Paper Group NANR 200
Accidental exploration through value predictors. Polarimetric Relative Pose Estimation. Hyper-Regularization: An Adaptive Choice for the Learning Rate in Gradient Descent. A Context-based Framework for Modeling the Role and Function of On-line Resource Citations in Scientific Literature. Knowledge-Aware Deep Dual Networks for Text-Based Mortality P …
Accidental exploration through value predictors
| Title | Accidental exploration through value predictors |
| Authors | Tomasz Kisielewski, Damian Leśniak, Maia Pasek |
| Abstract | Infinite length of trajectories is an almost universal assumption in the theoretical foundations of reinforcement learning. In practice learning occurs on finite trajectories. In this paper we examine a specific result of this disparity, namely a strong bias of the time-bounded Every-visit Monte Carlo value estimator. This manifests as a vastly different learning dynamic for algorithms that use value predictors, including encouraging or discouraging exploration. We investigate these claims theoretically for a one dimensional random walk, and empirically on a number of simple environments. We use GAE as an algorithm involving a value predictor and evolution strategies as a reference point. |
| Tasks | |
| Published | 2019-01-01 |
| URL | https://openreview.net/forum?id=S1llBiR5YX |
| https://openreview.net/pdf?id=S1llBiR5YX | |
| PWC | https://paperswithcode.com/paper/accidental-exploration-through-value |
| Repo | |
| Framework | |
Polarimetric Relative Pose Estimation
| Title | Polarimetric Relative Pose Estimation |
| Authors | Zhaopeng Cui, Viktor Larsson, Marc Pollefeys |
| Abstract | In this paper we consider the problem of relative pose estimation from two images with per-pixel polarimetric information. Using these additional measurements we derive a simple minimal solver for the essential matrix which only requires two point correspondences. The polarization constraints allow us to pointwise recover the 3D surface normal up to a two-fold ambiguity for the diffuse reflection. Since this ambiguity exists per point, there is a combinatorial explosion of possibilities. However, since our solver only requires two point correspondences, we only need to consider 16 configurations when solving for the relative pose. Once the relative orientation is recovered, we show that it is trivial to resolve the ambiguity for the remaining points. For robustness, we also propose a joint optimization between the relative pose and the refractive index to handle the refractive distortion. In experiments, on both synthetic and real data, we demonstrate that by leveraging the additional information available from polarization cameras, we can improve over classical methods which only rely on the 2D-point locations to estimate the geometry. Finally, we demonstrate the practical applicability of our approach by integrating it into a state-of-the-art global Structure-from-Motion pipeline. |
| Tasks | Pose Estimation |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Cui_Polarimetric_Relative_Pose_Estimation_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Cui_Polarimetric_Relative_Pose_Estimation_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/polarimetric-relative-pose-estimation |
| Repo | |
| Framework | |
Hyper-Regularization: An Adaptive Choice for the Learning Rate in Gradient Descent
| Title | Hyper-Regularization: An Adaptive Choice for the Learning Rate in Gradient Descent |
| Authors | Guangzeng Xie, Hao Jin, Dachao Lin, Zhihua Zhang |
| Abstract | We present a novel approach for adaptively selecting the learning rate in gradient descent methods. Specifically, we impose a regularization term on the learning rate via a generalized distance, and cast the joint updating process of the parameter and the learning rate into a maxmin problem. Some existing schemes such as AdaGrad (diagonal version) and WNGrad can be rederived from our approach. Based on our approach, the updating rules for the learning rate do not rely on the smoothness constant of optimization problems and are robust to the initial learning rate. We theoretically analyze our approach in full batch and online learning settings, which achieves comparable performances with other first-order gradient-based algorithms in terms of accuracy as well as convergence rate. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=S1e_ssC5F7 |
| https://openreview.net/pdf?id=S1e_ssC5F7 | |
| PWC | https://paperswithcode.com/paper/hyper-regularization-an-adaptive-choice-for |
| Repo | |
| Framework | |
A Context-based Framework for Modeling the Role and Function of On-line Resource Citations in Scientific Literature
| Title | A Context-based Framework for Modeling the Role and Function of On-line Resource Citations in Scientific Literature |
