Paper Group NANR 243
Variational Convolutional Neural Network Pruning. Multilingual Detection of Hate Speech Against Immigrants and Women in Twitter at SemEval-2019 Task 5: Frequency Analysis Interpolation for Hate in Speech Detection. PRUNING IN TRAINING: LEARNING AND RANKING SPARSE CONNECTIONS IN DEEP CONVOLUTIONAL NETWORKS. Generating a Novel Dataset of Multimodal R …
Variational Convolutional Neural Network Pruning
| Title | Variational Convolutional Neural Network Pruning |
| Authors | Chenglong Zhao, Bingbing Ni, Jian Zhang, Qiwei Zhao, Wenjun Zhang, Qi Tian |
| Abstract | We propose a variational Bayesian scheme for pruning convolutional neural networks in channel level. This idea is motivated by the fact that deterministic value based pruning methods are inherently improper and unstable. In a nutshell, variational technique is introduced to estimate distribution of a newly proposed parameter, called channel saliency, based on this, redundant channels can be removed from model via a simple criterion. The advantages are two-fold: 1) Our method conducts channel pruning without desire of re-training stage, thus improving the computation efficiency. 2) Our method is implemented as a stand-alone module, called variational pruning layer, which can be straightforwardly inserted into off-the-shelf deep learning packages, without any special network design. Extensive experimental results well demonstrate the effectiveness of our method: For CIFAR-10, we perform channel removal on different CNN models up to 74% reduction, which results in significant size reduction and computation saving. For ImageNet, about 40% channels of ResNet-50 are removed without compromising accuracy. |
| Tasks | Network Pruning |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Zhao_Variational_Convolutional_Neural_Network_Pruning_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Zhao_Variational_Convolutional_Neural_Network_Pruning_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/variational-convolutional-neural-network |
| Repo | |
| Framework | |
Multilingual Detection of Hate Speech Against Immigrants and Women in Twitter at SemEval-2019 Task 5: Frequency Analysis Interpolation for Hate in Speech Detection
| Title | Multilingual Detection of Hate Speech Against Immigrants and Women in Twitter at SemEval-2019 Task 5: Frequency Analysis Interpolation for Hate in Speech Detection |
| Authors | {`O}scar Garibo i Orts |
| Abstract | This document describes a text change of representation approach to the task of Multilingual Detection of Hate Speech Against Immigrants and Women in Twitter, as part of SemEval-2019 1 . The task is divided in two sub-tasks. Sub-task A consists in classifying tweets as being hateful or not hateful, whereas sub-task B requires fine tuning the classification by classifying the hateful tweets as being directed to single individuals or generic, if the tweet is aggressive or not. Our approach consists of a change of the space of representation of text into statistical descriptors which characterize the text. In addition, dimensional reduction is performed to 6 characteristics per class in order to make the method suitable for a Big Data environment. Frequency Analysis Interpolation (FAI) is the approach we use to achieve rank 5th in Spanish language and 9th in English language in sub-task B in both cases. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2081/ |
| https://www.aclweb.org/anthology/S19-2081 | |
| PWC | https://paperswithcode.com/paper/multilingual-detection-of-hate-speech-against |
| Repo | |
| Framework | |
PRUNING IN TRAINING: LEARNING AND RANKING SPARSE CONNECTIONS IN DEEP CONVOLUTIONAL NETWORKS
| Title | PRUNING IN TRAINING: LEARNING AND RANKING SPARSE CONNECTIONS IN DEEP CONVOLUTIONAL NETWORKS |
| Authors | Yanwei Fu, Shun Zhang, Donghao Li, Xinwei Sun, Xiangyang Xue, Yuan Yao |
| Abstract | This paper proposes a Pruning in Training (PiT) framework of learning to reduce the parameter size of networks. Different from existing works, our PiT framework employs the sparse penalties to train networks and thus help rank the importance of weights and filters. Our PiT algorithms can directly prune the network without any fine-tuning. The pruned networks can still achieve comparable performance to the original networks. In particular, we introduce the (Group) Lasso-type Penalty (L-P /GL-P), and (Group) Split LBI Penalty (S-P / GS-P) to regularize the networks, and a pruning strategy proposed is used in help prune the network. We conduct the extensive experiments on MNIST, Cifar-10, and miniImageNet. The results validate the efficacy of our proposed methods. Remarkably, on MNIST dataset, our PiT framework can save 17.5% parameter size of LeNet-5, which achieves the 98.47% recognition accuracy. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=r1GgDj0cKX |
