respectively. We also provide an upper bound baseline for both tasks. We found that for common XCMRC task, translation-based method and multilingual sentence encoder-based method can obtain reasonable performance but still have much room for improvement. As for pseudo low-resource XCMRC task, due to strict restrictions on the use of language resources, our two approaches are far below the upper bound so there are many challenges ahead. |
| Tasks | Machine Reading Comprehension, Reading Comprehension |
| Published | 2019-08-15 |
| URL | https://arxiv.org/abs/1908.05416v1 |
| https://arxiv.org/pdf/1908.05416v1.pdf | |
| PWC | https://paperswithcode.com/paper/xcmrc-evaluating-cross-lingual-machine |
| Repo | |
| Framework | |
Lung CT Imaging Sign Classification through Deep Learning on Small Data
| Title | Lung CT Imaging Sign Classification through Deep Learning on Small Data |
| Authors | Guocai He |
| Abstract | The annotated medical images are usually expensive to be collected. This paper proposes a deep learning method on small data to classify Common Imaging Signs of Lung diseases (CISL) in computed tomography (CT) images. We explore both the real data and the data generated by Generative Adversarial Network (GAN) to improve the reliability and the generalization of learning. First, we use GAN to generate a large number of CISLs from small annotated data, which are difficult to be distinguished from real counterparts. These generated samples are used to pre-train a Convolutional Neural Network (CNN) for classifying CISLs. Second, we fine-tune the CNN classification model with real data. Experiments were conducted on the LISS database of CISLs. We successfully convinced radiologists that our generated CISLs samples were real for 56.7% of our experiments. The pre-trained CNN model achieves 88.4% of mean accuracy of binary classification, and after fine-tuning, the mean accuracy is significantly increased to 95.0%. For multi-classification of all types of CISLs and normal tissues, through the two stages of training, the mean accuracy, sensitivity and specificity are up to about 91.83%, 92.73% and 99.0%, respectively. To our knowledge, this is the best result achieved on the LISS database, which demonstrates that the proposed method is effective and promising for fulfilling deep learning on small data. |
| Tasks | Computed Tomography (CT) |
| Published | 2019-03-01 |
| URL | http://arxiv.org/abs/1903.00183v1 |
| http://arxiv.org/pdf/1903.00183v1.pdf | |
| PWC | https://paperswithcode.com/paper/lung-ct-imaging-sign-classification-through |
| Repo | |
| Framework | |
Probabilistic Decoupling of Labels in Classification
| Title | Probabilistic Decoupling of Labels in Classification |
| Authors | Jeppe Nørregaard, Lars Kai Hansen |
| Abstract | We investigate probabilistic decoupling of labels supplied for training, from the underlying classes for prediction. Decoupling enables an inference scheme general enough to implement many classification problems, including supervised, semi-supervised, positive-unlabelled, noisy-label and suggests a general solution to the multi-positive-unlabelled learning problem. We test the method on the Fashion MNIST and 20 News Groups datasets for performance benchmarks, where we simulate noise, partial labelling etc. |
| Tasks | |
| Published | 2019-05-29 |
| URL | https://arxiv.org/abs/1905.12403v1 |
| https://arxiv.org/pdf/1905.12403v1.pdf | |
| PWC | https://paperswithcode.com/paper/probabilistic-decoupling-of-labels-in |
| Repo | |
| Framework | |
Age and gender bias in pedestrian detection algorithms
| Title | Age and gender bias in pedestrian detection algorithms |
| Authors | Martim Brandao |
| Abstract | Pedestrian detection algorithms are important components of mobile robots, such as autonomous vehicles, which directly relate to human safety. Performance disparities in these algorithms could translate into disparate impact in the form of biased accident outcomes. To evaluate the need for such concerns, we characterize the age and gender bias in the performance of state-of-the-art pedestrian detection algorithms. Our analysis is based on the INRIA Person Dataset extended with child, adult, male and female labels. We show that all of the 24 top-performing methods of the Caltech Pedestrian Detection Benchmark have higher miss rates on children. The difference is significant and we analyse how it varies with the classifier, features and training data used by the methods. Algorithms were also gender-biased on average but the performance differences were not significant. We discuss the source of the bias, the ethical implications, possible technical solutions and barriers. |
