Paper Group NANR 93
Transfer Learning on Manifolds via Learned Transport Operators. The Information-Autoencoding Family: A Lagrangian Perspective on Latent Variable Generative Modeling. Training deep learning based denoisers without ground truth data. Stacked Latent Attention for Multimodal Reasoning. Causality Analysis of Twitter Sentiments and Stock Market Returns. …
Transfer Learning on Manifolds via Learned Transport Operators
| Title | Transfer Learning on Manifolds via Learned Transport Operators |
| Authors | Marissa Connor, Christopher Rozell |
| Abstract | Within-class variation in a high-dimensional dataset can be modeled as being on a low-dimensional manifold due to the constraints of the physical processes producing that variation (e.g., translation, illumination, etc.). We desire a method for learning a representation of the manifolds induced by identity-preserving transformations that can be used to increase robustness, reduce the training burden, and encourage interpretability in machine learning tasks. In particular, what is needed is a representation of the transformation manifold that can robustly capture the shape of the manifold from the input data, generate new points on the manifold, and extend transformations outside of the training domain without significantly increasing the error. Previous work has proposed algorithms to efficiently learn analytic operators (called transport operators) that define the process of transporting one data point on a manifold to another. The main contribution of this paper is to define two transfer learning methods that use this generative manifold representation to learn natural transformations and incorporate them into new data. The first method uses this representation in a novel randomized approach to transfer learning that employs the learned generative model to map out unseen regions of the data space. These results are shown through demonstrations of transfer learning in a data augmentation task for few-shot image classification. The second method use of transport operators for injecting specific transformations into new data examples which allows for realistic image animation and informed data augmentation. These results are shown on stylized constructions using the classic swiss roll data structure and in demonstrations of transfer learning in a data augmentation task for few-shot image classification. We also propose the use of transport operators for injecting transformations into new data examples which allows for realistic image animation. |
| Tasks | Data Augmentation, Few-Shot Image Classification, Image Animation, Image Classification, Transfer Learning |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=rJL6pz-CZ |
| https://openreview.net/pdf?id=rJL6pz-CZ | |
| PWC | https://paperswithcode.com/paper/transfer-learning-on-manifolds-via-learned |
| Repo | |
| Framework | |
The Information-Autoencoding Family: A Lagrangian Perspective on Latent Variable Generative Modeling
| Title | The Information-Autoencoding Family: A Lagrangian Perspective on Latent Variable Generative Modeling |
| Authors | Shengjia Zhao, Jiaming Song, Stefano Ermon |
| Abstract | A variety of learning objectives have been recently proposed for training generative models. We show that many of them, including InfoGAN, ALI/BiGAN, ALICE, CycleGAN, VAE, $\beta$-VAE, adversarial autoencoders, AVB, and InfoVAE, are Lagrangian duals of the same primal optimization problem. This generalization reveals the implicit modeling trade-offs between flexibility and computational requirements being made by these models. Furthermore, we characterize the class of all objectives that can be optimized under certain computational constraints. Finally, we show how this new Lagrangian perspective can explain undesirable behavior of existing methods and provide new principled solutions. |
| Tasks | |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=ryZERzWCZ |
| https://openreview.net/pdf?id=ryZERzWCZ | |
| PWC | https://paperswithcode.com/paper/the-information-autoencoding-family-a-1 |
| Repo | |
| Framework | |
Training deep learning based denoisers without ground truth data
| Title | Training deep learning based denoisers without ground truth data |
| Authors | Shakarim Soltanayev, Se Young Chun |
| Abstract | Recently developed deep-learning-based denoisers often outperform state-of-the-art conventional denoisers, such as the BM3D. They are typically trained to minimizethe mean squared error (MSE) between the output image of a deep neural networkand a ground truth image. In deep learning based denoisers, it is important to use high quality noiseless ground truth data for high performance, but it is often challenging or even infeasible to obtain noiseless images in application areas such as hyperspectral remote sensing and medical imaging. In this article, we propose a method based on Stein’s unbiased risk estimator (SURE) for training deep neural network denoisers only based on the use of noisy images. We demonstrate that our SURE-based method, without the use of ground truth data, is able to train deep neural network denoisers to yield performances close to those networks trained with ground truth, and to outperform the state-of-the-art denoiser BM3D. Further improvements were achieved when noisy test images were used for training of denoiser networks using our proposed SURE-based method. |