| https://openreview.net/pdf?id=r1GgDj0cKX | |
| PWC | https://paperswithcode.com/paper/pruning-in-training-learning-and-ranking |
| Repo | |
| Framework | |
Generating a Novel Dataset of Multimodal Referring Expressions
| Title | Generating a Novel Dataset of Multimodal Referring Expressions |
| Authors | Nikhil Krishnaswamy, James Pustejovsky |
| Abstract | Referring expressions and definite descriptions of objects in space exploit information both about object characteristics and locations. To resolve potential ambiguity, referencing strategies in language can rely on increasingly abstract concepts to distinguish an object in a given location from similar ones elsewhere, yet the description of the intended location may still be imprecise or difficult to interpret. Meanwhile, modalities such as gesture may communicate spatial information such as locations in a more concise manner. In real peer-to-peer communication, humans use language and gesture together to reference entities, with a capacity for mixing and changing modalities where needed. While recent progress in AI and human-computer interaction has created systems where a human can interact with a computer multimodally, computers often lack the capacity to intelligently mix modalities when generating referring expressions. We present a novel dataset of referring expressions combining natural language and gesture, describe its creation and evaluation, and its uses to train computational models for generating and interpreting multimodal referring expressions. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://www.aclweb.org/anthology/W19-0507/ |
| https://www.aclweb.org/anthology/W19-0507 | |
| PWC | https://paperswithcode.com/paper/generating-a-novel-dataset-of-multimodal |
| Repo | |
| Framework | |
Deep Head Pose Estimation Using Synthetic Images and Partial Adversarial Domain Adaption for Continuous Label Spaces
| Title | Deep Head Pose Estimation Using Synthetic Images and Partial Adversarial Domain Adaption for Continuous Label Spaces |
| Authors | Felix Kuhnke, Jorn Ostermann |
| Abstract | Head pose estimation aims at predicting an accurate pose from an image. Current approaches rely on supervised deep learning, which typically requires large amounts of labeled data. Manual or sensor-based annotations of head poses are prone to errors. A solution is to generate synthetic training data by rendering 3D face models. However, the differences (domain gap) between rendered (source-domain) and real-world (target-domain) images can cause low performance. Advances in visual domain adaptation allow reducing the influence of domain differences using adversarial neural networks, which match the feature spaces between domains by enforcing domain-invariant features. While previous work on visual domain adaptation generally assumes discrete and shared label spaces, these assumptions are both invalid for pose estimation tasks. We are the first to present domain adaptation for head pose estimation with a focus on partially shared and continuous label spaces. More precisely, we adapt the predominant weighting approaches to continuous label spaces by applying a weighted resampling of the source domain during training. To evaluate our approach, we revise and extend existing datasets resulting in a new benchmark for visual domain adaption. Our experiments show that our method improves the accuracy of head pose estimation for real-world images despite using only labels from synthetic images. |
| Tasks | Domain Adaptation, Head Pose Estimation, Pose Estimation |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Kuhnke_Deep_Head_Pose_Estimation_Using_Synthetic_Images_and_Partial_Adversarial_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Kuhnke_Deep_Head_Pose_Estimation_Using_Synthetic_Images_and_Partial_Adversarial_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/deep-head-pose-estimation-using-synthetic |
| Repo | |
| Framework | |
Cross-Sentence N-ary Relation Extraction using Lower-Arity Universal Schemas
| Title | Cross-Sentence N-ary Relation Extraction using Lower-Arity Universal Schemas |
| Authors | Kosuke Akimoto, Takuya Hiraoka, Kunihiko Sadamasa, Mathias Niepert |
| Abstract | Most existing relation extraction approaches exclusively target binary relations, and n-ary relation extraction is relatively unexplored. Current state-of-the-art n-ary relation extraction method is based on a supervised learning approach and, therefore, may suffer from the lack of sufficient relation labels. In this paper, we propose a novel approach to cross-sentence n-ary relation extraction based on universal schemas. To alleviate the sparsity problem and to leverage inherent decomposability of n-ary relations, we propose to learn relation representations of lower-arity facts that result from decomposing higher-arity facts. The proposed method computes a score of a new n-ary fact by aggregating scores of its decomposed lower-arity facts. We conduct experiments with datasets for ternary relation extraction and empirically show that our method improves the n-ary relation extraction performance compared to previous methods. |