| Tasks | Autonomous Vehicles, Pedestrian Detection |
| Published | 2019-06-25 |
| URL | https://arxiv.org/abs/1906.10490v1 |
| https://arxiv.org/pdf/1906.10490v1.pdf | |
| PWC | https://paperswithcode.com/paper/age-and-gender-bias-in-pedestrian-detection |
| Repo | |
| Framework | |
Confidence regions and minimax rates in outlier-robust estimation on the probability simplex
| Title | Confidence regions and minimax rates in outlier-robust estimation on the probability simplex |
| Authors | Amir-Hossein Bateni, Arnak S. Dalalyan |
| Abstract | We consider the problem of estimating the mean of a distribution supported by the $k$-dimensional probability simplex in the setting where an $\varepsilon$ fraction of observations are subject to adversarial corruption. A simple particular example is the problem of estimating the distribution of a discrete random variable. Assuming that the discrete variable takes $k$ values, the unknown parameter $\boldsymbol \theta$ is a $k$-dimensional vector belonging to the probability simplex. We first describe various settings of contamination and discuss the relation between these settings. We then establish minimax rates when the quality of estimation is measured by the total-variation distance, the Hellinger distance, or the $\mathbb L^2$-distance between two probability measures. We also provide confidence regions for the unknown mean that shrink at the minimax rate. Our analysis reveals that the minimax rates associated to these three distances are all different, but they are all attained by the sample average. Furthermore, we show that the latter is adaptive to the possible sparsity of the unknown vector. Some numerical experiments illustrating our theoretical findings are reported. |
| Tasks | |
| Published | 2019-02-12 |
| URL | https://arxiv.org/abs/1902.04650v2 |
| https://arxiv.org/pdf/1902.04650v2.pdf | |
| PWC | https://paperswithcode.com/paper/minimax-rates-in-outlier-robust-estimation-of |
| Repo | |
| Framework | |
Egocentric affordance detection with the one-shot geometry-driven Interaction Tensor
| Title | Egocentric affordance detection with the one-shot geometry-driven Interaction Tensor |
| Authors | Eduardo Ruiz, Walterio Mayol-Cuevas |
| Abstract | In this abstract we describe recent [4,7] and latest work on the determination of affordances in visually perceived 3D scenes. Our method builds on the hypothesis that geometry on its own provides enough information to enable the detection of significant interaction possibilities in the environment. The motivation behind this is that geometric information is intimately related to the physical interactions afforded by objects in the world. The approach uses a generic representation for the interaction between everyday objects such as a mug or an umbrella with the environment, and also for more complex affordances such as humans Sitting or Riding a motorcycle. Experiments with synthetic and real RGB-D scenes show that the representation enables the prediction of affordance candidate locations in novel environments at fast rates and from a single (one-shot) training example. The determination of affordances is a crucial step towards systems that need to perceive and interact with their surroundings. We here illustrate output on two cases for a simulated robot and for an Augmented Reality setting, both perceiving in an egocentric manner. |
| Tasks | |
| Published | 2019-06-13 |
| URL | https://arxiv.org/abs/1906.05794v1 |
| https://arxiv.org/pdf/1906.05794v1.pdf | |
| PWC | https://paperswithcode.com/paper/egocentric-affordance-detection-with-the-one |
| Repo | |
| Framework | |
Towards Affordance Prediction with Vision via Task Oriented Grasp Quality Metrics
| Title | Towards Affordance Prediction with Vision via Task Oriented Grasp Quality Metrics |
| Authors | Luca Cavalli, Gianpaolo Di Pietro, Matteo Matteucci |
