Paper Group ANR 439
Incentivizing Exploration with Selective Data Disclosure. Diacritization of Maghrebi Arabic Sub-Dialects. Object detection at 200 Frames Per Second. Fast and Robust Small Infrared Target Detection Using Absolute Directional Mean Difference Algorithm. Variational Rejection Sampling. Natural language understanding for task oriented dialog in the biom …
Incentivizing Exploration with Selective Data Disclosure
| Title | Incentivizing Exploration with Selective Data Disclosure |
| Authors | Nicole Immorlica, Jieming Mao, Aleksandrs Slivkins, Zhiwei Steven Wu |
| Abstract | We study the design of rating systems that incentivize (more) efficient social learning among self-interested agents. Agents arrive sequentially and are presented with a set of possible actions, each of which yields a positive reward with an unknown probability. A disclosure policy sends messages about the rewards of previously-chosen actions to arriving agents. These messages can alter agents’ incentives towards exploration, taking potentially sub-optimal actions for the sake of learning more about their rewards. Prior work achieves much progress with disclosure policies that merely recommend an action to each user, but relies heavily on standard, yet very strong rationality assumptions. We study a particular class of disclosure policies that use messages, called unbiased subhistories, consisting of the actions and rewards from a subsequence of past agents. Each subsequence is chosen ahead of time, according to a predetermined partial order on the rounds. We posit a flexible model of frequentist agent response, which we argue is plausible for this class of “order-based” disclosure policies. We measure the success of a policy by its regret, i.e., the difference, over all rounds, between the expected reward of the best action and the reward induced by the policy. A disclosure policy that reveals full history in each round risks inducing herding behavior among the agents, and typically has regret linear in the time horizon $T$. Our main result is an order-based disclosure policy that obtains regret $\tilde{O}(\sqrt{T})$. This regret is known to be optimal in the worst case over reward distributions, even absent incentives. We also exhibit simpler order-based policies with higher, but still sublinear, regret. These policies can be interpreted as dividing a sublinear number of agents into constant-sized focus groups, whose histories are then revealed to future agents. |
| Tasks | |
| Published | 2018-11-14 |
| URL | https://arxiv.org/abs/1811.06026v3 |
| https://arxiv.org/pdf/1811.06026v3.pdf | |
| PWC | https://paperswithcode.com/paper/incentivizing-exploration-with-unbiased |
| Repo | |
| Framework | |
Diacritization of Maghrebi Arabic Sub-Dialects
| Title | Diacritization of Maghrebi Arabic Sub-Dialects |
| Authors | Ahmed Abdelali, Mohammed Attia, Younes Samih, Kareem Darwish, Hamdy Mubarak |
| Abstract | Diacritization process attempt to restore the short vowels in Arabic written text; which typically are omitted. This process is essential for applications such as Text-to-Speech (TTS). While diacritization of Modern Standard Arabic (MSA) still holds the lion share, research on dialectal Arabic (DA) diacritization is very limited. In this paper, we present our contribution and results on the automatic diacritization of two sub-dialects of Maghrebi Arabic, namely Tunisian and Moroccan, using a character-level deep neural network architecture that stacks two bi-LSTM layers over a CRF output layer. The model achieves word error rate of 2.7% and 3.6% for Moroccan and Tunisian respectively and is capable of implicitly identifying the sub-dialect of the input. |
| Tasks | |
| Published | 2018-10-15 |
| URL | https://arxiv.org/abs/1810.06619v3 |
| https://arxiv.org/pdf/1810.06619v3.pdf | |
| PWC | https://paperswithcode.com/paper/diacritization-of-maghrebi-arabic-sub |
| Repo | |
| Framework | |
Object detection at 200 Frames Per Second
| Title | Object detection at 200 Frames Per Second |
| Authors | Rakesh Mehta, Cemalettin Ozturk |
