Paper Group ANR 614
Multi-Scale Wavelet Domain Residual Learning for Limited-Angle CT Reconstruction. Single-epoch supernova classification with deep convolutional neural networks. CLaC @ QATS: Quality Assessment for Text Simplification. Luck is Hard to Beat: The Difficulty of Sports Prediction. Tensor Robust Principal Component Analysis: Exact Recovery of Corrupted L …
Multi-Scale Wavelet Domain Residual Learning for Limited-Angle CT Reconstruction
| Title | Multi-Scale Wavelet Domain Residual Learning for Limited-Angle CT Reconstruction |
| Authors | Jawook Gu, Jong Chul Ye |
| Abstract | Limited-angle computed tomography (CT) is often used in clinical applications such as C-arm CT for interventional imaging. However, CT images from limited angles suffers from heavy artifacts due to incomplete projection data. Existing iterative methods require extensive calculations but can not deliver satisfactory results. Based on the observation that the artifacts from limited angles have some directional property and are globally distributed, we propose a novel multi-scale wavelet domain residual learning architecture, which compensates for the artifacts. Experiments have shown that the proposed method effectively eliminates artifacts, thereby preserving edge and global structures of the image. |
| Tasks | Computed Tomography (CT) |
| Published | 2017-03-04 |
| URL | http://arxiv.org/abs/1703.01382v1 |
| http://arxiv.org/pdf/1703.01382v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-scale-wavelet-domain-residual-learning |
| Repo | |
| Framework | |
Single-epoch supernova classification with deep convolutional neural networks
| Title | Single-epoch supernova classification with deep convolutional neural networks |
| Authors | Akisato Kimura, Ichiro Takahashi, Masaomi Tanaka, Naoki Yasuda, Naonori Ueda, Naoki Yoshida |
| Abstract | Supernovae Type-Ia (SNeIa) play a significant role in exploring the history of the expansion of the Universe, since they are the best-known standard candles with which we can accurately measure the distance to the objects. Finding large samples of SNeIa and investigating their detailed characteristics have become an important issue in cosmology and astronomy. Existing methods relied on a photometric approach that first measures the luminance of supernova candidates precisely and then fits the results to a parametric function of temporal changes in luminance. However, it inevitably requires multi-epoch observations and complex luminance measurements. In this work, we present a novel method for classifying SNeIa simply from single-epoch observation images without any complex measurements, by effectively integrating the state-of-the-art computer vision methodology into the standard photometric approach. Our method first builds a convolutional neural network for estimating the luminance of supernovae from telescope images, and then constructs another neural network for the classification, where the estimated luminance and observation dates are used as features for classification. Both of the neural networks are integrated into a single deep neural network to classify SNeIa directly from observation images. Experimental results show the effectiveness of the proposed method and reveal classification performance comparable to existing photometric methods with multi-epoch observations. |
| Tasks | |
| Published | 2017-11-30 |
| URL | http://arxiv.org/abs/1711.11526v1 |
| http://arxiv.org/pdf/1711.11526v1.pdf | |
| PWC | https://paperswithcode.com/paper/single-epoch-supernova-classification-with |
| Repo | |
| Framework | |
CLaC @ QATS: Quality Assessment for Text Simplification
| Title | CLaC @ QATS: Quality Assessment for Text Simplification |
| Authors | Elnaz Davoodi, Leila Kosseim |
| Abstract | This paper describes our approach to the 2016 QATS quality assessment shared task. We trained three independent Random Forest classifiers in order to assess the quality of the simplified texts in terms of grammaticality, meaning preservation and simplicity. We used the language model of Google-Ngram as feature to predict the grammaticality. Meaning preservation is predicted using two complementary approaches based on word embedding and WordNet synonyms. A wider range of features including TF-IDF, sentence length and frequency of cue phrases are used to evaluate the simplicity aspect. Overall, the accuracy of the system ranges from 33.33% for the overall aspect to 58.73% for grammaticality. |
| Tasks | Language Modelling, Text Simplification |
| Published | 2017-08-19 |
| URL | http://arxiv.org/abs/1708.05797v1 |
| http://arxiv.org/pdf/1708.05797v1.pdf | |
| PWC | https://paperswithcode.com/paper/clac-qats-quality-assessment-for-text |
| Repo | |
| Framework | |
Luck is Hard to Beat: The Difficulty of Sports Prediction
| Title | Luck is Hard to Beat: The Difficulty of Sports Prediction |
