Paper Group NANR 203
Deep Ensemble Bayesian Active Learning : Adressing the Mode Collapse issue in Monte Carlo dropout via Ensembles. QC-GO Submission for MADAR Shared Task: Arabic Fine-Grained Dialect Identification. Non-Local Intrinsic Decomposition With Near-Infrared Priors. Dynamic Early Terminating of Multiply Accumulate Operations for Saving Computation Cost in C …
Deep Ensemble Bayesian Active Learning : Adressing the Mode Collapse issue in Monte Carlo dropout via Ensembles
| Title | Deep Ensemble Bayesian Active Learning : Adressing the Mode Collapse issue in Monte Carlo dropout via Ensembles |
| Authors | Remus Pop, Patric Fulop |
| Abstract | In image classification tasks, the ability of deep convolutional neural networks (CNNs) to deal with complex image data has proved to be unrivalled. Deep CNNs, however, require large amounts of labeled training data to reach their full potential. In specialised domains such as healthcare, labeled data can be difficult and expensive to obtain. One way to alleviate this problem is to rely on active learning, a learning technique that aims to reduce the amount of labelled data needed for a specific task while still delivering satisfactory performance. We propose a new active learning strategy designed for deep neural networks. This method improves upon the current state-of-the-art deep Bayesian active learning method, which suffers from the mode collapse problem. We correct for this deficiency by making use of the expressive power and statistical properties of model ensembles. Our proposed method manages to capture superior data uncertainty, which translates into improved classification performance. We demonstrate empirically that our ensemble method yields faster convergence of CNNs trained on the MNIST and CIFAR-10 datasets. |
| Tasks | Active Learning, Image Classification |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=Byx93sC9tm |
| https://openreview.net/pdf?id=Byx93sC9tm | |
| PWC | https://paperswithcode.com/paper/deep-ensemble-bayesian-active-learning |
| Repo | |
| Framework | |
QC-GO Submission for MADAR Shared Task: Arabic Fine-Grained Dialect Identification
| Title | QC-GO Submission for MADAR Shared Task: Arabic Fine-Grained Dialect Identification |
| Authors | Younes Samih, Hamdy Mubarak, Ahmed Abdelali, Mohammed Attia, Mohamed Eldesouki, Kareem Darwish |
| Abstract | This paper describes the QC-GO team submission to the MADAR Shared Task Subtask 1 (travel domain dialect identification) and Subtask 2 (Twitter user location identification). In our participation in both subtasks, we explored a number of approaches and system combinations to obtain the best performance for both tasks. These include deep neural nets and heuristics. Since individual approaches suffer from various shortcomings, the combination of different approaches was able to fill some of these gaps. Our system achieves F1-Scores of 66.1{%} and 67.0{%} on the development sets for Subtasks 1 and 2 respectively. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4639/ |
| https://www.aclweb.org/anthology/W19-4639 | |
| PWC | https://paperswithcode.com/paper/qc-go-submission-for-madar-shared-task-arabic |
| Repo | |
| Framework | |
Non-Local Intrinsic Decomposition With Near-Infrared Priors
| Title | Non-Local Intrinsic Decomposition With Near-Infrared Priors |
| Authors | Ziang Cheng, Yinqiang Zheng, Shaodi You, Imari Sato |
| Abstract | Intrinsic image decomposition is a highly under-constrained problem that has been extensively studied by computer vision researchers. Previous methods impose additional constraints by exploiting either empirical or data-driven priors. In this paper, we revisit intrinsic image decomposition with the aid of near-infrared (NIR) imagery. We show that NIR band is considerably less sensitive to textures and can be exploited to reduce ambiguity caused by reflectance variation, promoting a simple yet powerful prior for shading smoothness. With this observation, we formulate intrinsic decomposition as an energy minimisation problem. Unlike existing methods, our energy formulation decouples reflectance and shading estimation, into a convex local shading component based on NIR-RGB image pair, and a reflectance component that encourages reflectance homogeneity both locally and globally. We further show the minimisation process can be approached by a series of multi-dimensional kernel convolutions, each within linear time complexity. To validate the proposed algorithm, a NIR-RGB dataset is captured over real-world objects, where our NIR-assisted approach demonstrates clear superiority over RGB methods. |
| Tasks | Intrinsic Image Decomposition |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Cheng_Non-Local_Intrinsic_Decomposition_With_Near-Infrared_Priors_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Cheng_Non-Local_Intrinsic_Decomposition_With_Near-Infrared_Priors_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/non-local-intrinsic-decomposition-with-near |
