Paper Group ANR 636
Multi-cell LSTM Based Neural Language Model. bigMap: Big Data Mapping with Parallelized t-SNE. Network Inference from Temporal-Dependent Grouped Observations. Unsupervised Prostate Cancer Detection on H&E using Convolutional Adversarial Autoencoders. Unsupervisedly Training GANs for Segmenting Digital Pathology with Automatically Generated Annotati …
Multi-cell LSTM Based Neural Language Model
| Title | Multi-cell LSTM Based Neural Language Model |
| Authors | Thomas Cherian, Akshay Badola, Vineet Padmanabhan |
| Abstract | Language models, being at the heart of many NLP problems, are always of great interest to researchers. Neural language models come with the advantage of distributed representations and long range contexts. With its particular dynamics that allow the cycling of information within the network, `Recurrent neural network’ (RNN) becomes an ideal paradigm for neural language modeling. Long Short-Term Memory (LSTM) architecture solves the inadequacies of the standard RNN in modeling long-range contexts. In spite of a plethora of RNN variants, possibility to add multiple memory cells in LSTM nodes was seldom explored. Here we propose a multi-cell node architecture for LSTMs and study its applicability for neural language modeling. The proposed multi-cell LSTM language models outperform the state-of-the-art results on well-known Penn Treebank (PTB) setup. | |
| Tasks | Language Modelling |
| Published | 2018-11-15 |
| URL | http://arxiv.org/abs/1811.06477v1 |
| http://arxiv.org/pdf/1811.06477v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-cell-lstm-based-neural-language-model |
| Repo | |
| Framework | |
bigMap: Big Data Mapping with Parallelized t-SNE
| Title | bigMap: Big Data Mapping with Parallelized t-SNE |
| Authors | Joan Garriga, Frederic Bartumeus |
| Abstract | We introduce an improved unsupervised clustering protocol specially suited for large-scale structured data. The protocol follows three steps: a dimensionality reduction of the data, a density estimation over the low dimensional representation of the data, and a final segmentation of the density landscape. For the dimensionality reduction step we introduce a parallelized implementation of the well-known t-Stochastic Neighbouring Embedding (t-SNE) algorithm that significantly alleviates some inherent limitations, while improving its suitability for large datasets. We also introduce a new adaptive Kernel Density Estimation particularly coupled with the t-SNE framework in order to get accurate density estimates out of the embedded data, and a variant of the rainfalling watershed algorithm to identify clusters within the density landscape. The whole mapping protocol is wrapped in the bigMap R package, together with visualization and analysis tools to ease the qualitative and quantitative assessment of the clustering. |
| Tasks | Density Estimation, Dimensionality Reduction |
| Published | 2018-12-24 |
| URL | https://arxiv.org/abs/1812.09869v2 |
| https://arxiv.org/pdf/1812.09869v2.pdf | |
| PWC | https://paperswithcode.com/paper/bigmap-big-data-mapping-with-parallelized-t |
| Repo | |
| Framework | |
Network Inference from Temporal-Dependent Grouped Observations
| Title | Network Inference from Temporal-Dependent Grouped Observations |
| Authors | Yunpeng Zhao |
| Abstract | In social network analysis, the observed data is usually some social behavior, such as the formation of groups, rather than an explicit network structure. Zhao and Weko (2017) propose a model-based approach called the hub model to infer implicit networks from grouped observations. The hub model assumes independence between groups, which sometimes is not valid in practice. In this article, we generalize the idea of the hub model into the case of grouped observations with temporal dependence. As in the hub model, we assume that the group at each time point is gathered by one leader. Unlike in the hub model, the group leaders are not sampled independently but follow a Markov chain, and other members in adjacent groups can also be correlated. An expectation-maximization (EM) algorithm is developed for this model and a polynomial-time algorithm is proposed for the E-step. The performance of the new model is evaluated under different simulation settings. We apply this model to a data set of the Kibale Chimpanzee Project. |
| Tasks | |
| Published | 2018-08-25 |
| URL | http://arxiv.org/abs/1808.08478v1 |
| http://arxiv.org/pdf/1808.08478v1.pdf | |