| Tasks | Relation Extraction |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1645/ |
| https://www.aclweb.org/anthology/D19-1645 | |
| PWC | https://paperswithcode.com/paper/cross-sentence-n-ary-relation-extraction |
| Repo | |
| Framework | |
The binary trio at SemEval-2019 Task 5: Multitarget Hate Speech Detection in Tweets
| Title | The binary trio at SemEval-2019 Task 5: Multitarget Hate Speech Detection in Tweets |
| Authors | Patricia Chiril, Farah Benamara Zitoune, V{'e}ronique Moriceau, Abhishek Kumar |
| Abstract | The massive growth of user-generated web content through blogs, online forums and most notably, social media networks, led to a large spreading of hatred or abusive messages which have to be moderated. This paper proposes a supervised approach to hate speech detection towards immigrants and women in English tweets. Several models have been developed ranging from feature-engineering approaches to neural ones. |
| Tasks | Feature Engineering, Hate Speech Detection |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2087/ |
| https://www.aclweb.org/anthology/S19-2087 | |
| PWC | https://paperswithcode.com/paper/the-binary-trio-at-semeval-2019-task-5 |
| Repo | |
| Framework | |
Testing a Minimalist Grammar Parser on Italian Relative Clause Asymmetries
| Title | Testing a Minimalist Grammar Parser on Italian Relative Clause Asymmetries |
| Authors | Aniello De Santo |
| Abstract | Stabler{'}s (2013) top-down parser for Minimalist grammars has been used to account for off-line processing preferences across a variety of seemingly unrelated phenomena cross-linguistically, via complexity metrics measuring {``}memory burden{''}. This paper extends the empirical coverage of the model by looking at the processing asymmetries of Italian relative clauses, as I discuss the relevance of these constructions in evaluating plausible structure-driven models of processing difficulty. | |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-2911/ |
| https://www.aclweb.org/anthology/W19-2911 | |
| PWC | https://paperswithcode.com/paper/testing-a-minimalist-grammar-parser-on |
| Repo | |
| Framework | |
Learning Linear Transformations for Fast Image and Video Style Transfer
| Title | Learning Linear Transformations for Fast Image and Video Style Transfer |
| Authors | Xueting Li, Sifei Liu, Jan Kautz, Ming-Hsuan Yang |
| Abstract | Given a random pair of images, a universal style transfer method extracts the feel from a reference image to synthesize an output based on the look of a content image. Recent algorithms based on second-order statistics, however, are either computationally expensive or prone to generate artifacts due to the trade-off between image quality and runtime performance. In this work, we present an approach for universal style transfer that learns the transformation matrix in a data-driven fashion. Our algorithm is efficient yet flexible to transfer different levels of styles with the same auto-encoder network. It also produces stable video style transfer results due to the preservation of the content affinity. In addition, we propose a linear propagation module to enable a feed-forward network for photo-realistic style transfer. We demonstrate the effectiveness of our approach on three tasks: artistic style, photo-realistic and video style transfer, with comparisons to state-of-the-art methods. |
| Tasks | Style Transfer, Video Style Transfer |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Li_Learning_Linear_Transformations_for_Fast_Image_and_Video_Style_Transfer_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Li_Learning_Linear_Transformations_for_Fast_Image_and_Video_Style_Transfer_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/learning-linear-transformations-for-fast-1 |
| Repo | |
| Framework | |
Cross Domain Model Compression by Structurally Weight Sharing
| Title | Cross Domain Model Compression by Structurally Weight Sharing |
| Authors | Shangqian Gao, Cheng Deng, Heng Huang |