| Abstract | In this paper, we propose an efficient and fast object detector which can process hundreds of frames per second. To achieve this goal we investigate three main aspects of the object detection framework: network architecture, loss function and training data (labeled and unlabeled). In order to obtain compact network architecture, we introduce various improvements, based on recent work, to develop an architecture which is computationally light-weight and achieves a reasonable performance. To further improve the performance, while keeping the complexity same, we utilize distillation loss function. Using distillation loss we transfer the knowledge of a more accurate teacher network to proposed light-weight student network. We propose various innovations to make distillation efficient for the proposed one stage detector pipeline: objectness scaled distillation loss, feature map non-maximal suppression and a single unified distillation loss function for detection. Finally, building upon the distillation loss, we explore how much can we push the performance by utilizing the unlabeled data. We train our model with unlabeled data using the soft labels of the teacher network. Our final network consists of 10x fewer parameters than the VGG based object detection network and it achieves a speed of more than 200 FPS and proposed changes improve the detection accuracy by 14 mAP over the baseline on Pascal dataset. |
| Tasks | Object Detection |
| Published | 2018-05-16 |
| URL | http://arxiv.org/abs/1805.06361v1 |
| http://arxiv.org/pdf/1805.06361v1.pdf | |
| PWC | https://paperswithcode.com/paper/object-detection-at-200-frames-per-second |
| Repo | |
| Framework | |
Fast and Robust Small Infrared Target Detection Using Absolute Directional Mean Difference Algorithm
| Title | Fast and Robust Small Infrared Target Detection Using Absolute Directional Mean Difference Algorithm |
| Authors | Saed Moradi, Payman Moallem, Mohamad Farzan Sabahi |
| Abstract | Infrared small target detection in an infrared search and track (IRST) system is a challenging task. This situation becomes more complicated when high gray-intensity structural backgrounds appear in the field of view (FoV) of the infrared seeker. While the majority of the infrared small target detection algorithms neglect directional information, in this paper, a directional approach is presented to suppress structural backgrounds and develop more effective detection algorithm. To this end, a similar concept to the average absolute gray difference (AAGD) is utilized to construct a directional small target detection algorithm called absolute directional mean difference (ADMD). Also, an efficient implementation procedure is presented for the proposed algorithm. The proposed algorithm effectively enhances the target area and eliminates background clutter. Simulation results on real infrared images prove the significant effectiveness of the proposed algorithm. |
| Tasks | |
| Published | 2018-10-07 |
| URL | http://arxiv.org/abs/1810.03173v3 |
| http://arxiv.org/pdf/1810.03173v3.pdf | |
| PWC | https://paperswithcode.com/paper/fast-and-robust-small-infrared-target |
| Repo | |
| Framework | |
Variational Rejection Sampling
| Title | Variational Rejection Sampling |
| Authors | Aditya Grover, Ramki Gummadi, Miguel Lazaro-Gredilla, Dale Schuurmans, Stefano Ermon |
| Abstract | Learning latent variable models with stochastic variational inference is challenging when the approximate posterior is far from the true posterior, due to high variance in the gradient estimates. We propose a novel rejection sampling step that discards samples from the variational posterior which are assigned low likelihoods by the model. Our approach provides an arbitrarily accurate approximation of the true posterior at the expense of extra computation. Using a new gradient estimator for the resulting unnormalized proposal distribution, we achieve average improvements of 3.71 nats and 0.21 nats over state-of-the-art single-sample and multi-sample alternatives respectively for estimating marginal log-likelihoods using sigmoid belief networks on the MNIST dataset. |
| Tasks | Latent Variable Models |
| Published | 2018-04-05 |
| URL | http://arxiv.org/abs/1804.01712v1 |
| http://arxiv.org/pdf/1804.01712v1.pdf | |
| PWC | https://paperswithcode.com/paper/variational-rejection-sampling |
| Repo | |
| Framework | |
Natural language understanding for task oriented dialog in the biomedical domain in a low resources context
| Title | Natural language understanding for task oriented dialog in the biomedical domain in a low resources context |
| Authors | Antoine Neuraz, Leonardo Campillos Llanos, Anita Burgun, Sophie Rosset |
| Abstract | In the biomedical domain, the lack of sharable datasets often limit the possibility of developing natural language processing systems, especially dialogue applications and natural language understanding models. To overcome this issue, we explore data generation using templates and terminologies and data augmentation approaches. Namely, we report our experiments using paraphrasing and word representations learned on a large EHR corpus with Fasttext and ELMo, to learn a NLU model without any available dataset. We evaluate on a NLU task of natural language queries in EHRs divided in slot-filling and intent classification sub-tasks. On the slot-filling task, we obtain a F-score of 0.76 with the ELMo representation; and on the classification task, a mean F-score of 0.71. Our results show that this method could be used to develop a baseline system. |
