Paper Group NANR 190
Deep Defocus Map Estimation Using Domain Adaptation. PIE: Pseudo-Invertible Encoder. Whom to Learn From? Graph- vs. Text-based Word Embeddings. VizWiz-Priv: A Dataset for Recognizing the Presence and Purpose of Private Visual Information in Images Taken by Blind People. Graph Classification with Geometric Scattering. A Priori Estimates of the Gener …
Deep Defocus Map Estimation Using Domain Adaptation
| Title | Deep Defocus Map Estimation Using Domain Adaptation |
| Authors | Junyong Lee, Sungkil Lee, Sunghyun Cho, Seungyong Lee |
| Abstract | In this paper, we propose the first end-to-end convolutional neural network (CNN) architecture, Defocus Map Estimation Network (DMENet), for spatially varying defocus map estimation. To train the network, we produce a novel depth-of-field (DOF) dataset, SYNDOF, where each image is synthetically blurred with a ground-truth depth map. Due to the synthetic nature of SYNDOF, the feature characteristics of images in SYNDOF can differ from those of real defocused photos. To address this gap, we use domain adaptation that transfers the features of real defocused photos into those of synthetically blurred ones. Our DMENet consists of four subnetworks: blur estimation, domain adaptation, content preservation, and sharpness calibration networks. The subnetworks are connected to each other and jointly trained with their corresponding supervisions in an end-to-end manner. Our method is evaluated on publicly available blur detection and blur estimation datasets and the results show the state-of-the-art performance.In this paper, we propose the first end-to-end convolutional neural network (CNN) architecture, Defocus Map Estimation Network (DMENet), for spatially varying defocus map estimation. To train the network, we produce a novel depth-of-field (DOF) dataset, SYNDOF, where each image is synthetically blurred with a ground-truth depth map. Due to the synthetic nature of SYNDOF, the feature characteristics of images in SYNDOF can differ from those of real defocused photos. To address this gap, we use domain adaptation that transfers the features of real defocused photos into those of synthetically blurred ones. Our DMENet consists of four subnetworks: blur estimation, domain adaptation, content preservation, and sharpness calibration networks. The subnetworks are connected to each other and jointly trained with their corresponding supervisions in an end-to-end manner. Our method is evaluated on publicly available blur detection and blur estimation datasets and the results show the state-of-the-art performance. |
| Tasks | Calibration, Domain Adaptation |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Lee_Deep_Defocus_Map_Estimation_Using_Domain_Adaptation_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Lee_Deep_Defocus_Map_Estimation_Using_Domain_Adaptation_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/deep-defocus-map-estimation-using-domain |
| Repo | |
| Framework | |
PIE: Pseudo-Invertible Encoder
| Title | PIE: Pseudo-Invertible Encoder |
| Authors | Jan Jetze Beitler, Ivan Sosnovik, Arnold Smeulders |
| Abstract | We consider the problem of information compression from high dimensional data. Where many studies consider the problem of compression by non-invertible trans- formations, we emphasize the importance of invertible compression. We introduce new class of likelihood-based auto encoders with pseudo bijective architecture, which we call Pseudo Invertible Encoders. We provide the theoretical explanation of their principles. We evaluate Gaussian Pseudo Invertible Encoder on MNIST, where our model outperform WAE and VAE in sharpness of the generated images. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=SkgiX2Aqtm |
| https://openreview.net/pdf?id=SkgiX2Aqtm | |
| PWC | https://paperswithcode.com/paper/pie-pseudo-invertible-encoder |
| Repo | |
| Framework | |
Whom to Learn From? Graph- vs. Text-based Word Embeddings
| Title | Whom to Learn From? Graph- vs. Text-based Word Embeddings |
| Authors | Ma{\l}gorzata Salawa, Ant{'o}nio Branco, Ruben Branco, Jo{~a}o Ant{'o}nio Rodrigues, Chakaveh Saedi |
| Abstract | Vectorial representations of meaning can be supported by empirical data from diverse sources and obtained with diverse embedding approaches. This paper aims at screening this experimental space and reports on an assessment of word embeddings supported (i) by data in raw texts vs. in lexical graphs, (ii) by lexical information encoded in association- vs. inference-based graphs, and obtained (iii) by edge reconstruction- vs. matrix factorisation vs. random walk-based graph embedding methods. The results observed with these experiments indicate that the best solutions with graph-based word embeddings are very competitive, consistently outperforming mainstream text-based ones. |
| Tasks | Graph Embedding, Word Embeddings |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1120/ |
| https://www.aclweb.org/anthology/R19-1120 | |
| PWC | https://paperswithcode.com/paper/whom-to-learn-from-graph-vs-text-based-word |
| Repo | |
| Framework | |