| Abstract | While many quality metrics exist to evaluate the quality of a grasp by itself, no clear quantification of the quality of a grasp relatively to the task the grasp is used for has been defined yet. In this paper we propose a framework to extend the concept of grasp quality metric to task-oriented grasping by defining affordance functions via basic grasp metrics for an open set of task affordances. We evaluate both the effectivity of the proposed task oriented metrics and their practical applicability by learning to infer them from vision. Indeed, we assess the validity of our novel framework both in the context of perfect information, i.e., known object model, and in the partial information context, i.e., inferring task oriented metrics from vision, underlining advantages and limitations of both situations. In the former, physical metrics of grasp hypotheses on an object are defined and computed in known object model simulation, in the latter deep models are trained to infer such properties from partial information in the form of synthesized range images. |
| Tasks | |
| Published | 2019-07-10 |
| URL | https://arxiv.org/abs/1907.04761v1 |
| https://arxiv.org/pdf/1907.04761v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-affordance-prediction-with-vision-via |
| Repo | |
| Framework | |
Training Kinetics in 15 Minutes: Large-scale Distributed Training on Videos
| Title | Training Kinetics in 15 Minutes: Large-scale Distributed Training on Videos |
| Authors | Ji Lin, Chuang Gan, Song Han |
| Abstract | Deep video recognition is more computationally expensive than image recognition, especially on large-scale datasets like Kinetics [1]. Therefore, training scalability is essential to handle a large amount of videos. In this paper, we study the factors that impact the training scalability of video networks. We recognize three bottlenecks, including data loading (data movement from disk to GPU), communication (data movement over networking), and computation FLOPs. We propose three design guidelines to improve the scalability: (1) fewer FLOPs and hardware-friendly operator to increase the computation efficiency; (2) fewer input frames to reduce the data movement and increase the data loading efficiency; (3) smaller model size to reduce the networking traffic and increase the networking efficiency. With these guidelines, we designed a new operator Temporal Shift Module (TSM) that is efficient and scalable for distributed training. TSM model can achieve 1.8x higher throughput compared to previous I3D models. We scale up the training of the TSM model to 1,536 GPUs, with a mini-batch of 12,288 video clips/98,304 images, without losing the accuracy. With such hardware-aware model design, we are able to scale up the training on Summit supercomputer and reduce the training time on Kinetics dataset from 49 hours 55 minutes to 14 minutes 13 seconds, achieving a top-1 accuracy of 74.0%, which is 1.6x and 2.9x faster than previous 3D video models with higher accuracy. The code and more details can be found here: http://tsm-hanlab.mit.edu. |
| Tasks | Video Recognition |
| Published | 2019-10-01 |
| URL | https://arxiv.org/abs/1910.00932v2 |
| https://arxiv.org/pdf/1910.00932v2.pdf | |
| PWC | https://paperswithcode.com/paper/training-kinetics-in-15-minutes-large-scale |
| Repo | |
| Framework | |
JIM: Joint Influence Modeling for Collective Search Behavior
| Title | JIM: Joint Influence Modeling for Collective Search Behavior |
| Authors | Shubhra Kanti Karmaker Santu, Liangda Li, Yi Chang, ChengXiang Zhai |
| Abstract | Previous work has shown that popular trending events are important external factors which pose significant influence on user search behavior and also provided a way to computationally model this influence. However, their problem formulation was based on the strong assumption that each event poses its influence independently. This assumption is unrealistic as there are many correlated events in the real world which influence each other and thus, would pose a joint influence on the user search behavior rather than posing influence independently. In this paper, we study this novel problem of Modeling the Joint Influences posed by multiple correlated events on user search behavior. We propose a Joint Influence Model based on the Multivariate Hawkes Process which captures the inter-dependency among multiple events in terms of their influence upon user search behavior. We evaluate the proposed Joint Influence Model using two months query-log data from https://search.yahoo.com/. Experimental results show that the model can indeed capture the temporal dynamics of the joint influence over time and also achieves superior performance over different baseline methods when applied to solve various interesting prediction problems as well as real-word application scenarios, e.g., query auto-completion. |