| PWC | https://paperswithcode.com/paper/network-inference-from-temporal-dependent |
| Repo | |
| Framework | |
Unsupervised Prostate Cancer Detection on H&E using Convolutional Adversarial Autoencoders
| Title | Unsupervised Prostate Cancer Detection on H&E using Convolutional Adversarial Autoencoders |
| Authors | Wouter Bulten, Geert Litjens |
| Abstract | We propose an unsupervised method using self-clustering convolutional adversarial autoencoders to classify prostate tissue as tumor or non-tumor without any labeled training data. The clustering method is integrated into the training of the autoencoder and requires only little post-processing. Our network trains on hematoxylin and eosin (H&E) input patches and we tested two different reconstruction targets, H&E and immunohistochemistry (IHC). We show that antibody-driven feature learning using IHC helps the network to learn relevant features for the clustering task. Our network achieves a F1 score of 0.62 using only a small set of validation labels to assign classes to clusters. |
| Tasks | |
| Published | 2018-04-19 |
| URL | http://arxiv.org/abs/1804.07098v1 |
| http://arxiv.org/pdf/1804.07098v1.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-prostate-cancer-detection-on-he |
| Repo | |
| Framework | |
Unsupervisedly Training GANs for Segmenting Digital Pathology with Automatically Generated Annotations
| Title | Unsupervisedly Training GANs for Segmenting Digital Pathology with Automatically Generated Annotations |
| Authors | Michael Gadermayr, Laxmi Gupta, Barbara M. Klinkhammer, Peter Boor, Dorit Merhof |
| Abstract | Recently, generative adversarial networks exhibited excellent performances in semi-supervised image analysis scenarios. In this paper, we go even further by proposing a fully unsupervised approach for segmentation applications with prior knowledge of the objects’ shapes. We propose and investigate different strategies to generate simulated label data and perform image-to-image translation between the image and the label domain using an adversarial model. Specifically, we assess the impact of the annotation model’s accuracy as well as the effect of simulating additional low-level image features. For experimental evaluation, we consider the segmentation of the glomeruli, an application scenario from renal pathology. Experiments provide proof of concept and also confirm that the strategy for creating the simulated label data is of particular relevance considering the stability of GAN trainings. |
| Tasks | Image-to-Image Translation |
| Published | 2018-05-25 |
| URL | http://arxiv.org/abs/1805.10059v2 |
| http://arxiv.org/pdf/1805.10059v2.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervisedly-training-gans-for-segmenting |
| Repo | |
| Framework | |
Towards Enhancing Lexical Resource and Using Sense-annotations of OntoSenseNet for Sentiment Analysis
| Title | Towards Enhancing Lexical Resource and Using Sense-annotations of OntoSenseNet for Sentiment Analysis |
| Authors | Sreekavitha Parupalli, Vijjini Anvesh Rao, Radhika Mamidi |
| Abstract | This paper illustrates the interface of the tool we developed for crowd sourcing and we explain the annotation procedure in detail. Our tool is named as ‘Parupalli Padajaalam’ which means web of words by Parupalli. The aim of this tool is to populate the OntoSenseNet, sentiment polarity annotated Telugu resource. Recent works have shown the importance of word-level annotations on sentiment analysis. With this as basis, we aim to analyze the importance of sense-annotations obtained from OntoSenseNet in performing the task of sentiment analysis. We explain the fea- tures extracted from OntoSenseNet (Telugu). Furthermore we compute and explain the adverbial class distribution of verbs in OntoSenseNet. This task is known to aid in disambiguating word-senses which helps in enhancing the performance of word-sense disambiguation (WSD) task(s). |
| Tasks | Sentiment Analysis, Word Sense Disambiguation |
| Published | 2018-07-09 |
| URL | http://arxiv.org/abs/1807.03004v2 |
| http://arxiv.org/pdf/1807.03004v2.pdf | |
| PWC | https://paperswithcode.com/paper/towards-enhancing-lexical-resource-and-using |
| Repo | |
| Framework | |
Dynamic Swarm Dispersion in Particle Swarm Optimization for Mining Unsearched Area in Solution Space (DSDPSO)
| Title | Dynamic Swarm Dispersion in Particle Swarm Optimization for Mining Unsearched Area in Solution Space (DSDPSO) |
| Authors | Anvar Bahrampour, Omid Mohamad Nezami |
