Paper Group ANR 373
Ranking Based Locality Sensitive Hashing Enabled Cancelable Biometrics: Index-of-Max Hashing. Improving Deep Learning using Generic Data Augmentation. A GRU-based Encoder-Decoder Approach with Attention for Online Handwritten Mathematical Expression Recognition. Characterizing and Improving Stability in Neural Style Transfer. Automatic Summarizatio …
Ranking Based Locality Sensitive Hashing Enabled Cancelable Biometrics: Index-of-Max Hashing
| Title | Ranking Based Locality Sensitive Hashing Enabled Cancelable Biometrics: Index-of-Max Hashing |
| Authors | Zhe Jin, Yen-Lung Lai, Jung-Yeon Hwang, Soohyung Kim, Andrew Beng Jin Teoh |
| Abstract | In this paper, we propose a ranking based locality sensitive hashing inspired two-factor cancelable biometrics, dubbed “Index-of-Max” (IoM) hashing for biometric template protection. With externally generated random parameters, IoM hashing transforms a real-valued biometric feature vector into discrete index (max ranked) hashed code. We demonstrate two realizations from IoM hashing notion, namely Gaussian Random Projection based and Uniformly Random Permutation based hashing schemes. The discrete indices representation nature of IoM hashed codes enjoy serveral merits. Firstly, IoM hashing empowers strong concealment to the biometric information. This contributes to the solid ground of non-invertibility guarantee. Secondly, IoM hashing is insensitive to the features magnitude, hence is more robust against biometric features variation. Thirdly, the magnitude-independence trait of IoM hashing makes the hash codes being scale-invariant, which is critical for matching and feature alignment. The experimental results demonstrate favorable accuracy performance on benchmark FVC2002 and FVC2004 fingerprint databases. The analyses justify its resilience to the existing and newly introduced security and privacy attacks as well as satisfy the revocability and unlinkability criteria of cancelable biometrics. |
| Tasks | |
| Published | 2017-03-16 |
| URL | http://arxiv.org/abs/1703.05455v2 |
| http://arxiv.org/pdf/1703.05455v2.pdf | |
| PWC | https://paperswithcode.com/paper/ranking-based-locality-sensitive-hashing |
| Repo | |
| Framework | |
Improving Deep Learning using Generic Data Augmentation
| Title | Improving Deep Learning using Generic Data Augmentation |
| Authors | Luke Taylor, Geoff Nitschke |
| Abstract | Deep artificial neural networks require a large corpus of training data in order to effectively learn, where collection of such training data is often expensive and laborious. Data augmentation overcomes this issue by artificially inflating the training set with label preserving transformations. Recently there has been extensive use of generic data augmentation to improve Convolutional Neural Network (CNN) task performance. This study benchmarks various popular data augmentation schemes to allow researchers to make informed decisions as to which training methods are most appropriate for their data sets. Various geometric and photometric schemes are evaluated on a coarse-grained data set using a relatively simple CNN. Experimental results, run using 4-fold cross-validation and reported in terms of Top-1 and Top-5 accuracy, indicate that cropping in geometric augmentation significantly increases CNN task performance. |
| Tasks | Data Augmentation |
| Published | 2017-08-20 |
| URL | http://arxiv.org/abs/1708.06020v1 |
| http://arxiv.org/pdf/1708.06020v1.pdf | |
| PWC | https://paperswithcode.com/paper/improving-deep-learning-using-generic-data |
| Repo | |
| Framework | |
A GRU-based Encoder-Decoder Approach with Attention for Online Handwritten Mathematical Expression Recognition
| Title | A GRU-based Encoder-Decoder Approach with Attention for Online Handwritten Mathematical Expression Recognition |
| Authors | Jianshu Zhang, Jun Du, Lirong Dai |
| Abstract | In this study, we present a novel end-to-end approach based on the encoder-decoder framework with the attention mechanism for online handwritten mathematical expression recognition (OHMER). First, the input two-dimensional ink trajectory information of handwritten expression is encoded via the gated recurrent unit based recurrent neural network (GRU-RNN). Then the decoder is also implemented by the GRU-RNN with a coverage-based attention model. The proposed approach can simultaneously accomplish the symbol recognition and structural analysis to output a character sequence in LaTeX format. Validated on the CROHME 2014 competition task, our approach significantly outperforms the state-of-the-art with an expression recognition accuracy of 52.43% by only using the official training dataset. Furthermore, the alignments between the input trajectories of handwritten expressions and the output LaTeX sequences are visualized by the attention mechanism to show the effectiveness of the proposed method. |