| Authors | He Zhao, Zhunchen Luo, Chong Feng, Anqing Zheng, Xiaopeng Liu |
| Abstract | We introduce a new task of modeling the role and function for on-line resource citations in scientific literature. By categorizing the on-line resources and analyzing the purpose of resource citations in scientific texts, it can greatly help resource search and recommendation systems to better understand and manage the scientific resources. For this novel task, we are the first to create an annotation scheme, which models the different granularity of information from a hierarchical perspective. And we construct a dataset SciRes, which includes 3,088 manually annotated resource contexts. In this paper, we propose a possible solution by using a multi-task framework to build the scientific resource classifier (SciResCLF) for jointly recognizing the role and function types. Then we use the classification results to help a scientific resource recommendation (SciResREC) task. Experiments show that our model achieves the best results on both the classification task and the recommendation task. The SciRes dataset is released for future research. |
| Tasks | Recommendation Systems |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1524/ |
| https://www.aclweb.org/anthology/D19-1524 | |
| PWC | https://paperswithcode.com/paper/a-context-based-framework-for-modeling-the |
| Repo | |
| Framework | |
Knowledge-Aware Deep Dual Networks for Text-Based Mortality Prediction
| Title | Knowledge-Aware Deep Dual Networks for Text-Based Mortality Prediction |
| Authors | Ning Liu, Pan Lu, Wei Zhang, Jianyong Wang |
| Abstract | Mortality prediction is one of the essential tasks in medical data mining and is significant for inferring clinical outcomes. With a large number of medical notes collected from hospitals, there is an urgent need for developing effective models for predicting mortality based on them. In contrast to structured electronic health records, medical notes are unstructured texts written by experienced caregivers and contain more complicated information about patients, posing more challenges for modeling. Most previous studies rely on tedious hand-crafted features or generating indirect features based on some statistical models such as topic modeling, which might incur information loss for later model training. Recently, some deep models have been proposed to unify the stages of feature construction and model training. However, domain concept knowledge has been neglected, which is important to gain a better understanding of medical notes. To address the above issues, we propose novel Knowledge-aware Deep Dual Networks (K-DDN) for the text-based mortality prediction task. Specifically, a simple deep dual network is first proposed to fuse the representations of medical knowledge and raw text for prediction. Afterward, we incorporate a co-attention mechanism into the basic model, guiding the knowledge and text representation learning with the help of each other. Experimental results on two publicly real-world datasets show the proposed deep dual networks outperform state-of-the-art methods and the co-attention mechanism can further improve the performance. |
| Tasks | Medical Diagnosis, Mortality Prediction, Representation Learning |
| Published | 2019-06-06 |
| URL | https://ieeexplore.ieee.org/document/8731459/authors#authors |
| https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8731459 | |
| PWC | https://paperswithcode.com/paper/knowledge-aware-deep-dual-networks-for-text |
| Repo | |
| Framework | |
MVTec AD – A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection
| Title | MVTec AD – A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection |
| Authors | Paul Bergmann, Michael Fauser, David Sattlegger, Carsten Steger |
| Abstract | The detection of anomalous structures in natural image data is of utmost importance for numerous tasks in the field of computer vision. The development of methods for unsupervised anomaly detection requires data on which to train and evaluate new approaches and ideas. We introduce the MVTec Anomaly Detection (MVTec AD) dataset containing 5354 high-resolution color images of different object and texture categories. It contains normal, i.e., defect-free, images intended for training and images with anomalies intended for testing. The anomalies manifest themselves in the form of over 70 different types of defects such as scratches, dents, contaminations, and various structural changes. In addition, we provide pixel-precise ground truth regions for all anomalies. We also conduct a thorough evaluation of current state-of-the-art unsupervised anomaly detection methods based on deep architectures such as convolutional autoencoders, generative adversarial networks, and feature descriptors using pre-trained convolutional neural networks, as well as classical computer vision methods. This initial benchmark indicates that there is considerable room for improvement. To the best of our knowledge, this is the first comprehensive, multi-object, multi-defect dataset for anomaly detection that provides pixel-accurate ground truth regions and focuses on real-world applications. |
