Paper Group AWR 340
Contrastive Learning of Structured World Models. Span-based Joint Entity and Relation Extraction with Transformer Pre-training. Learning Aberrance Repressed Correlation Filters for Real-Time UAV Tracking. Quantity Tagger: A Latent-Variable Sequence Labeling Approach to Solving Addition-Subtraction Word Problems. Learning Vector-valued Functions wit …
Contrastive Learning of Structured World Models
| Title | Contrastive Learning of Structured World Models |
| Authors | Thomas Kipf, Elise van der Pol, Max Welling |
| Abstract | A structured understanding of our world in terms of objects, relations, and hierarchies is an important component of human cognition. Learning such a structured world model from raw sensory data remains a challenge. As a step towards this goal, we introduce Contrastively-trained Structured World Models (C-SWMs). C-SWMs utilize a contrastive approach for representation learning in environments with compositional structure. We structure each state embedding as a set of object representations and their relations, modeled by a graph neural network. This allows objects to be discovered from raw pixel observations without direct supervision as part of the learning process. We evaluate C-SWMs on compositional environments involving multiple interacting objects that can be manipulated independently by an agent, simple Atari games, and a multi-object physics simulation. Our experiments demonstrate that C-SWMs can overcome limitations of models based on pixel reconstruction and outperform typical representatives of this model class in highly structured environments, while learning interpretable object-based representations. |
| Tasks | Atari Games, Representation Learning |
| Published | 2019-11-27 |
| URL | https://arxiv.org/abs/1911.12247v2 |
| https://arxiv.org/pdf/1911.12247v2.pdf | |
| PWC | https://paperswithcode.com/paper/contrastive-learning-of-structured-world-1 |
| Repo | https://github.com/tkipf/c-swm |
| Framework | pytorch |
Span-based Joint Entity and Relation Extraction with Transformer Pre-training
| Title | Span-based Joint Entity and Relation Extraction with Transformer Pre-training |
| Authors | Markus Eberts, Adrian Ulges |
| Abstract | We introduce SpERT, an attention model for span-based joint entity and relation extraction. Our key contribution is a light-weight reasoning on BERT embeddings, which features entity recognition and filtering, as well as relation classification with a localized, marker-free context representation. The model is trained using strong within-sentence negative samples, which are efficiently extracted in a single BERT pass. These aspects facilitate a search over all spans in the sentence. In ablation studies, we demonstrate the benefits of pre-training, strong negative sampling and localized context. Our model outperforms prior work by up to 2.6% F1 score on several datasets for joint entity and relation extraction. |
| Tasks | Joint Entity and Relation Extraction, Named Entity Recognition, Relation Classification, Relation Extraction |
| Published | 2019-09-17 |
| URL | https://arxiv.org/abs/1909.07755v3 |
| https://arxiv.org/pdf/1909.07755v3.pdf | |
| PWC | https://paperswithcode.com/paper/span-based-joint-entity-and-relation |
| Repo | https://github.com/markus-eberts/spert |
| Framework | pytorch |
Learning Aberrance Repressed Correlation Filters for Real-Time UAV Tracking
| Title | Learning Aberrance Repressed Correlation Filters for Real-Time UAV Tracking |
| Authors | Ziyuan Huang, Changhong Fu, Yiming Li, Fuling Lin, Peng Lu |
| Abstract | Traditional framework of discriminative correlation filters (DCF) is often subject to undesired boundary effects. Several approaches to enlarge search regions have been already proposed in the past years to make up for this shortcoming. However, with excessive background information, more background noises are also introduced and the discriminative filter is prone to learn from the ambiance rather than the object. This situation, along with appearance changes of objects caused by full/partial occlusion, illumination variation, and other reasons has made it more likely to have aberrances in the detection process, which could substantially degrade the credibility of its result. Therefore, in this work, a novel approach to repress the aberrances happening during the detection process is proposed, i.e., aberrance repressed correlation filter (ARCF). By enforcing restriction to the rate of alteration in response maps generated in the detection phase, the ARCF tracker can evidently suppress aberrances and is thus more robust and accurate to track objects. Considerable experiments are conducted on different UAV datasets to perform object tracking from an aerial view, i.e., UAV123, UAVDT, and DTB70, with 243 challenging image sequences containing over 90K frames to verify the performance of the ARCF tracker and it has proven itself to have outperformed other 20 state-of-the-art trackers based on DCF and deep-based frameworks with sufficient speed for real-time applications. |