| Tasks | Data Augmentation, Intent Classification, Slot Filling |
| Published | 2018-11-23 |
| URL | http://arxiv.org/abs/1811.09417v2 |
| http://arxiv.org/pdf/1811.09417v2.pdf | |
| PWC | https://paperswithcode.com/paper/natural-language-understanding-for-task |
| Repo | |
| Framework | |
Buried object detection from B-scan ground penetrating radar data using Faster-RCNN
| Title | Buried object detection from B-scan ground penetrating radar data using Faster-RCNN |
| Authors | Minh-Tan Pham, Sébastien Lefèvre |
| Abstract | In this paper, we adapt the Faster-RCNN framework for the detection of underground buried objects (i.e. hyperbola reflections) in B-scan ground penetrating radar (GPR) images. Due to the lack of real data for training, we propose to incorporate more simulated radargrams generated from different configurations using the gprMax toolbox. Our designed CNN is first pre-trained on the grayscale Cifar-10 database. Then, the Faster-RCNN framework based on the pre-trained CNN is trained and fine-tuned on both real and simulated GPR data. Preliminary detection results show that the proposed technique can provide significant improvements compared to classical computer vision methods and hence becomes quite promising to deal with this kind of specific GPR data even with few training samples. |
| Tasks | Object Detection |
| Published | 2018-03-22 |
| URL | http://arxiv.org/abs/1803.08414v1 |
| http://arxiv.org/pdf/1803.08414v1.pdf | |
| PWC | https://paperswithcode.com/paper/buried-object-detection-from-b-scan-ground |
| Repo | |
| Framework | |
Salience Biased Loss for Object Detection in Aerial Images
| Title | Salience Biased Loss for Object Detection in Aerial Images |
| Authors | Peng Sun, Guang Chen, Guerdan Luke, Yi Shang |
| Abstract | Object detection in remote sensing, especially in aerial images, remains a challenging problem due to low image resolution, complex backgrounds, and variation of scale and angles of objects in images. In current implementations, multi-scale based and angle-based networks have been proposed and generate promising results with aerial image detection. In this paper, we propose a novel loss function, called Salience Biased Loss (SBL), for deep neural networks, which uses salience information of the input image to achieve improved performance for object detection. Our novel loss function treats training examples differently based on input complexity in order to avoid the over-contribution of easy cases in the training process. In our experiments, RetinaNet was trained with SBL to generate an one-stage detector, SBL-RetinaNet. SBL-RetinaNet is applied to the largest existing public aerial image dataset, DOTA. Experimental results show our proposed loss function with the RetinaNet architecture outperformed other state-of-art object detection models by at least 4.31 mAP, and RetinaNet by 2.26 mAP with the same inference speed of RetinaNet. |
| Tasks | Object Detection, Object Detection In Aerial Images |
| Published | 2018-10-18 |
| URL | http://arxiv.org/abs/1810.08103v1 |
| http://arxiv.org/pdf/1810.08103v1.pdf | |
| PWC | https://paperswithcode.com/paper/salience-biased-loss-for-object-detection-in |
| Repo | |
| Framework | |
Doubly Bayesian Optimization
| Title | Doubly Bayesian Optimization |
| Authors | Alexander Lavin |
| Abstract | Probabilistic programming systems enable users to encode model structure and naturally reason about uncertainties, which can be leveraged towards improved Bayesian optimization (BO) methods. Here we present a probabilistic program embedding of BO that is capable of addressing main issues such as problematic domains (noisy, non-smooth, high-dimensional) and the neglected inner-optimization. Not only can we utilize programmable structure to incorporate domain knowledge to aid optimization, but dealing with uncertainties and implementing advanced BO techniques become trivial, crucial for use in practice (particularly for non-experts). We demonstrate the efficacy of the approach on optimization benchmarks and a real-world drug development scenario. |
| Tasks | Probabilistic Programming |
| Published | 2018-12-11 |
| URL | http://arxiv.org/abs/1812.04562v4 |
| http://arxiv.org/pdf/1812.04562v4.pdf | |
| PWC | https://paperswithcode.com/paper/doubly-bayesian-optimization |
| Repo | |
| Framework | |
Prediction of Success or Failure for Final Examination using Nearest Neighbor Method to the Trend of Weekly Online Testing