VizWiz-Priv: A Dataset for Recognizing the Presence and Purpose of Private Visual Information in Images Taken by Blind People
| Title | VizWiz-Priv: A Dataset for Recognizing the Presence and Purpose of Private Visual Information in Images Taken by Blind People |
| Authors | Danna Gurari, Qing Li, Chi Lin, Yinan Zhao, Anhong Guo, Abigale Stangl, Jeffrey P. Bigham |
| Abstract | We introduce the first visual privacy dataset originating from people who are blind in order to better understand their privacy disclosures and to encourage the development of algorithms that can assist in preventing their unintended disclosures. It includes 8,862 regions showing private content across 5,537 images taken by blind people. Of these, 1,403 are paired with questions and 62% of those directly ask about the private content. Experiments demonstrate the utility of this data for predicting whether an image shows private information and whether a question asks about the private content in an image. The dataset is publicly-shared at http://vizwiz.org/data/. |
| Tasks | |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Gurari_VizWiz-Priv_A_Dataset_for_Recognizing_the_Presence_and_Purpose_of_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Gurari_VizWiz-Priv_A_Dataset_for_Recognizing_the_Presence_and_Purpose_of_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/vizwiz-priv-a-dataset-for-recognizing-the |
| Repo | |
| Framework | |
Graph Classification with Geometric Scattering
| Title | Graph Classification with Geometric Scattering |
| Authors | Feng Gao, Guy Wolf, Matthew Hirn |
| Abstract | One of the most notable contributions of deep learning is the application of convolutional neural networks (ConvNets) to structured signal classification, and in particular image classification. Beyond their impressive performances in supervised learning, the structure of such networks inspired the development of deep filter banks referred to as scattering transforms. These transforms apply a cascade of wavelet transforms and complex modulus operators to extract features that are invariant to group operations and stable to deformations. Furthermore, ConvNets inspired recent advances in geometric deep learning, which aim to generalize these networks to graph data by applying notions from graph signal processing to learn deep graph filter cascades. We further advance these lines of research by proposing a geometric scattering transform using graph wavelets defined in terms of random walks on the graph. We demonstrate the utility of features extracted with this designed deep filter bank in graph classification of biochemistry and social network data (incl. state of the art results in the latter case), and in data exploration, where they enable inference of EC exchange preferences in enzyme evolution. |
| Tasks | Graph Classification, Image Classification |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=SygK6sA5tX |
| https://openreview.net/pdf?id=SygK6sA5tX | |
| PWC | https://paperswithcode.com/paper/graph-classification-with-geometric |
| Repo | |
| Framework | |
A Priori Estimates of the Generalization Error for Two-layer Neural Networks
| Title | A Priori Estimates of the Generalization Error for Two-layer Neural Networks |
| Authors | Lei Wu, Chao Ma, Weinan E |
| Abstract | New estimates for the generalization error are established for a nonlinear regression problem using a two-layer neural network model. These new estimates are a priori in nature in the sense that the bounds depend only on some norms of the underlying functions to be fitted, not the parameters in the model. In contrast, most existing results for neural networks are a posteriori in nature in the sense that the bounds depend on some norms of the model parameters. The error rates are comparable to that of the Monte Carlo method in terms of the size of the dataset. Moreover, these bounds are equally effective in the over-parametrized regime when the network size is much larger than the size of the dataset. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=Sklqvo0qt7 |
| https://openreview.net/pdf?id=Sklqvo0qt7 | |
| PWC | https://paperswithcode.com/paper/a-priori-estimates-of-the-generalization |
| Repo | |
| Framework | |
ConSSED at SemEval-2019 Task 3: Configurable Semantic and Sentiment Emotion Detector
| Title | ConSSED at SemEval-2019 Task 3: Configurable Semantic and Sentiment Emotion Detector |
| Authors | Rafa{\l} Po{'s}wiata |
| Abstract | This paper describes our system participating in the SemEval-2019 Task 3: EmoContext: Contextual Emotion Detection in Text. The goal was to for a given textual dialogue, i.e. a user utterance along with two turns of context, identify the emotion of user utterance as one of the emotion classes: Happy, Sad, Angry or Others. Our system: ConSSED is a configurable combination of semantic and sentiment neural models. The official task submission achieved a micro-average F1 score of 75.31 which placed us 16th out of 165 participating systems. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2027/ |
| https://www.aclweb.org/anthology/S19-2027 | |