| Authors | Raquel YS Aoki, Renato M Assuncao, Pedro OS Vaz de Melo |
| Abstract | Predicting the outcome of sports events is a hard task. We quantify this difficulty with a coefficient that measures the distance between the observed final results of sports leagues and idealized perfectly balanced competitions in terms of skill. This indicates the relative presence of luck and skill. We collected and analyzed all games from 198 sports leagues comprising 1503 seasons from 84 countries of 4 different sports: basketball, soccer, volleyball and handball. We measured the competitiveness by countries and sports. We also identify in each season which teams, if removed from its league, result in a completely random tournament. Surprisingly, not many of them are needed. As another contribution of this paper, we propose a probabilistic graphical model to learn about the teams’ skills and to decompose the relative weights of luck and skill in each game. We break down the skill component into factors associated with the teams’ characteristics. The model also allows to estimate as 0.36 the probability that an underdog team wins in the NBA league, with a home advantage adding 0.09 to this probability. As shown in the first part of the paper, luck is substantially present even in the most competitive championships, which partially explains why sophisticated and complex feature-based models hardly beat simple models in the task of forecasting sports’ outcomes. |
| Tasks | |
| Published | 2017-06-08 |
| URL | http://arxiv.org/abs/1706.02447v1 |
| http://arxiv.org/pdf/1706.02447v1.pdf | |
| PWC | https://paperswithcode.com/paper/luck-is-hard-to-beat-the-difficulty-of-sports |
| Repo | |
| Framework | |
Tensor Robust Principal Component Analysis: Exact Recovery of Corrupted Low-Rank Tensors via Convex Optimization
| Title | Tensor Robust Principal Component Analysis: Exact Recovery of Corrupted Low-Rank Tensors via Convex Optimization |
| Authors | Canyi Lu, Jiashi Feng, Yudong Chen, Wei Liu, Zhouchen Lin, Shuicheng Yan |
| Abstract | This paper studies the Tensor Robust Principal Component (TRPCA) problem which extends the known Robust PCA (Candes et al. 2011) to the tensor case. Our model is based on a new tensor Singular Value Decomposition (t-SVD) (Kilmer and Martin 2011) and its induced tensor tubal rank and tensor nuclear norm. Consider that we have a 3-way tensor ${\mathcal{X}}\in\mathbb{R}^{n_1\times n_2\times n_3}$ such that ${\mathcal{X}}={\mathcal{L}}_0+{\mathcal{E}}_0$, where ${\mathcal{L}}_0$ has low tubal rank and ${\mathcal{E}}0$ is sparse. Is that possible to recover both components? In this work, we prove that under certain suitable assumptions, we can recover both the low-rank and the sparse components exactly by simply solving a convex program whose objective is a weighted combination of the tensor nuclear norm and the $\ell_1$-norm, i.e., $\min{{\mathcal{L}},\ {\mathcal{E}}} \ {{\mathcal{L}}}_*+\lambda{{\mathcal{E}}}_1, \ \text{s.t.} \ {\mathcal{X}}={\mathcal{L}}+{\mathcal{E}}$, where $\lambda= {1}/{\sqrt{\max(n_1,n_2)n_3}}$. Interestingly, TRPCA involves RPCA as a special case when $n_3=1$ and thus it is a simple and elegant tensor extension of RPCA. Also numerical experiments verify our theory and the application for the image denoising demonstrates the effectiveness of our method. |
| Tasks | Denoising, Image Denoising |
| Published | 2017-08-14 |
| URL | http://arxiv.org/abs/1708.04181v3 |
| http://arxiv.org/pdf/1708.04181v3.pdf | |
| PWC | https://paperswithcode.com/paper/tensor-robust-principal-component-analysis-1 |
| Repo | |
| Framework | |
Transfer Learning for Named-Entity Recognition with Neural Networks
| Title | Transfer Learning for Named-Entity Recognition with Neural Networks |
| Authors | Ji Young Lee, Franck Dernoncourt, Peter Szolovits |
| Abstract | Recent approaches based on artificial neural networks (ANNs) have shown promising results for named-entity recognition (NER). In order to achieve high performances, ANNs need to be trained on a large labeled dataset. However, labels might be difficult to obtain for the dataset on which the user wants to perform NER: label scarcity is particularly pronounced for patient note de-identification, which is an instance of NER. In this work, we analyze to what extent transfer learning may address this issue. In particular, we demonstrate that transferring an ANN model trained on a large labeled dataset to another dataset with a limited number of labels improves upon the state-of-the-art results on two different datasets for patient note de-identification. |
| Tasks | Named Entity Recognition, Transfer Learning |
| Published | 2017-05-17 |
| URL | http://arxiv.org/abs/1705.06273v1 |
| http://arxiv.org/pdf/1705.06273v1.pdf | |
| PWC | https://paperswithcode.com/paper/transfer-learning-for-named-entity |