| Title | Prediction of Success or Failure for Final Examination using Nearest Neighbor Method to the Trend of Weekly Online Testing |
| Authors | Hideo Hirose |
| Abstract | Using the trends of estimated abilities in terms of item response theory for online testing, we can predict the success/failure status for the final examination to each student at early stages in courses. In prediction, we applied the newly developed nearest neighbor method for determining the similarity of learning skill in the trends of estimated abilities, resulting a better prediction accuracy for success or failure. This paper shows that the use of the learning analytics incorporating the trends for abilities is effective. ROC curve and recall precision curve are informative to assist the proposed method. |
| Tasks | |
| Published | 2018-12-12 |
| URL | http://arxiv.org/abs/1901.02056v1 |
| http://arxiv.org/pdf/1901.02056v1.pdf | |
| PWC | https://paperswithcode.com/paper/prediction-of-success-or-failure-for-final |
| Repo | |
| Framework | |
Archetypal Analysis for Sparse Representation-based Hyperspectral Sub-pixel Quantification
| Title | Archetypal Analysis for Sparse Representation-based Hyperspectral Sub-pixel Quantification |
| Authors | Lukas Drees, Ribana Roscher, Susanne Wenzel |
| Abstract | The estimation of land cover fractions from remote sensing images is a frequently used indicator of the environmental quality. This paper focuses on the quantification of land cover fractions in an urban area of Berlin, Germany, using simulated hyperspectral EnMAP data with a spatial resolution of 30m$\times$30m. We use constrained sparse representation, where each pixel with unknown surface characteristics is expressed by a weighted linear combination of elementary spectra with known land cover class. We automatically determine the elementary spectra from image reference data using archetypal analysis by simplex volume maximization, and combine it with reversible jump Markov chain Monte Carlo method. In our experiments, the estimation of the automatically derived elementary spectra is compared to the estimation obtained by a manually designed spectral library by means of reconstruction error, mean absolute error of the fraction estimates, sum of fractions, $R^2$, and the number of used elementary spectra. The experiments show that a collection of archetypes can be an adequate and efficient alternative to the manually designed spectral library with respect to the mentioned criteria. |
| Tasks | |
| Published | 2018-02-08 |
| URL | http://arxiv.org/abs/1802.02813v1 |
| http://arxiv.org/pdf/1802.02813v1.pdf | |
| PWC | https://paperswithcode.com/paper/archetypal-analysis-for-sparse-representation |
| Repo | |
| Framework | |
Contrastive Hebbian Learning with Random Feedback Weights
| Title | Contrastive Hebbian Learning with Random Feedback Weights |
| Authors | Georgios Detorakis, Travis Bartley, Emre Neftci |
| Abstract | Neural networks are commonly trained to make predictions through learning algorithms. Contrastive Hebbian learning, which is a powerful rule inspired by gradient backpropagation, is based on Hebb’s rule and the contrastive divergence algorithm. It operates in two phases, the forward (or free) phase, where the data are fed to the network, and a backward (or clamped) phase, where the target signals are clamped to the output layer of the network and the feedback signals are transformed through the transpose synaptic weight matrices. This implies symmetries at the synaptic level, for which there is no evidence in the brain. In this work, we propose a new variant of the algorithm, called random contrastive Hebbian learning, which does not rely on any synaptic weights symmetries. Instead, it uses random matrices to transform the feedback signals during the clamped phase, and the neural dynamics are described by first order non-linear differential equations. The algorithm is experimentally verified by solving a Boolean logic task, classification tasks (handwritten digits and letters), and an autoencoding task. This article also shows how the parameters affect learning, especially the random matrices. We use the pseudospectra analysis to investigate further how random matrices impact the learning process. Finally, we discuss the biological plausibility of the proposed algorithm, and how it can give rise to better computational models for learning. |
| Tasks | |
| Published | 2018-06-19 |
| URL | http://arxiv.org/abs/1806.07406v1 |
| http://arxiv.org/pdf/1806.07406v1.pdf | |
| PWC | https://paperswithcode.com/paper/contrastive-hebbian-learning-with-random |
| Repo | |
| Framework | |
Actor-Action Semantic Segmentation with Region Masks
| Title | Actor-Action Semantic Segmentation with Region Masks |