| Abstract | Regular model compression methods focus on RGB input. While cross domain tasks demand more DNN models, each domain often needs its own model. Consequently, for such tasks, the storage cost, memory footprint and computation cost increase dramatically compared to single RGB input. Moreover, the distinct appearance and special structure in cross domain tasks make it difficult to directly apply regular compression methods on it. In this paper, thus, we propose a new robust cross domain model compression method. Specifically, the proposed method compress cross domain models by structurally weight sharing, which is achieved by regularizing the models with graph embedding at training time. Due to the channel wise weights sharing, the proposed method can reduce computation cost without specially designed algorithm. In the experiments, the proposed method achieves state of the art results on two diverse tasks: action recognition and RGB-D scene recognition. |
| Tasks | Graph Embedding, Model Compression, Scene Recognition, Temporal Action Localization |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Gao_Cross_Domain_Model_Compression_by_Structurally_Weight_Sharing_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Gao_Cross_Domain_Model_Compression_by_Structurally_Weight_Sharing_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/cross-domain-model-compression-by |
| Repo | |
| Framework | |
Team DOMLIN: Exploiting Evidence Enhancement for the FEVER Shared Task
| Title | Team DOMLIN: Exploiting Evidence Enhancement for the FEVER Shared Task |
| Authors | Dominik Stammbach, Guenter Neumann |
| Abstract | This paper contains our system description for the second Fact Extraction and VERification (FEVER) challenge. We propose a two-staged sentence selection strategy to account for examples in the dataset where evidence is not only conditioned on the claim, but also on previously retrieved evidence. We use a publicly available document retrieval module and have fine-tuned BERT checkpoints for sentence se- lection and as the entailment classifier. We report a FEVER score of 68.46{%} on the blind testset. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-6616/ |
| https://www.aclweb.org/anthology/D19-6616 | |
| PWC | https://paperswithcode.com/paper/team-domlin-exploiting-evidence-enhancement |
| Repo | |
| Framework | |
Translationese Features as Indicators of Quality in English-Russian Human Translation
| Title | Translationese Features as Indicators of Quality in English-Russian Human Translation |
| Authors | Maria Kunilovskaya, Ekaterina Lapshinova-Koltunski |
| Abstract | We use a range of morpho-syntactic features inspired by research in register studies (e.g. Biber, 1995; Neumann, 2013) and translation studies (e.g. Ilisei et al., 2010; Zanettin, 2013; Kunilovskaya and Kutuzov, 2018) to reveal the association between translationese and human translation quality. Translationese is understood as any statistical deviations of translations from non-translations (Baker, 1993) and is assumed to affect the fluency of translations, rendering them foreign-sounding and clumsy of wording and structure. This connection is often posited or implied in the studies of translationese or translational varieties (De Sutter et al., 2017), but is rarely directly tested. Our 45 features include frequencies of selected morphological forms and categories, some types of syntactic structures and relations, as well as several overall text measures extracted from Universal Dependencies annotation. The research corpora include English-to-Russian professional and student translations of informational or argumentative newspaper texts and a comparable corpus of non-translated Russian. Our results indicate lack of direct association between translationese and quality in our data: while our features distinguish translations and non-translations with the near perfect accuracy, the performance of the same algorithm on the quality classes barely exceeds the chance level. |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-8706/ |
| https://www.aclweb.org/anthology/W19-8706 | |
| PWC | https://paperswithcode.com/paper/translationese-features-as-indicators-of |
| Repo | |
| Framework | |
Deep Transfer Learning for Few-Shot SAR Image Classification
| Title | Deep Transfer Learning for Few-Shot SAR Image Classification |
| Authors | Mohammad Rostami 1, 2, *OrcID, Soheil Kolouri 1OrcID, Eric Eaton 2 and Kyungnam Kim 1 |
| Abstract | The reemergence of Deep Neural Networks (DNNs) has lead to high-performance supervised learning algorithms for the Electro-Optical (EO) domain classification and detection problems. This success is because generating huge labeled datasets has become possible using modern crowdsourcing labeling platforms such as Amazon’s Mechanical Turk that recruit ordinary people to label data. Unlike the EO domain, labeling the Synthetic Aperture Radar (SAR) domain data can be much more challenging, and for various reasons, using crowdsourcing platforms is not feasible for labeling the SAR domain data. As a result, training deep networks using supervised learning is more challenging in the SAR domain. In the paper, we present a new framework to train a deep neural network for classifying Synthetic Aperture Radar (SAR) images by