| Tasks | |
| Published | 2017-12-04 |
| URL | http://arxiv.org/abs/1712.03991v1 |
| http://arxiv.org/pdf/1712.03991v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-gru-based-encoder-decoder-approach-with |
| Repo | |
| Framework | |
Characterizing and Improving Stability in Neural Style Transfer
| Title | Characterizing and Improving Stability in Neural Style Transfer |
| Authors | Agrim Gupta, Justin Johnson, Alexandre Alahi, Li Fei-Fei |
| Abstract | Recent progress in style transfer on images has focused on improving the quality of stylized images and speed of methods. However, real-time methods are highly unstable resulting in visible flickering when applied to videos. In this work we characterize the instability of these methods by examining the solution set of the style transfer objective. We show that the trace of the Gram matrix representing style is inversely related to the stability of the method. Then, we present a recurrent convolutional network for real-time video style transfer which incorporates a temporal consistency loss and overcomes the instability of prior methods. Our networks can be applied at any resolution, do not re- quire optical flow at test time, and produce high quality, temporally consistent stylized videos in real-time. |
| Tasks | Optical Flow Estimation, Style Transfer, Video Style Transfer |
| Published | 2017-05-05 |
| URL | http://arxiv.org/abs/1705.02092v1 |
| http://arxiv.org/pdf/1705.02092v1.pdf | |
| PWC | https://paperswithcode.com/paper/characterizing-and-improving-stability-in |
| Repo | |
| Framework | |
Automatic Summarization of Online Debates
| Title | Automatic Summarization of Online Debates |
| Authors | Nattapong Sanchan, Ahmet Aker, Kalina Bontcheva |
| Abstract | Debate summarization is one of the novel and challenging research areas in automatic text summarization which has been largely unexplored. In this paper, we develop a debate summarization pipeline to summarize key topics which are discussed or argued in the two opposing sides of online debates. We view that the generation of debate summaries can be achieved by clustering, cluster labeling, and visualization. In our work, we investigate two different clustering approaches for the generation of the summaries. In the first approach, we generate the summaries by applying purely term-based clustering and cluster labeling. The second approach makes use of X-means for clustering and Mutual Information for labeling the clusters. Both approaches are driven by ontologies. We visualize the results using bar charts. We think that our results are a smooth entry for users aiming to receive the first impression about what is discussed within a debate topic containing waste number of argumentations. |
| Tasks | Text Summarization |
| Published | 2017-08-15 |
| URL | http://arxiv.org/abs/1708.04587v1 |
| http://arxiv.org/pdf/1708.04587v1.pdf | |
| PWC | https://paperswithcode.com/paper/automatic-summarization-of-online-debates |
| Repo | |
| Framework | |
Identifying Patterns of Associated-Conditions through Topic Models of Electronic Medical Records
| Title | Identifying Patterns of Associated-Conditions through Topic Models of Electronic Medical Records |
| Authors | Moumita Bhattacharya, Claudine Jurkovitz, Hagit Shatkay |
| Abstract | Multiple adverse health conditions co-occurring in a patient are typically associated with poor prognosis and increased office or hospital visits. Developing methods to identify patterns of co-occurring conditions can assist in diagnosis. Thus identifying patterns of associations among co-occurring conditions is of growing interest. In this paper, we report preliminary results from a data-driven study, in which we apply a machine learning method, namely, topic modeling, to electronic medical records, aiming to identify patterns of associated conditions. Specifically, we use the well established latent dirichlet allocation, a method based on the idea that documents can be modeled as a mixture of latent topics, where each topic is a distribution over words. In our study, we adapt the LDA model to identify latent topics in patients’ EMRs. We evaluate the performance of our method both qualitatively, and show that the obtained topics indeed align well with distinct medical phenomena characterized by co-occurring conditions. |