| Repo | |
| Framework | |
Learning Aggregated Transmission Propagation Networks for Haze Removal and Beyond
| Title | Learning Aggregated Transmission Propagation Networks for Haze Removal and Beyond |
| Authors | Risheng Liu, Xin Fan, Minjun Hou, Zhiying Jiang, Zhongxuan Luo, Lei Zhang |
| Abstract | Single image dehazing is an important low-level vision task with many applications. Early researches have investigated different kinds of visual priors to address this problem. However, they may fail when their assumptions are not valid on specific images. Recent deep networks also achieve relatively good performance in this task. But unfortunately, due to the disappreciation of rich physical rules in hazes, large amounts of data are required for their training. More importantly, they may still fail when there exist completely different haze distributions in testing images. By considering the collaborations of these two perspectives, this paper designs a novel residual architecture to aggregate both prior (i.e., domain knowledge) and data (i.e., haze distribution) information to propagate transmissions for scene radiance estimation. We further present a variational energy based perspective to investigate the intrinsic propagation behavior of our aggregated deep model. In this way, we actually bridge the gap between prior driven models and data driven networks and leverage advantages but avoid limitations of previous dehazing approaches. A lightweight learning framework is proposed to train our propagation network. Finally, by introducing a taskaware image separation formulation with a flexible optimization scheme, we extend the proposed model for more challenging vision tasks, such as underwater image enhancement and single image rain removal. Experiments on both synthetic and realworld images demonstrate the effectiveness and efficiency of the proposed framework. |
| Tasks | Image Dehazing, Image Enhancement, Rain Removal, Single Image Dehazing |
| Published | 2017-11-18 |
| URL | http://arxiv.org/abs/1711.06787v2 |
| http://arxiv.org/pdf/1711.06787v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-aggregated-transmission-propagation |
| Repo | |
| Framework | |
Photo-Guided Exploration of Volume Data Features
| Title | Photo-Guided Exploration of Volume Data Features |
| Authors | Mohammad Raji, Alok Hota, Robert Sisneros, Peter Messmer, Jian Huang |
| Abstract | In this work, we pose the question of whether, by considering qualitative information such as a sample target image as input, one can produce a rendered image of scientific data that is similar to the target. The algorithm resulting from our research allows one to ask the question of whether features like those in the target image exists in a given dataset. In that way, our method is one of imagery query or reverse engineering, as opposed to manual parameter tweaking of the full visualization pipeline. For target images, we can use real-world photographs of physical phenomena. Our method leverages deep neural networks and evolutionary optimization. Using a trained similarity function that measures the difference between renderings of a phenomenon and real-world photographs, our method optimizes rendering parameters. We demonstrate the efficacy of our method using a superstorm simulation dataset and images found online. We also discuss a parallel implementation of our method, which was run on NCSA’s Blue Waters. |
| Tasks | |
| Published | 2017-10-18 |
| URL | http://arxiv.org/abs/1710.06815v1 |
| http://arxiv.org/pdf/1710.06815v1.pdf | |
| PWC | https://paperswithcode.com/paper/photo-guided-exploration-of-volume-data |
| Repo | |
| Framework | |
What we really want to find by Sentiment Analysis: The Relationship between Computational Models and Psychological State
| Title | What we really want to find by Sentiment Analysis: The Relationship between Computational Models and Psychological State |
| Authors | Hwiyeol Jo, Soo-Min Kim, Jeong Ryu |
| Abstract | As the first step to model emotional state of a person, we build sentiment analysis models with existing deep neural network algorithms and compare the models with psychological measurements to enlighten the relationship. In the experiments, we first examined psychological state of 64 participants and asked them to summarize the story of a book, Chronicle of a Death Foretold (Marquez, 1981). Secondly, we trained models using crawled 365,802 movie review data; then we evaluated participants’ summaries using the pretrained model as a concept of transfer learning. With the background that emotion affects on memories, we investigated the relationship between the evaluation score of the summaries from computational models and the examined psychological measurements. The result shows that although CNN performed the best among other deep neural network algorithms (LSTM, GRU), its results are not related to the psychological state. Rather, GRU shows more explainable results depending on the psychological state. The contribution of this paper can be summarized as follows: (1) we enlighten the relationship between computational models and psychological measurements. (2) we suggest this framework as objective methods to evaluate the emotion; the real sentiment analysis of a person. |