| Tasks | Object Tracking |
| Published | 2019-08-06 |
| URL | https://arxiv.org/abs/1908.02231v2 |
| https://arxiv.org/pdf/1908.02231v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-aberrance-repressed-correlation |
| Repo | https://github.com/vision4robotics/ARCF-tracker |
| Framework | none |
Quantity Tagger: A Latent-Variable Sequence Labeling Approach to Solving Addition-Subtraction Word Problems
| Title | Quantity Tagger: A Latent-Variable Sequence Labeling Approach to Solving Addition-Subtraction Word Problems |
| Authors | Yanyan Zou, Wei Lu |
| Abstract | An arithmetic word problem typically includes a textual description containing several constant quantities. The key to solving the problem is to reveal the underlying mathematical relations (such as addition and subtraction) among quantities, and then generate equations to find solutions. This work presents a novel approach, Quantity Tagger, that automatically discovers such hidden relations by tagging each quantity with a sign corresponding to one type of mathematical operation. For each quantity, we assume there exists a latent, variable-sized quantity span surrounding the quantity token in the text, which conveys information useful for determining its sign. Empirical results show that our method achieves 5 and 8 points of accuracy gains on two datasets respectively, compared to prior approaches. |
| Tasks | |
| Published | 2019-08-31 |
| URL | https://arxiv.org/abs/1909.00176v1 |
| https://arxiv.org/pdf/1909.00176v1.pdf | |
| PWC | https://paperswithcode.com/paper/quantity-tagger-a-latent-variable-sequence-1 |
| Repo | https://github.com/zoezou2015/quantity_tagger |
| Framework | none |
Learning Vector-valued Functions with Local Rademacher Complexity and Unlabeled Data
| Title | Learning Vector-valued Functions with Local Rademacher Complexity and Unlabeled Data |
| Authors | Yong Liu, Jian Li, Lizhong Ding, Xinwang Liu, Weiping Wang |
| Abstract | We consider a general family of problems of which the output space admits vector-valued structure, covering a broad family of important domains, e.g. multi-label learning and multi-class classification. By using local Rademacher complexity and unlabeled data, we derived novel data-dependent excess risk bounds for vector-valued functions in both linear space and kernel space. The proposed bounds are much sharper than existing bounds and can be applied into specific vector-valued tasks in terms of different hypotheses sets and loss functions. Theoretical analysis motivates us to devise a unified learning framework for vector-valued functions based which is solved by proximal gradient descent on the primal, achieving a much better tradeoff between accuracy and efficiency. Empirical results on several benchmark datasets show that the proposed algorithm outperforms compared methods significantly, which coincides with our theoretical analysis. |
| Tasks | Multi-Label Learning |
| Published | 2019-09-11 |
| URL | https://arxiv.org/abs/1909.04883v2 |
| https://arxiv.org/pdf/1909.04883v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-vector-valued-functions-with-local |
| Repo | https://github.com/superlj666/Learning-Vector-valued-Functions-with-Local-Rademacher-Complexity |
| Framework | none |
Variational Autoencoders for Sparse and Overdispersed Discrete Data
| Title | Variational Autoencoders for Sparse and Overdispersed Discrete Data |
| Authors | He Zhao, Piyush Rai, Lan Du, Wray Buntine, Mingyuan Zhou |
| Abstract | Many applications, such as text modelling, high-throughput sequencing, and recommender systems, require analysing sparse, high-dimensional, and overdispersed discrete (count-valued or binary) data. Although probabilistic matrix factorisation and linear/nonlinear latent factor models have enjoyed great success in modelling such data, many existing models may have inferior modelling performance due to the insufficient capability of modelling overdispersion in count-valued data and model misspecification in general. In this paper, we comprehensively study these issues and propose a variational autoencoder based framework that generates discrete data via negative-binomial distribution. We also examine the model’s ability to capture properties, such as self- and cross-excitations in discrete data, which is critical for modelling overdispersion. We conduct extensive experiments on three important problems from discrete data analysis: text analysis, collaborative filtering, and multi-label learning. Compared with several state-of-the-art baselines, the proposed models achieve significantly better performance on the above problems. |