| Abstract | Premature convergence in particle swarm optimization (PSO) algorithm usually leads to gaining local optimum and preventing from surveying those regions of solution space which have optimal points in. In this paper, by applying special mechanisms, suitable regions were detected and then swarm was guided to them by dispersing part of particles on proper times. This process is called dynamic swarm dispersion in PSO (DSDPSO) algorithm. In order to specify the proper times and to rein the evolutionary process alternating between exploring and exploiting behaviors, we used a diversity measuring approach and implemented the dispersion mechanism. To promote the performance of DSDPSO algorithm, three different policies including particle relocation, velocity settings of dispersed particles and parameters setting were applied. We compared the promoted algorithm with similar new approaches and according to the numerical results, the proposed algorithm outperformed the basic GPSO, LPSO, DMS-PSO, CLPSO and APSO in most of the 12 standard benchmark problems with different properties taken in this study. |
| Tasks | |
| Published | 2018-07-02 |
| URL | http://arxiv.org/abs/1807.00438v1 |
| http://arxiv.org/pdf/1807.00438v1.pdf | |
| PWC | https://paperswithcode.com/paper/dynamic-swarm-dispersion-in-particle-swarm |
| Repo | |
| Framework | |
Linear and Deformable Image Registration with 3D Convolutional Neural Networks
| Title | Linear and Deformable Image Registration with 3D Convolutional Neural Networks |
| Authors | Stergios Christodoulidis, Mihir Sahasrabudhe, Maria Vakalopoulou, Guillaume Chassagnon, Marie-Pierre Revel, Stavroula Mougiakakou, Nikos Paragios |
| Abstract | Image registration and in particular deformable registration methods are pillars of medical imaging. Inspired by the recent advances in deep learning, we propose in this paper, a novel convolutional neural network architecture that couples linear and deformable registration within a unified architecture endowed with near real-time performance. Our framework is modular with respect to the global transformation component, as well as with respect to the similarity function while it guarantees smooth displacement fields. We evaluate the performance of our network on the challenging problem of MRI lung registration, and demonstrate superior performance with respect to state of the art elastic registration methods. The proposed deformation (between inspiration & expiration) was considered within a clinically relevant task of interstitial lung disease (ILD) classification and showed promising results. |
| Tasks | Image Registration |
| Published | 2018-09-13 |
| URL | http://arxiv.org/abs/1809.06226v1 |
| http://arxiv.org/pdf/1809.06226v1.pdf | |
| PWC | https://paperswithcode.com/paper/linear-and-deformable-image-registration-with |
| Repo | |
| Framework | |
On Low-Resolution Face Recognition in the Wild: Comparisons and New Techniques
| Title | On Low-Resolution Face Recognition in the Wild: Comparisons and New Techniques |
| Authors | Pei Li, Loreto Prieto, Domingo Mery, Patrick Flynn |
| Abstract | Although face recognition systems have achieved impressive performance in recent years, the low-resolution face recognition (LRFR) task remains challenging, especially when the LR faces are captured under non-ideal conditions, as is common in surveillance-based applications. Faces captured in such conditions are often contaminated by blur, nonuniform lighting, and nonfrontal face pose. In this paper, we analyze face recognition techniques using data captured under low-quality conditions in the wild. We provide a comprehensive analysis of experimental results for two of the most important applications in real surveillance applications, and demonstrate practical approaches to handle both cases that show promising performance. The following three contributions are made: {\em (i)} we conduct experiments to evaluate super-resolution methods for low-resolution face recognition; {\em (ii)} we study face re-identification on various public face datasets including real surveillance and low-resolution subsets of large-scale datasets, present a baseline result for several deep learning based approaches, and improve them by introducing a GAN pre-training approach and fully convolutional architecture; and {\em (iii)} we explore low-resolution face identification by employing a state-of-the-art supervised discriminative learning approach. Evaluations are conducted on challenging portions of the SCFace and UCCSface datasets. |