| Tasks | |
| Published | 2019-03-01 |
| URL | http://arxiv.org/abs/1903.00562v1 |
| http://arxiv.org/pdf/1903.00562v1.pdf | |
| PWC | https://paperswithcode.com/paper/jim-joint-influence-modeling-for-collective |
| Repo | |
| Framework | |
Generative Adversarial Networks Synthesize Realistic OCT Images of the Retina
| Title | Generative Adversarial Networks Synthesize Realistic OCT Images of the Retina |
| Authors | Stephen G. Odaibo, M. D., M. S., M. S. |
| Abstract | We report, to our knowledge, the first end-to-end application of Generative Adversarial Networks (GANs) towards the synthesis of Optical Coherence Tomography (OCT) images of the retina. Generative models have gained recent attention for the increasingly realistic images they can synthesize, given a sampling of a data type. In this paper, we apply GANs to a sampling distribution of OCTs of the retina. We observe the synthesis of realistic OCT images depicting recognizable pathology such as macular holes, choroidal neovascular membranes, myopic degeneration, cystoid macular edema, and central serous retinopathy amongst others. This represents the first such report of its kind. Potential applications of this new technology include for surgical simulation, for treatment planning, for disease prognostication, and for accelerating the development of new drugs and surgical procedures to treat retinal disease. |
| Tasks | |
| Published | 2019-02-18 |
| URL | http://arxiv.org/abs/1902.06676v1 |
| http://arxiv.org/pdf/1902.06676v1.pdf | |
| PWC | https://paperswithcode.com/paper/generative-adversarial-networks-synthesize |
| Repo | |
| Framework | |
JSDoop and TensorFlow.js: Volunteer Distributed Web Browser-Based Neural Network Training
| Title | JSDoop and TensorFlow.js: Volunteer Distributed Web Browser-Based Neural Network Training |
| Authors | José Á. Morell, Andrés Camero, Enrique Alba |
| Abstract | In 2019, around 57% of the population of the world has broadband access to the Internet. Moreover, there are 5.9 billion mobile broadband subscriptions, i.e., 1.3 subscriptions per user. So there is an enormous interconnected computational power held by users all around the world. Also, it is estimated that Internet users spend more than six and a half hours online every day. But in spite of being a great amount of time, those resources are idle most of the day. Therefore, taking advantage of them presents an interesting opportunity. In this study, we introduce JSDoop, a prototype implementation to profit from this opportunity. In particular, we propose a volunteer web browser-based high-performance computing library. JSdoop divides a problem into tasks and uses different queues to distribute the computation. Then, volunteers access the web page of the problem and start processing the tasks in their web browsers. We conducted a proof-of-concept using our proposal and TensorFlow.js to train a recurrent neural network that predicts text. We tested it in a computer cluster and with up to 32 volunteers. The experimental results show that training a neural network in distributed web browsers is feasible and accurate, has a high scalability, and it is an interesting area for research. |
| Tasks | |
| Published | 2019-10-12 |
| URL | https://arxiv.org/abs/1910.07402v1 |
| https://arxiv.org/pdf/1910.07402v1.pdf | |
| PWC | https://paperswithcode.com/paper/jsdoop-and-tensorflowjs-volunteer-distributed |
| Repo | |
| Framework | |
Implications of Quantum Computing for Artificial Intelligence alignment research
| Title | Implications of Quantum Computing for Artificial Intelligence alignment research |
| Authors | Jaime Sevilla, Pablo Moreno |
| Abstract | We explain some key features of quantum computing via three heuristics and apply them to argue that a deep understanding of quantum computing is unlikely to be helpful to address current bottlenecks in Artificial Intelligence Alignment. Our argument relies on the claims that Quantum Computing leads to compute overhang instead of algorithmic overhang, and that the difficulties associated with the measurement of quantum states do not invalidate any major assumptions of current Artificial Intelligence Alignment research agendas. We also discuss tripwiring, adversarial blinding, informed oversight and side effects as possible exceptions. |
| Tasks | |
| Published | 2019-08-19 |
| URL | https://arxiv.org/abs/1908.07613v3 |