| Tasks | Multi-Label Learning, Recommendation Systems |
| Published | 2019-05-02 |
| URL | https://arxiv.org/abs/1905.00616v2 |
| https://arxiv.org/pdf/1905.00616v2.pdf | |
| PWC | https://paperswithcode.com/paper/deep-generative-models-for-sparse-high |
| Repo | https://github.com/ethanhezhao/NBVAE |
| Framework | tf |
Pedestrian Attribute Recognition: A Survey
| Title | Pedestrian Attribute Recognition: A Survey |
| Authors | Xiao Wang, Shaofei Zheng, Rui Yang, Bin Luo, Jin Tang |
| Abstract | Recognizing pedestrian attributes is an important task in computer vision community due to it plays an important role in video surveillance. Many algorithms has been proposed to handle this task. The goal of this paper is to review existing works using traditional methods or based on deep learning networks. Firstly, we introduce the background of pedestrian attributes recognition (PAR, for short), including the fundamental concepts of pedestrian attributes and corresponding challenges. Secondly, we introduce existing benchmarks, including popular datasets and evaluation criterion. Thirdly, we analyse the concept of multi-task learning and multi-label learning, and also explain the relations between these two learning algorithms and pedestrian attribute recognition. We also review some popular network architectures which have widely applied in the deep learning community. Fourthly, we analyse popular solutions for this task, such as attributes group, part-based, \emph{etc}. Fifthly, we shown some applications which takes pedestrian attributes into consideration and achieve better performance. Finally, we summarized this paper and give several possible research directions for pedestrian attributes recognition. The project page of this paper can be found from the following website: \url{https://sites.google.com/view/ahu-pedestrianattributes/}. |
| Tasks | Multi-Label Learning, Multi-Task Learning, Pedestrian Attribute Recognition |
| Published | 2019-01-22 |
| URL | http://arxiv.org/abs/1901.07474v1 |
| http://arxiv.org/pdf/1901.07474v1.pdf | |
| PWC | https://paperswithcode.com/paper/pedestrian-attribute-recognition-a-survey |
| Repo | https://github.com/wangxiao5791509/Pedestrian-Attribute-Recognition-Paper-List |
| Framework | pytorch |
Geolocating Political Events in Text
| Title | Geolocating Political Events in Text |
| Authors | Andrew Halterman |
| Abstract | This work introduces a general method for automatically finding the locations where political events in text occurred. Using a novel set of 8,000 labeled sentences, I create a method to link automatically extracted events and locations in text. The model achieves human level performance on the annotation task and outperforms previous event geolocation systems. It can be applied to most event extraction systems across geographic contexts. I formalize the event–location linking task, describe the neural network model, describe the potential uses of such a system in political science, and demonstrate a workflow to answer an open question on the role of conventional military offensives in causing civilian casualties in the Syrian civil war. |
| Tasks | |
| Published | 2019-05-29 |
| URL | https://arxiv.org/abs/1905.12713v1 |
| https://arxiv.org/pdf/1905.12713v1.pdf | |
| PWC | https://paperswithcode.com/paper/geolocating-political-events-in-text |
| Repo | https://github.com/ahalterman/event_location |
| Framework | none |
Benchmarking Attribution Methods with Relative Feature Importance
| Title | Benchmarking Attribution Methods with Relative Feature Importance |
| Authors | Mengjiao Yang, Been Kim |
| Abstract | Interpretability is an important area of research for safe deployment of machine learning systems. One particular type of interpretability method attributes model decisions to input features. Despite active development, quantitative evaluation of feature attribution methods remains difficult due to the lack of ground truth: we do not know which input features are in fact important to a model. In this work, we propose a framework for Benchmarking Attribution Methods (BAM) with a priori knowledge of relative feature importance. BAM includes 1) a carefully crafted dataset and models trained with known relative feature importance and 2) three complementary metrics to quantitatively evaluate attribution methods by comparing feature attributions between pairs of models and pairs of inputs. Our evaluation on several widely-used attribution methods suggests that certain methods are more likely to produce false positive explanations—features that are incorrectly attributed as more important to model prediction. We open source our dataset, models, and metrics. |
| Tasks | Feature Importance |
| Published | 2019-07-23 |
| URL | https://arxiv.org/abs/1907.09701v2 |
| https://arxiv.org/pdf/1907.09701v2.pdf | |
| PWC | https://paperswithcode.com/paper/bim-towards-quantitative-evaluation-of |