| Repo | |
| Framework | |
Dynamic Early Terminating of Multiply Accumulate Operations for Saving Computation Cost in Convolutional Neural Networks
| Title | Dynamic Early Terminating of Multiply Accumulate Operations for Saving Computation Cost in Convolutional Neural Networks |
| Authors | Yu-Yi Su, Yung-Chih Chen, Xiang-Xiu Wu, Shih-Chieh Chang |
| Abstract | Deep learning has been attracting enormous attention from academia as well as industry due to its great success in many artificial intelligence applications. As more applications are developed, the need for implementing a complex neural network model on an energy-limited edge device becomes more critical. To this end, this paper proposes a new optimization method to reduce the computation efforts of convolutional neural networks. The method takes advantage of the fact that some convolutional operations are actually wasteful since their outputs are pruned by the following activation or pooling layers. Basically, a convolutional filter conducts a series of multiply-accumulate (MAC) operations. We propose to set a checkpoint in the MAC process to determine whether a filter could terminate early based on the intermediate result. Furthermore, a fine-tuning process is conducted to recover the accuracy drop due to the applied checkpoints. The experimental results show that the proposed method can save approximately 50% MAC operations with less than 1% accuracy drop for CIFAR-10 example model and Network in Network on the CIFAR-10 and CIFAR-100 datasets. Additionally, compared with the state-of- the-art method, the proposed method is more effective on the CIFAR-10 dataset and is competitive on the CIFAR-100 dataset. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=SJe8DsR9tm |
| https://openreview.net/pdf?id=SJe8DsR9tm | |
| PWC | https://paperswithcode.com/paper/dynamic-early-terminating-of-multiply |
| Repo | |
| Framework | |
GLoSH: Global-Local Spherical Harmonics for Intrinsic Image Decomposition
| Title | GLoSH: Global-Local Spherical Harmonics for Intrinsic Image Decomposition |
| Authors | Hao Zhou, Xiang Yu, David W. Jacobs |
| Abstract | Traditional intrinsic image decomposition focuses on decomposing images into reflectance and shading, leaving surfaces normals and lighting entangled in shading. In this work, we propose a Global-Local Spherical Harmonics (GLoSH) lighting model to improve the lighting component, and jointly predict reflectance and surface normals. The global SH models the holistic lighting while local SH account for the spatial variation of lighting. Also, a novel non-negative lighting constraint is proposed to encourage the estimated SH to be physically meaningful. To seamlessly reflect the GLoSH model, we design a coarse-to-fine network structure. The coarse network predicts global SH, reflectance and normals, and the fine network predicts their local residuals. Lacking labels for reflectance and lighting, we apply synthetic data for model pre-training and fine-tune the model with real data in a self-supervised way. Compared to the state-of-the-art methods only targeting normals or reflectance and shading, our method recovers all components and achieves consistently better results on three real datasets, IIW, SAW and NYUv2. |
| Tasks | Intrinsic Image Decomposition |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Zhou_GLoSH_Global-Local_Spherical_Harmonics_for_Intrinsic_Image_Decomposition_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Zhou_GLoSH_Global-Local_Spherical_Harmonics_for_Intrinsic_Image_Decomposition_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/glosh-global-local-spherical-harmonics-for |
| Repo | |
| Framework | |
Multilingual Whispers: Generating Paraphrases with Translation
| Title | Multilingual Whispers: Generating Paraphrases with Translation |
| Authors | Christian Federmann, Oussama Elachqar, Chris Quirk |
| Abstract | Naturally occurring paraphrase data, such as multiple news stories about the same event, is a useful but rare resource. This paper compares translation-based paraphrase gathering using human, automatic, or hybrid techniques to monolingual paraphrasing by experts and non-experts. We gather translations, paraphrases, and empirical human quality assessments of these approaches. Neural machine translation techniques, especially when pivoting through related languages, provide a relatively robust source of paraphrases with diversity comparable to expert human paraphrases. Surprisingly, human translators do not reliably outperform neural systems. The resulting data release will not only be a useful test set, but will also allow additional explorations in translation and paraphrase quality assessments and relationships. |
| Tasks | Machine Translation |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5503/ |
| https://www.aclweb.org/anthology/D19-5503 | |
| PWC | https://paperswithcode.com/paper/multilingual-whispers-generating-paraphrases |
| Repo | |
| Framework | |
Seeded self-play for language learning