| Tasks | Sentiment Analysis, Transfer Learning |
| Published | 2017-04-11 |
| URL | http://arxiv.org/abs/1704.03407v2 |
| http://arxiv.org/pdf/1704.03407v2.pdf | |
| PWC | https://paperswithcode.com/paper/what-we-really-want-to-find-by-sentiment |
| Repo | |
| Framework | |
GHCLNet: A Generalized Hierarchically tuned Contact Lens detection Network
| Title | GHCLNet: A Generalized Hierarchically tuned Contact Lens detection Network |
| Authors | Avantika Singh, Vishesh Mistry, Dhananjay Yadav, Aditya Nigam |
| Abstract | Iris serves as one of the best biometric modality owing to its complex, unique and stable structure. However, it can still be spoofed using fabricated eyeballs and contact lens. Accurate identification of contact lens is must for reliable performance of any biometric authentication system based on this modality. In this paper, we present a novel approach for detecting contact lens using a Generalized Hierarchically tuned Contact Lens detection Network (GHCLNet) . We have proposed hierarchical architecture for three class oculus classification namely: no lens, soft lens and cosmetic lens. Our network architecture is inspired by ResNet-50 model. This network works on raw input iris images without any pre-processing and segmentation requirement and this is one of its prodigious strength. We have performed extensive experimentation on two publicly available data-sets namely: 1)IIIT-D 2)ND and on IIT-K data-set (not publicly available) to ensure the generalizability of our network. The proposed architecture results are quite promising and outperforms the available state-of-the-art lens detection algorithms. |
| Tasks | |
| Published | 2017-10-14 |
| URL | http://arxiv.org/abs/1710.05152v1 |
| http://arxiv.org/pdf/1710.05152v1.pdf | |
| PWC | https://paperswithcode.com/paper/ghclnet-a-generalized-hierarchically-tuned |
| Repo | |
| Framework | |
Nonconvex One-bit Single-label Multi-label Learning
| Title | Nonconvex One-bit Single-label Multi-label Learning |
| Authors | Shuang Qiu, Tingjin Luo, Jieping Ye, Ming Lin |
| Abstract | We study an extreme scenario in multi-label learning where each training instance is endowed with a single one-bit label out of multiple labels. We formulate this problem as a non-trivial special case of one-bit rank-one matrix sensing and develop an efficient non-convex algorithm based on alternating power iteration. The proposed algorithm is able to recover the underlying low-rank matrix model with linear convergence. For a rank-$k$ model with $d_1$ features and $d_2$ classes, the proposed algorithm achieves $O(\epsilon)$ recovery error after retrieving $O(k^{1.5}d_1 d_2/\epsilon)$ one-bit labels within $O(kd)$ memory. Our bound is nearly optimal in the order of $O(1/\epsilon)$. This significantly improves the state-of-the-art sampling complexity of one-bit multi-label learning. We perform experiments to verify our theory and evaluate the performance of the proposed algorithm. |
| Tasks | Multi-Label Learning |
| Published | 2017-03-17 |
| URL | http://arxiv.org/abs/1703.06104v1 |
| http://arxiv.org/pdf/1703.06104v1.pdf | |
| PWC | https://paperswithcode.com/paper/nonconvex-one-bit-single-label-multi-label |
| Repo | |
| Framework | |
Enhancing Convolutional Neural Networks for Face Recognition with Occlusion Maps and Batch Triplet Loss
| Title | Enhancing Convolutional Neural Networks for Face Recognition with Occlusion Maps and Batch Triplet Loss |
| Authors | Daniel Sáez Trigueros, Li Meng, Margaret Hartnett |
| Abstract | Despite the recent success of convolutional neural networks for computer vision applications, unconstrained face recognition remains a challenge. In this work, we make two contributions to the field. Firstly, we consider the problem of face recognition with partial occlusions and show how current approaches might suffer significant performance degradation when dealing with this kind of face images. We propose a simple method to find out which parts of the human face are more important to achieve a high recognition rate, and use that information during training to force a convolutional neural network to learn discriminative features from all the face regions more equally, including those that typical approaches tend to pay less attention to. We test the accuracy of the proposed method when dealing with real-life occlusions using the AR face database. Secondly, we propose a novel loss function called batch triplet loss that improves the performance of the triplet loss by adding an extra term to the loss function to cause minimisation of the standard deviation of both positive and negative scores. We show consistent improvement in the Labeled Faces in the Wild (LFW) benchmark by applying both proposed adjustments to the convolutional neural network training. |