| Tasks | |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7587-training-deep-learning-based-denoisers-without-ground-truth-data |
| http://papers.nips.cc/paper/7587-training-deep-learning-based-denoisers-without-ground-truth-data.pdf | |
| PWC | https://paperswithcode.com/paper/training-deep-learning-based-denoisers-1 |
| Repo | |
| Framework | |
Stacked Latent Attention for Multimodal Reasoning
| Title | Stacked Latent Attention for Multimodal Reasoning |
| Authors | Haoqi Fan, Jiatong Zhou |
| Abstract | Attention has shown to be a pivotal development in deep learning and has been used for a multitude of multimodal learning tasks such as visual question answering and image captioning. In this work, we pinpoint the potential limitations to the design of a traditional attention model. We identify that 1) current attention mechanisms discard the latent information from intermediate reasoning, losing the positional information already captured by the attention heatmaps and 2) stacked attention, a common way to improve spatial reasoning, may have suboptimal performance because of the vanishing gradient problem. We introduce a novel attention architecture to address these problems, in which all spatial configuration information contained in the intermediate reasoning process is retained in a pathway of convolutional layers. We show that this new attention leads to substantial improvements in multiple multimodal reasoning tasks, including achieving single model performance without using external knowledge comparable to the state-of-the-art on the VQA dataset, as well as clear gains for the image captioning task. |
| Tasks | Image Captioning, Question Answering, Visual Question Answering |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Fan_Stacked_Latent_Attention_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Fan_Stacked_Latent_Attention_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/stacked-latent-attention-for-multimodal |
| Repo | |
| Framework | |
Causality Analysis of Twitter Sentiments and Stock Market Returns
| Title | Causality Analysis of Twitter Sentiments and Stock Market Returns |
| Authors | Narges Tabari, Piyusha Biswas, Bhanu Praneeth, Armin Seyeditabari, Mirsad Hadzikadic, Wlodek Zadrozny |
| Abstract | Sentiment analysis is the process of identifying the opinion expressed in text. Recently, it has been used to study behavioral finance, and in particular the effect of opinions and emotions on economic or financial decisions. In this paper, we use a public dataset of labeled tweets that has been labeled by Amazon Mechanical Turk and then we propose a baseline classification model. Then, by using Granger causality of both sentiment datasets with the different stocks, we shows that there is causality between social media and stock market returns (in both directions) for many stocks. Finally, We evaluate this causality analysis by showing that in the event of a specific news on certain dates, there are evidences of trending the same news on Twitter for that stock. |
| Tasks | Sentiment Analysis, Twitter Sentiment Analysis |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-3102/ |
| https://www.aclweb.org/anthology/W18-3102 | |
| PWC | https://paperswithcode.com/paper/causality-analysis-of-twitter-sentiments-and |
| Repo | |
| Framework | |
When ACE met KBP: End-to-End Evaluation of Knowledge Base Population with Component-level Annotation
| Title | When ACE met KBP: End-to-End Evaluation of Knowledge Base Population with Component-level Annotation |
| Authors | Bonan Min, Marjorie Freedman, Roger Bock, Ralph Weischedel |
| Abstract | |
| Tasks | Knowledge Base Population, Named Entity Recognition, Question Answering, Relation Extraction, Slot Filling |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1031/ |
| https://www.aclweb.org/anthology/L18-1031 | |
| PWC | https://paperswithcode.com/paper/when-ace-met-kbp-end-to-end-evaluation-of |
| Repo | |
| Framework | |
Toward An Epic Epigraph Graph
| Title | Toward An Epic Epigraph Graph |
| Authors | Francis Bond, Graham Matthews |
| Abstract | |
| Tasks | |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1522/ |
| https://www.aclweb.org/anthology/L18-1522 | |
| PWC | https://paperswithcode.com/paper/toward-an-epic-epigraph-graph |
| Repo | |
| Framework | |
TakeLab at SemEval-2018 Task12: Argument Reasoning Comprehension with Skip-Thought Vectors
| Title | TakeLab at SemEval-2018 Task12: Argument Reasoning Comprehension with Skip-Thought Vectors |
| Authors | Ana Brassard, Tin Kuculo, Filip Boltu{\v{z}}i{'c}, Jan {\v{S}}najder |
| Abstract | This paper describes our system for the SemEval-2018 Task 12: Argument Reasoning Comprehension Task. We utilize skip-thought vectors, sentence-level distributional vectors inspired by the popular word embeddings and the skip-gram model. We encode preprocessed sentences from the dataset into vectors, then perform a binary supervised classification of the warrant that justifies the use of the reason as support for the claim. We explore a few variations of the model, reaching 54.1{%} accuracy on the test set, which placed us 16th out of 22 teams participating in the task. |