| Repo | https://github.com/google-research-datasets/bim |
| Framework | tf |
Deep Gamblers: Learning to Abstain with Portfolio Theory
| Title | Deep Gamblers: Learning to Abstain with Portfolio Theory |
| Authors | Liu Ziyin, Zhikang Wang, Paul Pu Liang, Ruslan Salakhutdinov, Louis-Philippe Morency, Masahito Ueda |
| Abstract | We deal with the \textit{selective classification} problem (supervised-learning problem with a rejection option), where we want to achieve the best performance at a certain level of coverage of the data. We transform the original $m$-class classification problem to $(m+1)$-class where the $(m+1)$-th class represents the model abstaining from making a prediction due to disconfidence. Inspired by portfolio theory, we propose a loss function for the selective classification problem based on the doubling rate of gambling. Minimizing this loss function corresponds naturally to maximizing the return of a \textit{horse race}, where a player aims to balance between betting on an outcome (making a prediction) when confident and reserving one’s winnings (abstaining) when not confident. This loss function allows us to train neural networks and characterize the disconfidence of prediction in an end-to-end fashion. In comparison with previous methods, our method requires almost no modification to the model inference algorithm or model architecture. Experiments show that our method can identify uncertainty in data points, and achieves strong results on SVHN and CIFAR10 at various coverages of the data. |
| Tasks | |
| Published | 2019-06-29 |
| URL | https://arxiv.org/abs/1907.00208v2 |
| https://arxiv.org/pdf/1907.00208v2.pdf | |
| PWC | https://paperswithcode.com/paper/deep-gamblers-learning-to-abstain-with |
| Repo | https://github.com/wzkkzw12345/NIPS2019DeepGamblers |
| Framework | pytorch |
Discovering patterns of online popularity from time series
| Title | Discovering patterns of online popularity from time series |
| Authors | Mert Ozer, Anna Sapienza, Andrés Abeliuk, Goran Muric, Emilio Ferrara |
| Abstract | How is popularity gained online? Is being successful strictly related to rapidly becoming viral in an online platform or is it possible to acquire popularity in a steady and disciplined fashion? What are other temporal characteristics that can unveil the popularity of online content? To answer these questions, we leverage a multi-faceted temporal analysis of the evolution of popular online contents. Here, we present dipm-SC: a multi-dimensional shape-based time-series clustering algorithm with a heuristic to find the optimal number of clusters. First, we validate the accuracy of our algorithm on synthetic datasets generated from benchmark time series models. Second, we show that dipm-SC can uncover meaningful clusters of popularity behaviors in a real-world Twitter dataset. By clustering the multidimensional time-series of the popularity of contents coupled with other domain-specific dimensions, we uncover two main patterns of popularity: bursty and steady temporal behaviors. Moreover, we find that the way popularity is gained over time has no significant impact on the final cumulative popularity. |
| Tasks | Time Series, Time Series Clustering |
| Published | 2019-04-10 |
| URL | http://arxiv.org/abs/1904.04994v1 |
| http://arxiv.org/pdf/1904.04994v1.pdf | |
| PWC | https://paperswithcode.com/paper/discovering-patterns-of-online-popularity |
| Repo | https://github.com/mertozer/mts-clustering |
| Framework | none |
Sparse Networks from Scratch: Faster Training without Losing Performance
| Title | Sparse Networks from Scratch: Faster Training without Losing Performance |
| Authors | Tim Dettmers, Luke Zettlemoyer |
| Abstract | We demonstrate the possibility of what we call sparse learning: accelerated training of deep neural networks that maintain sparse weights throughout training while achieving dense performance levels. We accomplish this by developing sparse momentum, an algorithm which uses exponentially smoothed gradients (momentum) to identify layers and weights which reduce the error efficiently. Sparse momentum redistributes pruned weights across layers according to the mean momentum magnitude of each layer. Within a layer, sparse momentum grows weights according to the momentum magnitude of zero-valued weights. We demonstrate state-of-the-art sparse performance on MNIST, CIFAR-10, and ImageNet, decreasing the mean error by a relative 8%, 15%, and 6% compared to other sparse algorithms. Furthermore, we show that sparse momentum reliably reproduces dense performance levels while providing up to 5.61x faster training. In our analysis, ablations show that the benefits of momentum redistribution and growth increase with the depth and size of the network. Additionally, we find that sparse momentum is insensitive to the choice of its hyperparameters suggesting that sparse momentum is robust and easy to use. |