| Tasks | Topic Models |
| Published | 2017-11-17 |
| URL | http://arxiv.org/abs/1711.10960v1 |
| http://arxiv.org/pdf/1711.10960v1.pdf | |
| PWC | https://paperswithcode.com/paper/identifying-patterns-of-associated-conditions |
| Repo | |
| Framework | |
Importance of Image Enhancement Techniques in Color Image Segmentation: A Comprehensive and Comparative Study
| Title | Importance of Image Enhancement Techniques in Color Image Segmentation: A Comprehensive and Comparative Study |
| Authors | Dibya Jyoti Bora |
| Abstract | Color image segmentation is a very emerging research topic in the area of color image analysis and pattern recognition. Many state-of-the-art algorithms have been developed for this purpose. But, often the segmentation results of these algorithms seem to be suffering from miss-classifications and over-segmentation. The reasons behind these are the degradation of image quality during the acquisition, transmission and color space conversion. So, here arises the need of an efficient image enhancement technique which can remove the redundant pixels or noises from the color image before proceeding for final segmentation. In this paper, an effort has been made to study and analyze different image enhancement techniques and thereby finding out the better one for color image segmentation. Also, this comparative study is done on two well-known color spaces HSV and LAB separately to find out which color space supports segmentation task more efficiently with respect to those enhancement techniques. |
| Tasks | Image Enhancement, Semantic Segmentation |
| Published | 2017-08-09 |
| URL | http://arxiv.org/abs/1708.05081v1 |
| http://arxiv.org/pdf/1708.05081v1.pdf | |
| PWC | https://paperswithcode.com/paper/importance-of-image-enhancement-techniques-in |
| Repo | |
| Framework | |
Measuring the Similarity of Sentential Arguments in Dialog
| Title | Measuring the Similarity of Sentential Arguments in Dialog |
| Authors | Amita Misra, Brian Ecker, Marilyn A. Walker |
| Abstract | When people converse about social or political topics, similar arguments are often paraphrased by different speakers, across many different conversations. Debate websites produce curated summaries of arguments on such topics; these summaries typically consist of lists of sentences that represent frequently paraphrased propositions, or labels capturing the essence of one particular aspect of an argument, e.g. Morality or Second Amendment. We call these frequently paraphrased propositions ARGUMENT FACETS. Like these curated sites, our goal is to induce and identify argument facets across multiple conversations, and produce summaries. However, we aim to do this automatically. We frame the problem as consisting of two steps: we first extract sentences that express an argument from raw social media dialogs, and then rank the extracted arguments in terms of their similarity to one another. Sets of similar arguments are used to represent argument facets. We show here that we can predict ARGUMENT FACET SIMILARITY with a correlation averaging 0.63 compared to a human topline averaging 0.68 over three debate topics, easily beating several reasonable baselines. |
| Tasks | |
| Published | 2017-09-06 |
| URL | http://arxiv.org/abs/1709.01887v1 |
| http://arxiv.org/pdf/1709.01887v1.pdf | |
| PWC | https://paperswithcode.com/paper/measuring-the-similarity-of-sentential |
| Repo | |
| Framework | |
Self-supervised Multi-level Face Model Learning for Monocular Reconstruction at over 250 Hz
| Title | Self-supervised Multi-level Face Model Learning for Monocular Reconstruction at over 250 Hz |
| Authors | Ayush Tewari, Michael Zollhöfer, Pablo Garrido, Florian Bernard, Hyeongwoo Kim, Patrick Pérez, Christian Theobalt |
| Abstract | The reconstruction of dense 3D models of face geometry and appearance from a single image is highly challenging and ill-posed. To constrain the problem, many approaches rely on strong priors, such as parametric face models learned from limited 3D scan data. However, prior models restrict generalization of the true diversity in facial geometry, skin reflectance and illumination. To alleviate this problem, we present the first approach that jointly learns 1) a regressor for face shape, expression, reflectance and illumination on the basis of 2) a concurrently learned parametric face model. Our multi-level face model combines the advantage of 3D Morphable Models for regularization with the out-of-space generalization of a learned corrective space. We train end-to-end on in-the-wild images without dense annotations by fusing a convolutional encoder with a differentiable expert-designed renderer and a self-supervised training loss, both defined at multiple detail levels. Our approach compares favorably to the state-of-the-art in terms of reconstruction quality, better generalizes to real world faces, and runs at over 250 Hz. |