| Tasks | Common Sense Reasoning, Natural Language Inference, Word Embeddings |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/S18-1192/ |
| https://www.aclweb.org/anthology/S18-1192 | |
| PWC | https://paperswithcode.com/paper/takelab-at-semeval-2018-task12-argument |
| Repo | |
| Framework | |
Universal Language Model Fine-tuning for Patent Classification
| Title | Universal Language Model Fine-tuning for Patent Classification |
| Authors | Jason Hepburn |
| Abstract | This paper describes the methods used for the 2018 ALTA Shared Task. The task this year was to automatically classify Australian patents into their main International Patent Classification section. Our final submission used a Support Vector Machine (SVM) and Universal Language Model with Fine-tuning (ULMFiT). Our system achieved the best results in the student category. |
| Tasks | Language Modelling |
| Published | 2018-12-01 |
| URL | https://www.aclweb.org/anthology/U18-1013/ |
| https://www.aclweb.org/anthology/U18-1013 | |
| PWC | https://paperswithcode.com/paper/universal-language-model-fine-tuning-for |
| Repo | |
| Framework | |
Generative Semantic Manipulation with Mask-Contrasting GAN
| Title | Generative Semantic Manipulation with Mask-Contrasting GAN |
| Authors | Xiaodan Liang, Hao Zhang, Liang Lin, Eric Xing |
| Abstract | Despite the promising results on paired/unpaired image-to-image translation achieved by Generative Adversarial Networks (GANs), prior works often only transfer the low-level information (e.g. color or texture changes), but fail to manipulate high-level semantic meanings (e.g., geometric structure or content) of different object regions. On the other hand, while some researches can synthesize compelling real-world images given a class label or caption, they cannot condition on arbitrary shapes or structures, which largely limits their application scenarios and interpretive capability of model results. In this work, we focus on a more challenging semantic manipulation task, aiming at modifying the semantic meaning of an object while preserving its own characteristics (e.g. viewpoints and shapes), such as cow$ ightarrow$sheep, motor$ ightarrow$ bicycle, cat$ ightarrow$dog. To tackle such large semantic changes, we introduce a contrasting GAN (contrast-GAN) with a novel adversarial contrasting objective which is able to perform all types of semantic translations with one category-conditional generator. Instead of directly making the synthesized samples close to target data as previous GANs did, our adversarial contrasting objective optimizes over the distance comparisons between samples, that is, enforcing the manipulated data be semantically closer to the real data with target category than the input data. Equipped with the new contrasting objective, a novel mask-conditional contrast-GAN architecture is proposed to enable disentangle image background with object semantic changes. Extensive qualitative and quantitative experiments on several semantic manipulation tasks on ImageNet and MSCOCO dataset show considerable performance gain by our contrast-GAN over other conditional GANs. |
| Tasks | Image-to-Image Translation |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Liang_Generative_Semantic_Manipulation_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Liang_Generative_Semantic_Manipulation_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/generative-semantic-manipulation-with-mask |
| Repo | |
| Framework | |
Multiple-Step Greedy Policies in Approximate and Online Reinforcement Learning
| Title | Multiple-Step Greedy Policies in Approximate and Online Reinforcement Learning |
| Authors | Yonathan Efroni, Gal Dalal, Bruno Scherrer, Shie Mannor |
| Abstract | Multiple-step lookahead policies have demonstrated high empirical competence in Reinforcement Learning, via the use of Monte Carlo Tree Search or Model Predictive Control. In a recent work (Efroni et al., 2018), multiple-step greedy policies and their use in vanilla Policy Iteration algorithms were proposed and analyzed. In this work, we study multiple-step greedy algorithms in more practical setups. We begin by highlighting a counter-intuitive difficulty, arising with soft-policy updates: even in the absence of approximations, and contrary to the 1-step-greedy case, monotonic policy improvement is not guaranteed unless the update stepsize is sufficiently large. Taking particular care about this difficulty, we formulate and analyze online and approximate algorithms that use such a multi-step greedy operator. |
| Tasks | |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7770-multiple-step-greedy-policies-in-approximate-and-online-reinforcement-learning |
| http://papers.nips.cc/paper/7770-multiple-step-greedy-policies-in-approximate-and-online-reinforcement-learning.pdf | |
| PWC | https://paperswithcode.com/paper/multiple-step-greedy-policies-in-approximate |