| Tasks | Anomaly Detection, Unsupervised Anomaly Detection |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Bergmann_MVTec_AD_--_A_Comprehensive_Real-World_Dataset_for_Unsupervised_Anomaly_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Bergmann_MVTec_AD_--_A_Comprehensive_Real-World_Dataset_for_Unsupervised_Anomaly_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/mvtec-ad-a-comprehensive-real-world-dataset |
| Repo | |
| Framework | |
Generating Diverse and Descriptive Image Captions Using Visual Paraphrases
| Title | Generating Diverse and Descriptive Image Captions Using Visual Paraphrases |
| Authors | Lixin Liu, Jiajun Tang, Xiaojun Wan, Zongming Guo |
| Abstract | Recently there has been significant progress in image captioning with the help of deep learning. However, captions generated by current state-of-the-art models are still far from satisfactory, despite high scores in terms of conventional metrics such as BLEU and CIDEr. Human-written captions are diverse, informative and precise, but machine-generated captions seem to be simple, vague and dull. In this paper, aimed at improving diversity and descriptiveness characteristics of generated image captions, we propose a model utilizing visual paraphrases (different sentences describing the same image) in captioning datasets. We explore different strategies to select useful visual paraphrase pairs for training by designing a variety of scoring functions. Our model consists of two decoding stages, where a preliminary caption is generated in the first stage and then paraphrased into a more diverse and descriptive caption in the second stage. Extensive experiments are conducted on the benchmark MS COCO dataset, with automatic evaluation and human evaluation results verifying the effectiveness of our model. |
| Tasks | Image Captioning |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Liu_Generating_Diverse_and_Descriptive_Image_Captions_Using_Visual_Paraphrases_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Liu_Generating_Diverse_and_Descriptive_Image_Captions_Using_Visual_Paraphrases_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/generating-diverse-and-descriptive-image |
| Repo | |
| Framework | |
Compound Density Networks
| Title | Compound Density Networks |
| Authors | Agustinus Kristiadi, Asja Fischer |
| Abstract | Despite the huge success of deep neural networks (NNs), finding good mechanisms for quantifying their prediction uncertainty is still an open problem. It was recently shown, that using an ensemble of NNs trained with a proper scoring rule leads to results competitive to those of Bayesian NNs. This ensemble method can be understood as finite mixture model with uniform mixing weights. We build on this mixture model approach and increase its flexibility by replacing the fixed mixing weights by an adaptive, input-dependent distribution (specifying the probability of each component) represented by an NN, and by considering uncountably many mixture components. The resulting model can be seen as the continuous counterpart to mixture density networks and is therefore referred to as compound density network. We empirically show that the proposed model results in better uncertainty estimates and is more robust to adversarial examples than previous approaches. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=rkgv9oRqtQ |
| https://openreview.net/pdf?id=rkgv9oRqtQ | |
| PWC | https://paperswithcode.com/paper/compound-density-networks |
| Repo | |
| Framework | |
NL2pSQL: Generating Pseudo-SQL Queries from Under-Specified Natural Language Questions
| Title | NL2pSQL: Generating Pseudo-SQL Queries from Under-Specified Natural Language Questions |
| Authors | Fuxiang Chen, Seung-won Hwang, Jaegul Choo, Jung-Woo Ha, Sunghun Kim |
| Abstract | Generating SQL codes from natural language questions (NL2SQL) is an emerging research area. Existing studies have mainly focused on clear scenarios where specified information is fully given to generate a SQL query. However, in developer forums such as Stack Overflow, questions cover more diverse tasks including table manipulation or performance issues, where a table is not specified. The SQL query posted in Stack Overflow, Pseudo-SQL (pSQL), does not usually contain table schemas and is not necessarily executable, is sufficient to guide developers. Here we describe a new NL2pSQL task to generate pSQL codes from natural language questions on under-specified database issues, NL2pSQL. In addition, we define two new metrics suitable for the proposed NL2pSQL task, Canonical-BLEU and SQL-BLEU, instead of the conventional BLEU. With a baseline model using sequence-to-sequence architecture integrated by denoising autoencoder, we confirm the validity of our task. Experiments show that the proposed NL2pSQL approach yields well-formed queries (up to 43{%} more than a standard Seq2Seq model). Our code and datasets will be publicly released. |