| Title | Seeded self-play for language learning |
| Authors | Abhinav Gupta, Ryan Lowe, Jakob Foerster, Douwe Kiela, Joelle Pineau |
| Abstract | How can we teach artificial agents to use human language flexibly to solve problems in real-world environments? We have an example of this in nature: human babies eventually learn to use human language to solve problems, and they are taught with an adult human-in-the-loop. Unfortunately, current machine learning methods (e.g. from deep reinforcement learning) are too data inefficient to learn language in this way. An outstanding goal is finding an algorithm with a suitable {`}language learning prior{'} that allows it to learn human language, while minimizing the number of on-policy human interactions. In this paper, we propose to learn such a prior in simulation using an approach we call, Learning to Learn to Communicate (L2C). Specifically, in L2C we train a meta-learning agent in simulation to interact with populations of pre-trained agents, each with their own distinct communication protocol. Once the meta-learning agent is able to quickly adapt to each population of agents, it can be deployed in new populations, including populations speaking human language. Our key insight is that such populations can be obtained via self-play, after pre-training agents with imitation learning on a small amount of off-policy human language data. We call this latter technique Seeded Self-Play (S2P). Our preliminary experiments show that agents trained with L2C and S2P need fewer on-policy samples to learn a compositional language in a Lewis signaling game. | |
| Tasks | Imitation Learning, Meta-Learning |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-6409/ |
| https://www.aclweb.org/anthology/D19-6409 | |
| PWC | https://paperswithcode.com/paper/seeded-self-play-for-language-learning |
| Repo | |
| Framework | |
Fact Checking or Psycholinguistics: How to Distinguish Fake and True Claims?
| Title | Fact Checking or Psycholinguistics: How to Distinguish Fake and True Claims? |
| Authors | Aleks Wawer, er, Grzegorz Wojdyga, Justyna Sarzy{'n}ska-Wawer |
| Abstract | The goal of our paper is to compare psycholinguistic text features with fact checking approaches to distinguish lies from true statements. We examine both methods using data from a large ongoing study on deception and deception detection covering a mixture of factual and opinionated topics that polarize public opinion. We conclude that fact checking approaches based on Wikipedia are too limited for this task, as only a few percent of sentences from our study has enough evidence to become supported or refuted. Psycholinguistic features turn out to outperform both fact checking and human baselines, but the accuracy is not high. Overall, it appears that deception detection applicable to less-than-obvious topics is a difficult task and a problem to be solved. |
| Tasks | Deception Detection |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-6602/ |
| https://www.aclweb.org/anthology/D19-6602 | |
| PWC | https://paperswithcode.com/paper/fact-checking-or-psycholinguistics-how-to |
| Repo | |
| Framework | |
Fast-deepKCF Without Boundary Effect
| Title | Fast-deepKCF Without Boundary Effect |
| Authors | Linyu Zheng, Ming Tang, Yingying Chen, Jinqiao Wang, Hanqing Lu |
| Abstract | In recent years, correlation filter based trackers (CF trackers) have received much attention because of their top performance. Most CF trackers, however, suffer from low frame-per-second (fps) in pursuit of higher localization accuracy by relaxing the boundary effect or exploiting the high-dimensional deep features. In order to achieve real-time tracking speed while maintaining high localization accuracy, in this paper, we propose a novel CF tracker, fdKCF*, which casts aside the popular acceleration tool, i.e., fast Fourier transform, employed by all existing CF trackers, and exploits the inherent high-overlap among real (i.e., noncyclic) and dense samples to efficiently construct the kernel matrix. Our fdKCF* enjoys the following three advantages. (i) It is efficiently trained in kernel space and spatial domain without the boundary effect. (ii) Its fps is almost independent of the number of feature channels. Therefore, it is almost real-time, i.e., 24 fps on OTB-2015, even though the high-dimensional deep features are employed. (iii) Its localization accuracy is state-of-the-art. Extensive experiments on four public benchmarks, OTB-2013, OTB-2015, VOT2016, and VOT2017, show that the proposed fdKCF* achieves the state-of-the-art localization performance with remarkably faster speed than C-COT and ECO. |
| Tasks | |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Zheng_Fast-deepKCF_Without_Boundary_Effect_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Zheng_Fast-deepKCF_Without_Boundary_Effect_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/fast-deepkcf-without-boundary-effect |
| Repo | |
| Framework | |