| Repo | |
| Framework | |
A Comparison of Entity Matching Methods between English and Japanese Katakana
| Title | A Comparison of Entity Matching Methods between English and Japanese Katakana |
| Authors | Michiharu Yamashita, Hideki Awashima, Hidekazu Oiwa |
| Abstract | Japanese Katakana is one component of the Japanese writing system and is used to express English terms, loanwords, and onomatopoeia in Japanese characters based on the phonemes. The main purpose of this research is to find the best entity matching methods between English and Katakana. We built two research questions to clarify which types of entity matching systems works better than others. The first question is what transliteration should be used for conversion. We need to transliterate English or Katakana terms into the same form in order to compute the string similarity. We consider five conversions that transliterate English to Katakana directly, Katakana to English directly, English to Katakana via phoneme, Katakana to English via phoneme, and both English and Katakana to phoneme. The second question is what should be used for the similarity measure at entity matching. To investigate the problem, we choose six methods, which are Overlap Coefficient, Cosine, Jaccard, Jaro-Winkler, Levenshtein, and the similarity of the phoneme probability predicted by RNN. Our results show that 1) matching using phonemes and conversion of Katakana to English works better than other methods, and 2) the similarity of phonemes outperforms other methods while other similarity score is changed depending on data and models. |
| Tasks | Transliteration |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-5809/ |
| https://www.aclweb.org/anthology/W18-5809 | |
| PWC | https://paperswithcode.com/paper/a-comparison-of-entity-matching-methods |
| Repo | |
| Framework | |
The Circumstantial Event Ontology (CEO) and ECB+/CEO: an Ontology and Corpus for Implicit Causal Relations between Events
| Title | The Circumstantial Event Ontology (CEO) and ECB+/CEO: an Ontology and Corpus for Implicit Causal Relations between Events |
| Authors | Roxane Segers, Tommaso Caselli, Piek Vossen |
| Abstract | |
| Tasks | Semantic Role Labeling |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1725/ |
| https://www.aclweb.org/anthology/L18-1725 | |
| PWC | https://paperswithcode.com/paper/the-circumstantial-event-ontology-ceo-and |
| Repo | |
| Framework | |
Spotting Spurious Data with Neural Networks
| Title | Spotting Spurious Data with Neural Networks |
| Authors | Hadi Amiri, Timothy Miller, Guergana Savova |
| Abstract | Automatic identification of spurious instances (those with potentially wrong labels in datasets) can improve the quality of existing language resources, especially when annotations are obtained through crowdsourcing or automatically generated based on coded rankings. In this paper, we present effective approaches inspired by queueing theory and psychology of learning to automatically identify spurious instances in datasets. Our approaches discriminate instances based on their {``}difficulty to learn,{''} determined by a downstream learner. Our methods can be applied to any dataset assuming the existence of a neural network model for the target task of the dataset. Our best approach outperforms competing state-of-the-art baselines and has a MAP of 0.85 and 0.22 in identifying spurious instances in synthetic and carefully-crowdsourced real-world datasets respectively. | |
| Tasks | Object Classification |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/N18-1182/ |
| https://www.aclweb.org/anthology/N18-1182 | |
| PWC | https://paperswithcode.com/paper/spotting-spurious-data-with-neural-networks |
| Repo | |
| Framework | |
Efficient 6-DoF Tracking of Handheld Objects from an Egocentric Viewpoint
| Title | Efficient 6-DoF Tracking of Handheld Objects from an Egocentric Viewpoint |
| Authors | Rohit Pandey, Pavel Pidlypenskyi, Shuoran Yang, Christine Kaeser-Chen |
| Abstract | Virtual and augmented reality technologies have seen significant growth in the past few years. A key component of such systems is the ability to track the pose of head mounted displays and controllers in 3D space. We tackle the problem of efficient 6-DoF tracking of a handheld controller from egocentric camera perspectives. We collected the HMD Controller dataset which consist of over 540,000 stereo image pairs labelled with the full 6-DoF pose of the handheld controller. Our proposed SSD-AF-Stereo3D model achieves a mean average error of 33.5 millimeters in 3D keypoint prediction and is used in conjunction with an IMU sensor on the controller to enable 6-DoF tracking. We also present results on approaches for model based full 6-DoF tracking. All our models operate under the strict constraints of real time mobile CPU inference. |
| Tasks | |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Rohit_Pandey_Efficient_6-DoF_Tracking_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Rohit_Pandey_Efficient_6-DoF_Tracking_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-6-dof-tracking-of-handheld-objects |
| Repo | |
| Framework | |