| PWC | https://paperswithcode.com/paper/conssed-at-semeval-2019-task-3-configurable |
| Repo | |
| Framework | |
M2FPA: A Multi-Yaw Multi-Pitch High-Quality Dataset and Benchmark for Facial Pose Analysis
| Title | M2FPA: A Multi-Yaw Multi-Pitch High-Quality Dataset and Benchmark for Facial Pose Analysis |
| Authors | Peipei Li, Xiang Wu, Yibo Hu, Ran He, Zhenan Sun |
| Abstract | Facial images in surveillance or mobile scenarios often have large view-point variations in terms of pitch and yaw angles. These jointly occurred angle variations make face recognition challenging. Current public face databases mainly consider the case of yaw variations. In this paper, a new large-scale Multi-yaw Multi-pitch high-quality database is proposed for Facial Pose Analysis (M2FPA), including face frontalization, face rotation, facial pose estimation and pose-invariant face recognition. It contains 397,544 images of 229 subjects with yaw, pitch, attribute, illumination and accessory. M2FPA is the most comprehensive multi-view face database for facial pose analysis. Further, we provide an effective benchmark for face frontalization and pose-invariant face recognition on M2FPA with several state-of-the-art methods, including DR-GAN, TP-GAN and CAPG-GAN. We believe that the new database and benchmark can significantly push forward the advance of facial pose analysis in real-world applications. Moreover, a simple yet effective parsing guided discriminator is introduced to capture the local consistency during GAN optimization. Extensive quantitative and qualitative results on M2FPA and Multi-PIE demonstrate the superiority of our face frontalization method. Baseline results for both face synthesis and face recognition from state-of-the-art methods demonstrate the challenge offered by this new database. |
| Tasks | Face Generation, Face Recognition, Pose Estimation, Robust Face Recognition |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Li_M2FPA_A_Multi-Yaw_Multi-Pitch_High-Quality_Dataset_and_Benchmark_for_Facial_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Li_M2FPA_A_Multi-Yaw_Multi-Pitch_High-Quality_Dataset_and_Benchmark_for_Facial_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/m2fpa-a-multi-yaw-multi-pitch-high-quality-1 |
| Repo | |
| Framework | |
Electronical resources for Livonian
| Title | Electronical resources for Livonian |
| Authors | Valts Ern{\v{s}}treits |
| Abstract | |
| Tasks | |
| Published | 2019-01-01 |
| URL | https://www.aclweb.org/anthology/W19-0314/ |
| https://www.aclweb.org/anthology/W19-0314 | |
| PWC | https://paperswithcode.com/paper/electronical-resources-for-livonian |
| Repo | |
| Framework | |
Two Generator Game: Learning to Sample via Linear Goodness-of-Fit Test
| Title | Two Generator Game: Learning to Sample via Linear Goodness-of-Fit Test |
| Authors | Lizhong Ding, Mengyang Yu, Li Liu, Fan Zhu, Yong Liu, Yu Li, Ling Shao |
| Abstract | Learning the probability distribution of high-dimensional data is a challenging problem. To solve this problem, we formulate a deep energy adversarial network (DEAN), which casts the energy model learned from real data into an optimization of a goodness-of-fit (GOF) test statistic. DEAN can be interpreted as a GOF game between two generative networks, where one explicit generative network learns an energy-based distribution that fits the real data, and the other implicit generative network is trained by minimizing a GOF test statistic between the energy-based distribution and the generated data, such that the underlying distribution of the generated data is close to the energy-based distribution. We design a two-level alternative optimization procedure to train the explicit and implicit generative networks, such that the hyper-parameters can also be automatically learned. Experimental results show that DEAN achieves high quality generations compared to the state-of-the-art approaches. |
| Tasks | |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/9304-two-generator-game-learning-to-sample-via-linear-goodness-of-fit-test |
| http://papers.nips.cc/paper/9304-two-generator-game-learning-to-sample-via-linear-goodness-of-fit-test.pdf | |
| PWC | https://paperswithcode.com/paper/two-generator-game-learning-to-sample-via |
| Repo | |
| Framework | |
MaxpoolNMS: Getting Rid of NMS Bottlenecks in Two-Stage Object Detectors
| Title | MaxpoolNMS: Getting Rid of NMS Bottlenecks in Two-Stage Object Detectors |
| Authors | Lile Cai, Bin Zhao, Zhe Wang, Jie Lin, Chuan Sheng Foo, Mohamed Sabry Aly, Vijay Chandrasekhar |
| Abstract | Modern convolutional object detectors have improved the detection accuracy significantly, which in turn inspired the development of dedicated hardware accelerators to achieve real-time performance by exploiting inherent parallelism in the algorithm. Non-maximum suppression (NMS) is an indispensable operation in object detection. In stark contrast to most operations, the commonly-adopted GreedyNMS algorithm does not foster parallelism, which can be a major performance bottleneck. In this paper, we introduce MaxpoolNMS, a parallelizable alternative to the NMS algorithm, which is based on max-pooling classification score maps. By employing a novel multi-scale multi-channel max-pooling strategy, our method is 20x faster than GreedyNMS while simultaneously achieves comparable accuracy, when quantified across various benchmarking datasets, i.e., MS COCO, KITTI and PASCAL VOC. Furthermore, our method is better suited for hardware-based acceleration than GreedyNMS. |