| Tasks | Face Recognition |
| Published | 2017-07-25 |
| URL | http://arxiv.org/abs/1707.07923v4 |
| http://arxiv.org/pdf/1707.07923v4.pdf | |
| PWC | https://paperswithcode.com/paper/enhancing-convolutional-neural-networks-for |
| Repo | |
| Framework | |
A Forward-Backward Approach for Visualizing Information Flow in Deep Networks
| Title | A Forward-Backward Approach for Visualizing Information Flow in Deep Networks |
| Authors | Aditya Balu, Thanh V. Nguyen, Apurva Kokate, Chinmay Hegde, Soumik Sarkar |
| Abstract | We introduce a new, systematic framework for visualizing information flow in deep networks. Specifically, given any trained deep convolutional network model and a given test image, our method produces a compact support in the image domain that corresponds to a (high-resolution) feature that contributes to the given explanation. Our method is both computationally efficient as well as numerically robust. We present several preliminary numerical results that support the benefits of our framework over existing methods. |
| Tasks | |
| Published | 2017-11-16 |
| URL | http://arxiv.org/abs/1711.06221v1 |
| http://arxiv.org/pdf/1711.06221v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-forward-backward-approach-for-visualizing |
| Repo | |
| Framework | |
Learning and Real-time Classification of Hand-written Digits With Spiking Neural Networks
| Title | Learning and Real-time Classification of Hand-written Digits With Spiking Neural Networks |
| Authors | Shruti R. Kulkarni, John M. Alexiades, Bipin Rajendran |
| Abstract | We describe a novel spiking neural network (SNN) for automated, real-time handwritten digit classification and its implementation on a GP-GPU platform. Information processing within the network, from feature extraction to classification is implemented by mimicking the basic aspects of neuronal spike initiation and propagation in the brain. The feature extraction layer of the SNN uses fixed synaptic weight maps to extract the key features of the image and the classifier layer uses the recently developed NormAD approximate gradient descent based supervised learning algorithm for spiking neural networks to adjust the synaptic weights. On the standard MNIST database images of handwritten digits, our network achieves an accuracy of 99.80% on the training set and 98.06% on the test set, with nearly 7x fewer parameters compared to the state-of-the-art spiking networks. We further use this network in a GPU based user-interface system demonstrating real-time SNN simulation to infer digits written by different users. On a test set of 500 such images, this real-time platform achieves an accuracy exceeding 97% while making a prediction within an SNN emulation time of less than 100ms. |
| Tasks | |
| Published | 2017-11-09 |
| URL | http://arxiv.org/abs/1711.03637v1 |
| http://arxiv.org/pdf/1711.03637v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-and-real-time-classification-of-hand |
| Repo | |
| Framework | |
BrainSegNet : A Segmentation Network for Human Brain Fiber Tractography Data into Anatomically Meaningful Clusters
| Title | BrainSegNet : A Segmentation Network for Human Brain Fiber Tractography Data into Anatomically Meaningful Clusters |
| Authors | Tushar Gupta, Shreyas Malakarjun Patil, Mukkaram Tailor, Daksh Thapar, Aditya Nigam |
| Abstract | The segregation of brain fiber tractography data into distinct and anatomically meaningful clusters can help to comprehend the complex brain structure and early investigation and management of various neural disorders. We propose a novel stacked bidirectional long short-term memory(LSTM) based segmentation network, (BrainSegNet) for human brain fiber tractography data classification. We perform a two-level hierarchical classification a) White vs Grey matter (Macro) and b) White matter clusters (Micro). BrainSegNet is trained over three brain tractography data having over 250,000 fibers each. Our experimental evaluation shows that our model achieves state-of-the-art results. We have performed inter as well as intra class testing over three patient’s brain tractography data and achieved a high classification accuracy for both macro and micro levels both under intra as well as inter brain testing scenario. |
| Tasks | |
| Published | 2017-10-14 |
| URL | http://arxiv.org/abs/1710.05158v1 |
| http://arxiv.org/pdf/1710.05158v1.pdf | |
| PWC | https://paperswithcode.com/paper/brainsegnet-a-segmentation-network-for-human |
| Repo | |
| Framework | |