| Tasks | Denoising |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1262/ |
| https://www.aclweb.org/anthology/D19-1262 | |
| PWC | https://paperswithcode.com/paper/nl2psql-generating-pseudo-sql-queries-from |
| Repo | |
| Framework | |
The Four Stages of Machine Translation Acceptance in a Freelancer’s Life
| Title | The Four Stages of Machine Translation Acceptance in a Freelancer’s Life |
| Authors | Maria Sgourou |
| Abstract | Technology is a big challenge and raises many questions and issues when it comes to its application in the translation process, but translation{'}s biggest problem is not technology; it is rather how technology is perceived by translators. MT developers and researchers should take into account this perception and move towards a more democratized approach to include the base of the translation industry and perhaps its more valuable asset, the translators. |
| Tasks | Machine Translation |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-8717/ |
| https://www.aclweb.org/anthology/W19-8717 | |
| PWC | https://paperswithcode.com/paper/the-four-stages-of-machine-translation |
| Repo | |
| Framework | |
PMS-Net: Robust Haze Removal Based on Patch Map for Single Images
| Title | PMS-Net: Robust Haze Removal Based on Patch Map for Single Images |
| Authors | Wei-Ting Chen, Jian-Jiun Ding, Sy-Yen Kuo |
| Abstract | In this paper, we proposed a novel haze removal algorithm based on a new feature called the patch map. Conventional patch-based haze removal algorithms (e.g. the Dark Channel prior) usually performs dehazing with a fixed patch size. However, it may produce several problems in recovered results such as oversaturation and color distortion. Therefore, in this paper, we designed an adaptive and automatic patch size selection model called the Patch Map Selection Network (PMS-Net) to select the patch size corresponding to each pixel. This network is designed based on the convolutional neural network (CNN), which can generate the patch map from the image to image. Experimental results on both synthesized and real-world hazy images show that, with the combination of the proposed PMS-Net, the performance in haze removal is much better than that of other state-of-the-art algorithms and we can address the problems caused by the fixed patch size. |
| Tasks | |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Chen_PMS-Net_Robust_Haze_Removal_Based_on_Patch_Map_for_Single_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Chen_PMS-Net_Robust_Haze_Removal_Based_on_Patch_Map_for_Single_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/pms-net-robust-haze-removal-based-on-patch |
| Repo | |
| Framework | |
Stochastic Learning of Additive Second-Order Penalties with Applications to Fairness
| Title | Stochastic Learning of Additive Second-Order Penalties with Applications to Fairness |
| Authors | Heinrich Jiang, Yifan Wu, Ofir Nachum |
| Abstract | Many notions of fairness may be expressed as linear constraints, and the resulting constrained objective is often optimized by transforming the problem into its Lagrangian dual with additive linear penalties. In non-convex settings, the resulting problem may be difficult to solve as the Lagrangian is not guaranteed to have a deterministic saddle-point equilibrium. In this paper, we propose to modify the linear penalties to second-order ones, and we argue that this results in a more practical training procedure in non-convex, large-data settings. For one, the use of second-order penalties allows training the penalized objective with a fixed value of the penalty coefficient, thus avoiding the instability and potential lack of convergence associated with two-player min-max games. Secondly, we derive a method for efficiently computing the gradients associated with the second-order penalties in stochastic mini-batch settings. Our resulting algorithm performs well empirically, learning an appropriately fair classifier on a number of standard benchmarks. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=Bke0rjR5F7 |
| https://openreview.net/pdf?id=Bke0rjR5F7 | |
| PWC | https://paperswithcode.com/paper/stochastic-learning-of-additive-second-order |
| Repo | |
| Framework | |
Dual Attention Matching for Audio-Visual Event Localization
| Title | Dual Attention Matching for Audio-Visual Event Localization |