| Tasks | Object Detection |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Cai_MaxpoolNMS_Getting_Rid_of_NMS_Bottlenecks_in_Two-Stage_Object_Detectors_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Cai_MaxpoolNMS_Getting_Rid_of_NMS_Bottlenecks_in_Two-Stage_Object_Detectors_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/maxpoolnms-getting-rid-of-nms-bottlenecks-in |
| Repo | |
| Framework | |
Using a Lexical Semantic Network for the Ontology Building
| Title | Using a Lexical Semantic Network for the Ontology Building |
| Authors | Nadia Bebeshina-Clairet, Sylvie Despres, Mathieu Lafourcade |
| Abstract | Building multilingual ontologies is a hard task as ontologies are often data-rich resources. We introduce an approach which allows exploiting structured lexical semantic knowledge for the ontology building. Given a multilingual lexical semantic (non ontological) resource and an ontology model, it allows mining relevant semantic knowledge and make the ontology building and enhancement process faster. |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1012/ |
| https://www.aclweb.org/anthology/R19-1012 | |
| PWC | https://paperswithcode.com/paper/using-a-lexical-semantic-network-for-the |
| Repo | |
| Framework | |
BrainEE at SemEval-2019 Task 3: Ensembling Linear Classifiers for Emotion Prediction
| Title | BrainEE at SemEval-2019 Task 3: Ensembling Linear Classifiers for Emotion Prediction |
| Authors | Vachagan Gratian |
| Abstract | The paper describes an ensemble of linear perceptrons trained for emotion classification as part of the SemEval-2019 shared-task 3. The model uses a matrix of probabilities to weight the activations of the base-classifiers and makes a final prediction using the sum rule. The base-classifiers are multi-class perceptrons utilizing character and word n-grams, part-of-speech tags and sentiment polarity scores. The results of our experiments indicate that the ensemble outperforms the base-classifiers, but only marginally. In the best scenario our model attains an F-Micro score of 0.672, whereas the base-classifiers attained scores ranging from 0.636 to 0.666. |
| Tasks | Emotion Classification |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2020/ |
| https://www.aclweb.org/anthology/S19-2020 | |
| PWC | https://paperswithcode.com/paper/brainee-at-semeval-2019-task-3-ensembling |
| Repo | |
| Framework | |
Generating Fluent Adversarial Examples for Natural Languages
| Title | Generating Fluent Adversarial Examples for Natural Languages |
| Authors | Huangzhao Zhang, Hao Zhou, Ning Miao, Lei Li |
| Abstract | Efficiently building an adversarial attacker for natural language processing (NLP) tasks is a real challenge. Firstly, as the sentence space is discrete, it is difficult to make small perturbations along the direction of gradients. Secondly, the fluency of the generated examples cannot be guaranteed. In this paper, we propose MHA, which addresses both problems by performing Metropolis-Hastings sampling, whose proposal is designed with the guidance of gradients. Experiments on IMDB and SNLI show that our proposed MHAoutperforms the baseline model on attacking capability. Adversarial training with MHA also leads to better robustness and performance. |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1559/ |
| https://www.aclweb.org/anthology/P19-1559 | |
| PWC | https://paperswithcode.com/paper/generating-fluent-adversarial-examples-for |
| Repo | |
| Framework | |
SINAI at SemEval-2019 Task 3: Using affective features for emotion classification in textual conversations
| Title | SINAI at SemEval-2019 Task 3: Using affective features for emotion classification in textual conversations |
| Authors | Flor Miriam Plaza-del-Arco, M. Dolores Molina-Gonz{'a}lez, Maite Martin, L. Alfonso Ure{~n}a-L{'o}pez |
| Abstract | Detecting emotions in textual conversation is a challenging problem in absence of nonverbal cues typically associated with emotion, like fa- cial expression or voice modulations. How- ever, more and more users are using message platforms such as WhatsApp or Telegram. For this reason, it is important to develop systems capable of understanding human emotions in textual conversations. In this paper, we carried out different systems to analyze the emotions of textual dialogue from SemEval-2019 Task 3: EmoContext for English language. Our main contribution is the integration of emotional and sentimental features in the classification using the SVM algorithm. |
| Tasks | Emotion Classification |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2053/ |
| https://www.aclweb.org/anthology/S19-2053 | |
| PWC | https://paperswithcode.com/paper/sinai-at-semeval-2019-task-3-using-affective |
| Repo | |
| Framework | |