Training Data Augmentation for Context-Sensitive Neural Lemmatizer Using Inflection Tables and Raw Text
| Title | Training Data Augmentation for Context-Sensitive Neural Lemmatizer Using Inflection Tables and Raw Text |
| Authors | Toms Bergmanis, Sharon Goldwater |
| Abstract | Lemmatization aims to reduce the sparse data problem by relating the inflected forms of a word to its dictionary form. Using context can help, both for unseen and ambiguous words. Yet most context-sensitive approaches require full lemma-annotated sentences for training, which may be scarce or unavailable in low-resource languages. In addition (as shown here), in a low-resource setting, a lemmatizer can learn more from n labeled examples of distinct words (types) than from n (contiguous) labeled tokens, since the latter contain far fewer distinct types. To combine the efficiency of type-based learning with the benefits of context, we propose a way to train a context-sensitive lemmatizer with little or no labeled corpus data, using inflection tables from the UniMorph project and raw text examples from Wikipedia that provide sentence contexts for the unambiguous UniMorph examples. Despite these being unambiguous examples, the model successfully generalizes from them, leading to improved results (both overall, and especially on unseen words) in comparison to a baseline that does not use context. |
| Tasks | Data Augmentation, Lemmatization |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-1418/ |
| https://www.aclweb.org/anthology/N19-1418 | |
| PWC | https://paperswithcode.com/paper/training-data-augmentation-for-context |
| Repo | |
| Framework | |
Understanding the Shades of Sexism in Popular TV Series
| Title | Understanding the Shades of Sexism in Popular TV Series |
| Authors | Nayeon Lee, Yejin Bang, Jamin Shin, Pascale Fung |
| Abstract | [Multiple-submission] In the midst of a generation widely exposed to and influenced by media entertainment, the NLP research community has shown relatively little attention on the sexist comments in popular TV series. To understand sexism in TV series, we propose a way of collecting distant supervision dataset using Character Persona information with the psychological theories on sexism. We assume that sexist characters from TV shows are more prone to making sexist comments when talking about women, and show that this hypothesis is valid through experiment. Finally, we conduct an interesting analysis on popular TV show characters and successfully identify different shades of sexism that is often overlooked. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/papers/W/W19/W19-3638/ |
| https://www.aclweb.org/anthology/W19-3638 | |
| PWC | https://paperswithcode.com/paper/understanding-the-shades-of-sexism-in-popular |
| Repo | |
| Framework | |
P-MVSNet: Learning Patch-Wise Matching Confidence Aggregation for Multi-View Stereo
| Title | P-MVSNet: Learning Patch-Wise Matching Confidence Aggregation for Multi-View Stereo |
| Authors | Keyang Luo, Tao Guan, Lili Ju, Haipeng Huang, Yawei Luo |
| Abstract | Learning-based methods are demonstrating their strong competitiveness in estimating depth for multi-view stereo reconstruction in recent years. Among them the approaches that generate cost volumes based on the plane-sweeping algorithm and then use them for feature matching have shown to be very prominent recently. The plane-sweep volumes are essentially anisotropic in depth and spatial directions, but they are often approximated by isotropic cost volumes in those methods, which could be detrimental. In this paper, we propose a new end-to-end deep learning network of P-MVSNet for multi-view stereo based on isotropic and anisotropic 3D convolutions. Our P-MVSNet consists of two core modules: a patch-wise aggregation module learns to aggregate the pixel-wise correspondence information of extracted features to generate a matching confidence volume, from which a hybrid 3D U-Net then infers a depth probability distribution and predicts the depth maps. We perform extensive experiments on the DTU and Tanks & Temples benchmark datasets, and the results show that the proposed P-MVSNet achieves the state-of-the-art performance over many existing methods on multi-view stereo. |
| Tasks | |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Luo_P-MVSNet_Learning_Patch-Wise_Matching_Confidence_Aggregation_for_Multi-View_Stereo_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Luo_P-MVSNet_Learning_Patch-Wise_Matching_Confidence_Aggregation_for_Multi-View_Stereo_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/p-mvsnet-learning-patch-wise-matching |
| Repo | |
| Framework | |
Not All Areas Are Equal: Transfer Learning for Semantic Segmentation via Hierarchical Region Selection
| Title | Not All Areas Are Equal: Transfer Learning for Semantic Segmentation via Hierarchical Region Selection |
| Authors | Ruoqi Sun, Xinge Zhu, Chongruo Wu, Chen Huang, Jianping Shi, Lizhuang Ma |