| Authors | Yu Wu, Linchao Zhu, Yan Yan, Yi Yang |
| Abstract | In this paper, we investigate the audio-visual event localization problem. This task is to localize a visible and audible event in a video. Previous methods first divide a video into short segments, and then fuse visual and acoustic features at the segment level. The duration of these segments is usually short, making the visual and acoustic feature of each segment possibly not well aligned. Direct concatenation of the two features at the segment level can be vulnerable to a minor temporal misalignment of the two signals. We propose a Dual Attention Matching (DAM) module to cover a longer video duration for better high-level event information modeling, while the local temporal information is attained by the global cross-check mechanism. Our premise is that one should watch the whole video to understand the high-level event, while shorter segments should be checked in detail for localization. Specifically, the global feature of one modality queries the local feature in the other modality in a bi-directional way. With temporal co-occurrence encoded between auditory and visual signals, DAM can be readily applied in various audio-visual event localization tasks, e.g., cross-modality localization, supervised event localization. Experiments on the AVE dataset show our method outperforms the state-of-the-art by a large margin. |
| Tasks | |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Wu_Dual_Attention_Matching_for_Audio-Visual_Event_Localization_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Wu_Dual_Attention_Matching_for_Audio-Visual_Event_Localization_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/dual-attention-matching-for-audio-visual |
| Repo | |
| Framework | |
Comparing Unsupervised Word Translation Methods Step by Step
| Title | Comparing Unsupervised Word Translation Methods Step by Step |
| Authors | Mareike Hartmann, Yova Kementchedjhieva, Anders Søgaard |
| Abstract | Cross-lingual word vector space alignment is the task of mapping the vocabularies of two languages into a shared semantic space, which can be used for dictionary induction, unsupervised machine translation, and transfer learning. In the unsupervised regime, an initial seed dictionary is learned in the absence of any known correspondences between words, through {\bf distribution matching}, and the seed dictionary is then used to supervise the induction of the final alignment in what is typically referred to as a (possibly iterative) {\bf refinement} step. We focus on the first step and compare distribution matching techniques in the context of language pairs for which mixed training stability and evaluation scores have been reported. We show that, surprisingly, when looking at this initial step in isolation, vanilla GANs are superior to more recent methods, both in terms of precision and robustness. The improvements reported by more recent methods thus stem from the refinement techniques, and we show that we can obtain state-of-the-art performance combining vanilla GANs with such refinement techniques. |
| Tasks | Machine Translation, Transfer Learning, Unsupervised Machine Translation |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/8836-comparing-unsupervised-word-translation-methods-step-by-step |
| http://papers.nips.cc/paper/8836-comparing-unsupervised-word-translation-methods-step-by-step.pdf | |
| PWC | https://paperswithcode.com/paper/comparing-unsupervised-word-translation |
| Repo | |
| Framework | |
Supervised and Unsupervised Machine Translation for Myanmar-English and Khmer-English
| Title | Supervised and Unsupervised Machine Translation for Myanmar-English and Khmer-English |
| Authors | Benjamin Marie, Hour Kaing, Aye Myat Mon, Chenchen Ding, Atsushi Fujita, Masao Utiyama, Eiichiro Sumita |
| Abstract | This paper presents the NICT{'}s supervised and unsupervised machine translation systems for the WAT2019 Myanmar-English and Khmer-English translation tasks. For all the translation directions, we built state-of-the-art supervised neural (NMT) and statistical (SMT) machine translation systems, using monolingual data cleaned and normalized. Our combination of NMT and SMT performed among the best systems for the four translation directions. We also investigated the feasibility of unsupervised machine translation for low-resource and distant language pairs and confirmed observations of previous work showing that unsupervised MT is still largely unable to deal with them. |
| Tasks | Machine Translation, Unsupervised Machine Translation |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5206/ |
| https://www.aclweb.org/anthology/D19-5206 | |
| PWC | https://paperswithcode.com/paper/supervised-and-unsupervised-machine |
| Repo | |
| Framework | |