| Tasks | |
| Published | 2017-12-07 |
| URL | http://arxiv.org/abs/1712.02859v2 |
| http://arxiv.org/pdf/1712.02859v2.pdf | |
| PWC | https://paperswithcode.com/paper/self-supervised-multi-level-face-model |
| Repo | |
| Framework | |
Feed-forward approximations to dynamic recurrent network architectures
| Title | Feed-forward approximations to dynamic recurrent network architectures |
| Authors | Dylan Richard Muir |
| Abstract | Recurrent neural network architectures can have useful computational properties, with complex temporal dynamics and input-sensitive attractor states. However, evaluation of recurrent dynamic architectures requires solution of systems of differential equations, and the number of evaluations required to determine their response to a given input can vary with the input, or can be indeterminate altogether in the case of oscillations or instability. In feed-forward networks, by contrast, only a single pass through the network is needed to determine the response to a given input. Modern machine-learning systems are designed to operate efficiently on feed-forward architectures. We hypothesised that two-layer feedforward architectures with simple, deterministic dynamics could approximate the responses of single-layer recurrent network architectures. By identifying the fixed-point responses of a given recurrent network, we trained two-layer networks to directly approximate the fixed-point response to a given input. These feed-forward networks then embodied useful computations, including competitive interactions, information transformations and noise rejection. Our approach was able to find useful approximations to recurrent networks, which can then be evaluated in linear and deterministic time complexity. |
| Tasks | |
| Published | 2017-04-21 |
| URL | http://arxiv.org/abs/1704.06645v2 |
| http://arxiv.org/pdf/1704.06645v2.pdf | |
| PWC | https://paperswithcode.com/paper/feed-forward-approximations-to-dynamic |
| Repo | |
| Framework | |
Improving image generative models with human interactions
| Title | Improving image generative models with human interactions |
| Authors | Andrew Kyle Lampinen, David So, Douglas Eck, Fred Bertsch |
| Abstract | GANs provide a framework for training generative models which mimic a data distribution. However, in many cases we wish to train these generative models to optimize some auxiliary objective function within the data it generates, such as making more aesthetically pleasing images. In some cases, these objective functions are difficult to evaluate, e.g. they may require human interaction. Here, we develop a system for efficiently improving a GAN to target an objective involving human interaction, specifically generating images that increase rates of positive user interactions. To improve the generative model, we build a model of human behavior in the targeted domain from a relatively small set of interactions, and then use this behavioral model as an auxiliary loss function to improve the generative model. We show that this system is successful at improving positive interaction rates, at least on simulated data, and characterize some of the factors that affect its performance. |
| Tasks | |
| Published | 2017-09-29 |
| URL | http://arxiv.org/abs/1709.10459v1 |
| http://arxiv.org/pdf/1709.10459v1.pdf | |
| PWC | https://paperswithcode.com/paper/improving-image-generative-models-with-human |
| Repo | |
| Framework | |
LIDE: Language Identification from Text Documents
| Title | LIDE: Language Identification from Text Documents |
| Authors | Priyank Mathur, Arkajyoti Misra, Emrah Budur |
| Abstract | The increase in the use of microblogging came along with the rapid growth on short linguistic data. On the other hand deep learning is considered to be the new frontier to extract meaningful information out of large amount of raw data in an automated manner. In this study, we engaged these two emerging fields to come up with a robust language identifier on demand, namely Language Identification Engine (LIDE). As a result, we achieved 95.12% accuracy in Discriminating between Similar Languages (DSL) Shared Task 2015 dataset, which is comparable to the maximum reported accuracy of 95.54% achieved so far. |