eliminating the need for a huge labeled dataset. Our idea is based on transferring knowledge from a related EO domain problem, where labeled data are easy to obtain. We transfer knowledge from the EO domain through learning a shared invariant cross-domain embedding space that is also discriminative for classification. To this end, we train two deep encoders that are coupled through their last year to map data points from the EO and the SAR domains to the shared embedding space such that the distance between the distributions of the two domains is minimized in the latent embedding space. We use the Sliced Wasserstein Distance (SWD) to measure and minimize the distance between these two distributions and use a limited number of SAR label data points to match the distributions class-conditionally. As a result of this training procedure, a classifier trained from the embedding space to the label space using mostly the EO data would generalize well on the SAR domain. We provide a theoretical analysis to demonstrate why our approach is effective and validate our algorithm on the problem of ship classification in the SAR domain by comparing against several other competing learning approaches. |
| Tasks | Image Classification, Transfer Learning |
| Published | 2019-04-30 |
| URL | https://www.mdpi.com/2072-4292/11/11/1374 |
| https://www.mdpi.com/2072-4292/11/11/1374 | |
| PWC | https://paperswithcode.com/paper/deep-transfer-learning-for-few-shot-sar-image |
| Repo | |
| Framework | |
Constrained deep neural network architecture search for IoT devices accounting for hardware calibration
| Title | Constrained deep neural network architecture search for IoT devices accounting for hardware calibration |
| Authors | Florian Scheidegger, Luca Benini, Costas Bekas, A. Cristiano I. Malossi |
| Abstract | Deep neural networks achieve outstanding results for challenging image classification tasks. However, the design of network topologies is a complex task, and the research community is conducting ongoing efforts to discover top-accuracy topologies, either manually or by employing expensive architecture searches. We propose a unique narrow-space architecture search that focuses on delivering low-cost and rapidly executing networks that respect strict memory and time requirements typical of Internet-of-Things (IoT) near-sensor computing platforms. Our approach provides solutions with classification latencies below 10~ms running on a low-cost device with 1~GB RAM and a peak performance of 5.6~GFLOPS. The narrow-space search of floating-point models improves the accuracy on CIFAR10 of an established IoT model from 70.64% to 74.87% within the same memory constraints. We further improve the accuracy to 82.07% by including 16-bit half types and obtain the highest accuracy of 83.45% by extending the search with model-optimized IEEE 754 reduced types. To the best of our knowledge, this is the first empirical demonstration of more than 3000 trained models that run with reduced precision and push the Pareto optimal front by a wide margin. Within a given memory constraint, accuracy is improved by more than 7% points for half and more than 1% points for the best individual model format. |
| Tasks | Calibration, Image Classification |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/8838-constrained-deep-neural-network-architecture-search-for-iot-devices-accounting-for-hardware-calibration |
| http://papers.nips.cc/paper/8838-constrained-deep-neural-network-architecture-search-for-iot-devices-accounting-for-hardware-calibration.pdf | |
| PWC | https://paperswithcode.com/paper/constrained-deep-neural-network-architecture-1 |
| Repo | |
| Framework | |
Using Machine Learning and Deep Learning Methods to Find Mentions of Adverse Drug Reactions in Social Media
| Title | Using Machine Learning and Deep Learning Methods to Find Mentions of Adverse Drug Reactions in Social Media |
| Authors | Pilar L{'o}pez {'U}beda, Manuel Carlos D{'\i}az Galiano, Maite Martin, L. Alfonso Urena Lopez |
| Abstract | Over time the use of social networks is becoming very popular platforms for sharing health related information. Social Media Mining for Health Applications (SMM4H) provides tasks such as those described in this document to help manage information in the health domain. This document shows the first participation of the SINAI group. We study approaches based on machine learning and deep learning to extract adverse drug reaction mentions from Twitter. The results obtained in the tasks are encouraging, we are close to the average of all participants and even above in some cases. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-3216/ |
| https://www.aclweb.org/anthology/W19-3216 | |
| PWC | https://paperswithcode.com/paper/using-machine-learning-and-deep-learning |
| Repo | |
| Framework | |