| Abstract | The success of deep neural networks for semantic segmentation heavily relies on large-scale and well-labeled datasets, which are hard to collect in practice. Synthetic data offers an alternative to obtain ground-truth labels for free. However, models directly trained on synthetic data often struggle to generalize to real images. In this paper, we consider transfer learning for semantic segmentation that aims to mitigate the gap between abundant synthetic data (source domain) and limited real data (target domain). Unlike previous approaches that either learn mappings to target domain or finetune on target images, our proposed method jointly learn from real images and selectively from realistic pixels in synthetic images to adapt to the target domain. Our key idea is to have weighting networks to score how similar the synthetic pixels are to real ones, and learn such weighting at pixel-, region- and image-levels. We jointly learn these hierarchical weighting networks and segmentation network in an end-to-end manner. Extensive experiments demonstrate that our proposed approach significantly outperforms other existing baselines, and is applicable to scenarios with extremely limited real images. |
| Tasks | Semantic Segmentation, Transfer Learning |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Sun_Not_All_Areas_Are_Equal_Transfer_Learning_for_Semantic_Segmentation_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Sun_Not_All_Areas_Are_Equal_Transfer_Learning_for_Semantic_Segmentation_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/not-all-areas-are-equal-transfer-learning-for |
| Repo | |
| Framework | |
Weakly Supervised Multilingual Causality Extraction from Wikipedia
| Title | Weakly Supervised Multilingual Causality Extraction from Wikipedia |
| Authors | Chikara Hashimoto |
| Abstract | We present a method for extracting causality knowledge from Wikipedia, such as Protectionism -{\textgreater} Trade war, where the cause and effect entities correspond to Wikipedia articles. Such causality knowledge is easy to verify by reading corresponding Wikipedia articles, to translate to multiple languages through Wikidata, and to connect to knowledge bases derived from Wikipedia. Our method exploits Wikipedia article sections that describe causality and the redundancy stemming from the multilinguality of Wikipedia. Experiments showed that our method achieved precision and recall above 98{%} and 64{%}, respectively. In particular, it could extract causalities whose cause and effect were written distantly in a Wikipedia article. We have released the code and data for further research. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1296/ |
| https://www.aclweb.org/anthology/D19-1296 | |
| PWC | https://paperswithcode.com/paper/weakly-supervised-multilingual-causality |
| Repo | |
| Framework | |
Graph Spectral Regularization For Neural Network Interpretability
| Title | Graph Spectral Regularization For Neural Network Interpretability |
| Authors | Alexander Tong, David van Dijk, Jay Stanley, Guy Wolf, Smita Krishnaswamy |
| Abstract | Deep neural networks can learn meaningful representations of data. However, these representations are hard to interpret. For example, visualizing a latent layer is generally only possible for at most three dimensions. Neural networks are able to learn and benefit from much higher dimensional representations but these are not visually interpretable because nodes have arbitrary ordering within a layer. Here, we utilize the ability of the human observer to identify patterns in structured representations to visualize higher dimensions. To do so, we propose a class of regularizations we call \textit{Graph Spectral Regularizations} that impose graph-structure on latent layers. This is achieved by treating activations as signals on a predefined graph and constraining those activations using graph filters, such as low pass and wavelet-like filters. This framework allows for any kind of graph as well as filter to achieve a wide range of structured regularizations depending on the inference needs of the data. First, we show a synthetic example that the graph-structured layer can reveal topological features of the data. Next, we show that a smoothing regularization can impose semantically consistent ordering of nodes when applied to capsule nets. Further, we show that the graph-structured layer, using wavelet-like spatially localized filters, can form localized receptive fields for improved image and biomedical data interpretation. In other words, the mapping between latent layer, neurons and the output space becomes clear due to the localization of the activations. Finally, we show that when structured as a grid, the representations create coherent images that allow for image-processing techniques such as convolutions. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=B1lnjo05Km |
| https://openreview.net/pdf?id=B1lnjo05Km | |
| PWC | https://paperswithcode.com/paper/graph-spectral-regularization-for-neural-1 |
| Repo | |
| Framework | |