| Tasks | Face Identification, Face Recognition, Super-Resolution |
| Published | 2018-05-29 |
| URL | http://arxiv.org/abs/1805.11529v2 |
| http://arxiv.org/pdf/1805.11529v2.pdf | |
| PWC | https://paperswithcode.com/paper/low-resolution-face-recognition-in-the-wild |
| Repo | |
| Framework | |
A Deep Face Identification Network Enhanced by Facial Attributes Prediction
| Title | A Deep Face Identification Network Enhanced by Facial Attributes Prediction |
| Authors | Fariborz Taherkhani, Nasser M. Nasrabadi, Jeremy Dawson |
| Abstract | In this paper, we propose a new deep framework which predicts facial attributes and leverage it as a soft modality to improve face identification performance. Our model is an end to end framework which consists of a convolutional neural network (CNN) whose output is fanned out into two separate branches; the first branch predicts facial attributes while the second branch identifies face images. Contrary to the existing multi-task methods which only use a shared CNN feature space to train these two tasks jointly, we fuse the predicted attributes with the features from the face modality in order to improve the face identification performance. Experimental results show that our model brings benefits to both face identification as well as facial attribute prediction performance, especially in the case of identity facial attributes such as gender prediction. We tested our model on two standard datasets annotated by identities and face attributes. Experimental results indicate that the proposed model outperforms most of the current existing face identification and attribute prediction methods. |
| Tasks | Face Identification, Gender Prediction |
| Published | 2018-04-20 |
| URL | http://arxiv.org/abs/1805.00324v1 |
| http://arxiv.org/pdf/1805.00324v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-deep-face-identification-network-enhanced |
| Repo | |
| Framework | |
Working Memory Networks: Augmenting Memory Networks with a Relational Reasoning Module
| Title | Working Memory Networks: Augmenting Memory Networks with a Relational Reasoning Module |
| Authors | Juan Pavez, Héctor Allende, Héctor Allende-Cid |
| Abstract | During the last years, there has been a lot of interest in achieving some kind of complex reasoning using deep neural networks. To do that, models like Memory Networks (MemNNs) have combined external memory storages and attention mechanisms. These architectures, however, lack of more complex reasoning mechanisms that could allow, for instance, relational reasoning. Relation Networks (RNs), on the other hand, have shown outstanding results in relational reasoning tasks. Unfortunately, their computational cost grows quadratically with the number of memories, something prohibitive for larger problems. To solve these issues, we introduce the Working Memory Network, a MemNN architecture with a novel working memory storage and reasoning module. Our model retains the relational reasoning abilities of the RN while reducing its computational complexity from quadratic to linear. We tested our model on the text QA dataset bAbI and the visual QA dataset NLVR. In the jointly trained bAbI-10k, we set a new state-of-the-art, achieving a mean error of less than 0.5%. Moreover, a simple ensemble of two of our models solves all 20 tasks in the joint version of the benchmark. |
| Tasks | Relational Reasoning |
| Published | 2018-05-23 |
| URL | http://arxiv.org/abs/1805.09354v1 |
| http://arxiv.org/pdf/1805.09354v1.pdf | |
| PWC | https://paperswithcode.com/paper/working-memory-networks-augmenting-memory |
| Repo | |
| Framework | |
Adversarial Training in Affective Computing and Sentiment Analysis: Recent Advances and Perspectives
| Title | Adversarial Training in Affective Computing and Sentiment Analysis: Recent Advances and Perspectives |
| Authors | Jing Han, Zixing Zhang, Nicholas Cummins, Björn Schuller |
| Abstract | Over the past few years, adversarial training has become an extremely active research topic and has been successfully applied to various Artificial Intelligence (AI) domains. As a potentially crucial technique for the development of the next generation of emotional AI systems, we herein provide a comprehensive overview of the application of adversarial training to affective computing and sentiment analysis. Various representative adversarial training algorithms are explained and discussed accordingly, aimed at tackling diverse challenges associated with emotional AI systems. Further, we highlight a range of potential future research directions. We expect that this overview will help facilitate the development of adversarial training for affective computing and sentiment analysis in both the academic and industrial communities. |