| Authors | Kang Dang, Chunluan Zhou, Zhigang Tu, Michael Hoy, Justin Dauwels, Junsong Yuan |
| Abstract | In this paper, we study the actor-action semantic segmentation problem, which requires joint labeling of both actor and action categories in video frames. One major challenge for this task is that when an actor performs an action, different body parts of the actor provide different types of cues for the action category and may receive inconsistent action labeling when they are labeled independently. To address this issue, we propose an end-to-end region-based actor-action segmentation approach which relies on region masks from an instance segmentation algorithm. Our main novelty is to avoid labeling pixels in a region mask independently - instead we assign a single action label to these pixels to achieve consistent action labeling. When a pixel belongs to multiple region masks, max pooling is applied to resolve labeling conflicts. Our approach uses a two-stream network as the front-end (which learns features capturing both appearance and motion information), and uses two region-based segmentation networks as the back-end (which takes the fused features from the two-stream network as the input and predicts actor-action labeling). Experiments on the A2D dataset demonstrate that both the region-based segmentation strategy and the fused features from the two-stream network contribute to the performance improvements. The proposed approach outperforms the state-of-the-art results by more than 8% in mean class accuracy, and more than 5% in mean class IOU, which validates its effectiveness. |
| Tasks | action segmentation, Instance Segmentation, Semantic Segmentation |
| Published | 2018-07-23 |
| URL | http://arxiv.org/abs/1807.08430v1 |
| http://arxiv.org/pdf/1807.08430v1.pdf | |
| PWC | https://paperswithcode.com/paper/actor-action-semantic-segmentation-with |
| Repo | |
| Framework | |
A Survey of the Usages of Deep Learning in Natural Language Processing
| Title | A Survey of the Usages of Deep Learning in Natural Language Processing |
| Authors | Daniel W. Otter, Julian R. Medina, Jugal K. Kalita |
| Abstract | Over the last several years, the field of natural language processing has been propelled forward by an explosion in the use of deep learning models. This survey provides a brief introduction to the field and a quick overview of deep learning architectures and methods. It then sifts through the plethora of recent studies and summarizes a large assortment of relevant contributions. Analyzed research areas include several core linguistic processing issues in addition to a number of applications of computational linguistics. A discussion of the current state of the art is then provided along with recommendations for future research in the field. |
| Tasks | |
| Published | 2018-07-27 |
| URL | https://arxiv.org/abs/1807.10854v3 |
| https://arxiv.org/pdf/1807.10854v3.pdf | |
| PWC | https://paperswithcode.com/paper/a-survey-of-the-usages-of-deep-learning-in |
| Repo | |
| Framework | |
Eyes are the Windows to the Soul: Predicting the Rating of Text Quality Using Gaze Behaviour
| Title | Eyes are the Windows to the Soul: Predicting the Rating of Text Quality Using Gaze Behaviour |
| Authors | Sandeep Mathias, Diptesh Kanojia, Kevin Patel, Samarth Agarwal, Abhijit Mishra, Pushpak Bhattacharyya |
| Abstract | Predicting a reader’s rating of text quality is a challenging task that involves estimating different subjective aspects of the text, like structure, clarity, etc. Such subjective aspects are better handled using cognitive information. One such source of cognitive information is gaze behaviour. In this paper, we show that gaze behaviour does indeed help in effectively predicting the rating of text quality. To do this, we first model text quality as a function of three properties - organization, coherence and cohesion. Then, we demonstrate how capturing gaze behaviour helps in predicting each of these properties, and hence the overall quality, by reporting improvements obtained by adding gaze features to traditional textual features for score prediction. We also hypothesize that if a reader has fully understood the text, the corresponding gaze behaviour would give a better indication of the assigned rating, as opposed to partial understanding. Our experiments validate this hypothesis by showing greater agreement between the given rating and the predicted rating when the reader has a full understanding of the text. |
| Tasks | |
| Published | 2018-10-11 |
| URL | http://arxiv.org/abs/1810.04839v1 |
| http://arxiv.org/pdf/1810.04839v1.pdf | |
| PWC | https://paperswithcode.com/paper/eyes-are-the-windows-to-the-soul-predicting |
| Repo | |
| Framework | |