| https://arxiv.org/pdf/1908.07613v3.pdf | |
| PWC | https://paperswithcode.com/paper/190807613 |
| Repo | |
| Framework | |
Lessons from Archives: Strategies for Collecting Sociocultural Data in Machine Learning
| Title | Lessons from Archives: Strategies for Collecting Sociocultural Data in Machine Learning |
| Authors | Eun Seo Jo, Timnit Gebru |
| Abstract | A growing body of work shows that many problems in fairness, accountability, transparency, and ethics in machine learning systems are rooted in decisions surrounding the data collection and annotation process. In spite of its fundamental nature however, data collection remains an overlooked part of the machine learning (ML) pipeline. In this paper, we argue that a new specialization should be formed within ML that is focused on methodologies for data collection and annotation: efforts that require institutional frameworks and procedures. Specifically for sociocultural data, parallels can be drawn from archives and libraries. Archives are the longest standing communal effort to gather human information and archive scholars have already developed the language and procedures to address and discuss many challenges pertaining to data collection such as consent, power, inclusivity, transparency, and ethics & privacy. We discuss these five key approaches in document collection practices in archives that can inform data collection in sociocultural ML. By showing data collection practices from another field, we encourage ML research to be more cognizant and systematic in data collection and draw from interdisciplinary expertise. |
| Tasks | |
| Published | 2019-12-22 |
| URL | https://arxiv.org/abs/1912.10389v1 |
| https://arxiv.org/pdf/1912.10389v1.pdf | |
| PWC | https://paperswithcode.com/paper/lessons-from-archives-strategies-for |
| Repo | |
| Framework | |
Distributed Online Optimization with Long-Term Constraints
| Title | Distributed Online Optimization with Long-Term Constraints |
| Authors | Deming Yuan, Alexandre Proutiere, Guodong Shi |
| Abstract | We consider distributed online convex optimization problems, where the distributed system consists of various computing units connected through a time-varying communication graph. In each time step, each computing unit selects a constrained vector, experiences a loss equal to an arbitrary convex function evaluated at this vector, and may communicate to its neighbors in the graph. The objective is to minimize the system-wide loss accumulated over time. We propose a decentralized algorithm with regret and cumulative constraint violation in $\mathcal{O}(T^{\max{c,1-c} })$ and $\mathcal{O}(T^{1-c/2})$, respectively, for any $c\in (0,1)$, where $T$ is the time horizon. When the loss functions are strongly convex, we establish improved regret and constraint violation upper bounds in $\mathcal{O}(\log(T))$ and $\mathcal{O}(\sqrt{T\log(T)})$. These regret scalings match those obtained by state-of-the-art algorithms and fundamental limits in the corresponding centralized online optimization problem (for both convex and strongly convex loss functions). In the case of bandit feedback, the proposed algorithms achieve a regret and constraint violation in $\mathcal{O}(T^{\max{c,1-c/3 } })$ and $\mathcal{O}(T^{1-c/2})$ for any $c\in (0,1)$. We numerically illustrate the performance of our algorithms for the particular case of distributed online regularized linear regression problems. |
| Tasks | |
| Published | 2019-12-20 |
| URL | https://arxiv.org/abs/1912.09705v1 |
| https://arxiv.org/pdf/1912.09705v1.pdf | |
| PWC | https://paperswithcode.com/paper/distributed-online-optimization-with-long-1 |
| Repo | |
| Framework | |
Blameworthiness in Security Games
| Title | Blameworthiness in Security Games |
| Authors | Pavel Naumov, Jia Tao |
| Abstract | Security games are an example of a successful real-world application of game theory. The paper defines blameworthiness of the defender and the attacker in security games using the principle of alternative possibilities and provides a sound and complete logical system for reasoning about blameworthiness in such games. Two of the axioms of this system capture the asymmetry of information in security games. |
| Tasks | |
| Published | 2019-10-18 |
| URL | https://arxiv.org/abs/1910.08647v2 |
| https://arxiv.org/pdf/1910.08647v2.pdf | |
| PWC | https://paperswithcode.com/paper/blameworthiness-in-security-games |
| Repo | |
| Framework | |