| Tasks | Sentiment Analysis |
| Published | 2018-09-21 |
| URL | http://arxiv.org/abs/1809.08927v1 |
| http://arxiv.org/pdf/1809.08927v1.pdf | |
| PWC | https://paperswithcode.com/paper/adversarial-training-in-affective-computing |
| Repo | |
| Framework | |
Generating Neural Networks with Neural Networks
| Title | Generating Neural Networks with Neural Networks |
| Authors | Lior Deutsch |
| Abstract | Hypernetworks are neural networks that generate weights for another neural network. We formulate the hypernetwork training objective as a compromise between accuracy and diversity, where the diversity takes into account trivial symmetry transformations of the target network. We explain how this simple formulation generalizes variational inference. We use multi-layered perceptrons to form the mapping from the low dimensional input random vector to the high dimensional weight space, and demonstrate how to reduce the number of parameters in this mapping by parameter sharing. We perform experiments and show that the generated weights are diverse and lie on a non-trivial manifold. |
| Tasks | |
| Published | 2018-01-06 |
| URL | http://arxiv.org/abs/1801.01952v4 |
| http://arxiv.org/pdf/1801.01952v4.pdf | |
| PWC | https://paperswithcode.com/paper/generating-neural-networks-with-neural |
| Repo | |
| Framework | |
Machine Learning in Compiler Optimisation
| Title | Machine Learning in Compiler Optimisation |
| Authors | Zheng Wang, Michael O’Boyle |
| Abstract | In the last decade, machine learning based compilation has moved from an an obscure research niche to a mainstream activity. In this article, we describe the relationship between machine learning and compiler optimisation and introduce the main concepts of features, models, training and deployment. We then provide a comprehensive survey and provide a road map for the wide variety of different research areas. We conclude with a discussion on open issues in the area and potential research directions. This paper provides both an accessible introduction to the fast moving area of machine learning based compilation and a detailed bibliography of its main achievements. |
| Tasks | |
| Published | 2018-05-09 |
| URL | http://arxiv.org/abs/1805.03441v1 |
| http://arxiv.org/pdf/1805.03441v1.pdf | |
| PWC | https://paperswithcode.com/paper/machine-learning-in-compiler-optimisation |
| Repo | |
| Framework | |
An efficient K -means clustering algorithm for massive data
| Title | An efficient K -means clustering algorithm for massive data |
| Authors | Marco Capó, Aritz Pérez, Jose A. Lozano |
| Abstract | The analysis of continously larger datasets is a task of major importance in a wide variety of scientific fields. In this sense, cluster analysis algorithms are a key element of exploratory data analysis, due to their easiness in the implementation and relatively low computational cost. Among these algorithms, the K -means algorithm stands out as the most popular approach, besides its high dependency on the initial conditions, as well as to the fact that it might not scale well on massive datasets. In this article, we propose a recursive and parallel approximation to the K -means algorithm that scales well on both the number of instances and dimensionality of the problem, without affecting the quality of the approximation. In order to achieve this, instead of analyzing the entire dataset, we work on small weighted sets of points that mostly intend to extract information from those regions where it is harder to determine the correct cluster assignment of the original instances. In addition to different theoretical properties, which deduce the reasoning behind the algorithm, experimental results indicate that our method outperforms the state-of-the-art in terms of the trade-off between number of distance computations and the quality of the solution obtained. |
| Tasks | |
| Published | 2018-01-09 |
| URL | http://arxiv.org/abs/1801.02949v1 |
| http://arxiv.org/pdf/1801.02949v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-efficient-k-means-clustering-algorithm-for |
| Repo | |
| Framework | |