| Tasks | Language Identification |
| Published | 2017-01-13 |
| URL | http://arxiv.org/abs/1701.03682v1 |
| http://arxiv.org/pdf/1701.03682v1.pdf | |
| PWC | https://paperswithcode.com/paper/lide-language-identification-from-text |
| Repo | |
| Framework | |
Precise Recovery of Latent Vectors from Generative Adversarial Networks
| Title | Precise Recovery of Latent Vectors from Generative Adversarial Networks |
| Authors | Zachary C. Lipton, Subarna Tripathi |
| Abstract | Generative adversarial networks (GANs) transform latent vectors into visually plausible images. It is generally thought that the original GAN formulation gives no out-of-the-box method to reverse the mapping, projecting images back into latent space. We introduce a simple, gradient-based technique called stochastic clipping. In experiments, for images generated by the GAN, we precisely recover their latent vector pre-images 100% of the time. Additional experiments demonstrate that this method is robust to noise. Finally, we show that even for unseen images, our method appears to recover unique encodings. |
| Tasks | |
| Published | 2017-02-15 |
| URL | http://arxiv.org/abs/1702.04782v2 |
| http://arxiv.org/pdf/1702.04782v2.pdf | |
| PWC | https://paperswithcode.com/paper/precise-recovery-of-latent-vectors-from |
| Repo | |
| Framework | |
LASAGNE: Locality And Structure Aware Graph Node Embedding
| Title | LASAGNE: Locality And Structure Aware Graph Node Embedding |
| Authors | Evgeniy Faerman, Felix Borutta, Kimon Fountoulakis, Michael W. Mahoney |
| Abstract | In this work we propose Lasagne, a methodology to learn locality and structure aware graph node embeddings in an unsupervised way. In particular, we show that the performance of existing random-walk based approaches depends strongly on the structural properties of the graph, e.g., the size of the graph, whether the graph has a flat or upward-sloping Network Community Profile (NCP), whether the graph is expander-like, whether the classes of interest are more k-core-like or more peripheral, etc. For larger graphs with flat NCPs that are strongly expander-like, existing methods lead to random walks that expand rapidly, touching many dissimilar nodes, thereby leading to lower-quality vector representations that are less useful for downstream tasks. Rather than relying on global random walks or neighbors within fixed hop distances, Lasagne exploits strongly local Approximate Personalized PageRank stationary distributions to more precisely engineer local information into node embeddings. This leads, in particular, to more meaningful and more useful vector representations of nodes in poorly-structured graphs. We show that Lasagne leads to significant improvement in downstream multi-label classification for larger graphs with flat NCPs, that it is comparable for smaller graphs with upward-sloping NCPs, and that is comparable to existing methods for link prediction tasks. |
| Tasks | Link Prediction, Multi-Label Classification |
| Published | 2017-10-17 |
| URL | http://arxiv.org/abs/1710.06520v1 |
| http://arxiv.org/pdf/1710.06520v1.pdf | |
| PWC | https://paperswithcode.com/paper/lasagne-locality-and-structure-aware-graph |
| Repo | |
| Framework | |
Describing Natural Images Containing Novel Objects with Knowledge Guided Assitance
| Title | Describing Natural Images Containing Novel Objects with Knowledge Guided Assitance |
| Authors | Aditya Mogadala, Umanga Bista, Lexing Xie, Achim Rettinger |
| Abstract | Images in the wild encapsulate rich knowledge about varied abstract concepts and cannot be sufficiently described with models built only using image-caption pairs containing selected objects. We propose to handle such a task with the guidance of a knowledge base that incorporate many abstract concepts. Our method is a two-step process where we first build a multi-entity-label image recognition model to predict abstract concepts as image labels and then leverage them in the second step as an external semantic attention and constrained inference in the caption generation model for describing images that depict unseen/novel objects. Evaluations show that our models outperform most of the prior work for out-of-domain captioning on MSCOCO and are useful for integration of knowledge and vision in general. |
| Tasks | |
| Published | 2017-10-17 |
| URL | http://arxiv.org/abs/1710.06303v1 |
| http://arxiv.org/pdf/1710.06303v1.pdf | |
| PWC | https://paperswithcode.com/paper/describing-natural-images-containing-novel |
| Repo | |
| Framework | |