| Tasks | Image Classification, Sparse Learning |
| Published | 2019-07-10 |
| URL | https://arxiv.org/abs/1907.04840v2 |
| https://arxiv.org/pdf/1907.04840v2.pdf | |
| PWC | https://paperswithcode.com/paper/sparse-networks-from-scratch-faster-training |
| Repo | https://github.com/TimDettmers/sparse_learning |
| Framework | pytorch |
Automated quantum programming via reinforcement learning for combinatorial optimization
| Title | Automated quantum programming via reinforcement learning for combinatorial optimization |
| Authors | Keri A. McKiernan, Erik Davis, M. Sohaib Alam, Chad Rigetti |
| Abstract | We develop a general method for incentive-based programming of hybrid quantum-classical computing systems using reinforcement learning, and apply this to solve combinatorial optimization problems on both simulated and real gate-based quantum computers. Relative to a set of randomly generated problem instances, agents trained through reinforcement learning techniques are capable of producing short quantum programs which generate high quality solutions on both types of quantum resources. We observe generalization to problems outside of the training set, as well as generalization from the simulated quantum resource to the physical quantum resource. |
| Tasks | Combinatorial Optimization |
| Published | 2019-08-21 |
| URL | https://arxiv.org/abs/1908.08054v1 |
| https://arxiv.org/pdf/1908.08054v1.pdf | |
| PWC | https://paperswithcode.com/paper/automated-quantum-programming-via |
| Repo | https://github.com/rigetti/gym-forest |
| Framework | none |
Augmenting expert detection of early coronary artery occlusion from 12 lead electrocardiograms using deep learning
| Title | Augmenting expert detection of early coronary artery occlusion from 12 lead electrocardiograms using deep learning |
| Authors | Rob Brisk, Raymond R Bond. Dewar D Finlay, James McLaughlin, Alicja Piadlo, Stephen J Leslie, David E Gossman, Ian B A Menown, David J McEneaney |
| Abstract | Early diagnosis of acute coronary artery occlusion based on electrocardiogram (ECG) findings is essential for prompt delivery of primary percutaneous coronary intervention. Current ST elevation (STE) criteria are specific but insensitive. Consequently, it is likely that many patients are missing out on potentially life-saving treatment. Experts combining non-specific ECG changes with STE detect ischaemia with higher sensitivity, but at the cost of specificity. We show that a deep learning model can detect ischaemia caused by acute coronary artery occlusion with a better balance of sensitivity and specificity than STE criteria, existing computerised analysers or expert cardiologists. |
| Tasks | |
| Published | 2019-03-11 |
| URL | https://arxiv.org/abs/1903.04421v4 |
| https://arxiv.org/pdf/1903.04421v4.pdf | |
| PWC | https://paperswithcode.com/paper/better-than-expert-detection-of-early |
| Repo | https://github.com/docbrisky/coronary-occlusion |
| Framework | tf |
PointRend: Image Segmentation as Rendering
| Title | PointRend: Image Segmentation as Rendering |
| Authors | Alexander Kirillov, Yuxin Wu, Kaiming He, Ross Girshick |
| Abstract | We present a new method for efficient high-quality image segmentation of objects and scenes. By analogizing classical computer graphics methods for efficient rendering with over- and undersampling challenges faced in pixel labeling tasks, we develop a unique perspective of image segmentation as a rendering problem. From this vantage, we present the PointRend (Point-based Rendering) neural network module: a module that performs point-based segmentation predictions at adaptively selected locations based on an iterative subdivision algorithm. PointRend can be flexibly applied to both instance and semantic segmentation tasks by building on top of existing state-of-the-art models. While many concrete implementations of the general idea are possible, we show that a simple design already achieves excellent results. Qualitatively, PointRend outputs crisp object boundaries in regions that are over-smoothed by previous methods. Quantitatively, PointRend yields significant gains on COCO and Cityscapes, for both instance and semantic segmentation. PointRend’s efficiency enables output resolutions that are otherwise impractical in terms of memory or computation compared to existing approaches. Code has been made available at https://github.com/facebookresearch/detectron2/tree/master/projects/PointRend. |
| Tasks | Semantic Segmentation |
| Published | 2019-12-17 |
| URL | https://arxiv.org/abs/1912.08193v2 |
| https://arxiv.org/pdf/1912.08193v2.pdf | |
| PWC | https://paperswithcode.com/paper/pointrend-image-segmentation-as-rendering |
| Repo | https://github.com/ShanghaiTechCVDL/Weekly_Group_Meeting_Paper_List |
| Framework | none |
