Paper Group ANR 249
Combining Weakly and Webly Supervised Learning for Classifying Food Images. A Framework for Enriching Lexical Semantic Resources with Distributional Semantics. On Loss Functions for Deep Neural Networks in Classification. Predictive modeling of die filling of the pharmaceutical granules using the flexible neural tree. Cheshire: An Online Algorithm …
Combining Weakly and Webly Supervised Learning for Classifying Food Images
| Title | Combining Weakly and Webly Supervised Learning for Classifying Food Images |
| Authors | Parneet Kaur, Karan Sikka, Ajay Divakaran |
| Abstract | Food classification from images is a fine-grained classification problem. Manual curation of food images is cost, time and scalability prohibitive. On the other hand, web data is available freely but contains noise. In this paper, we address the problem of classifying food images with minimal data curation. We also tackle a key problems with food images from the web where they often have multiple cooccuring food types but are weakly labeled with a single label. We first demonstrate that by sequentially adding a few manually curated samples to a larger uncurated dataset from two web sources, the top-1 classification accuracy increases from 50.3% to 72.8%. To tackle the issue of weak labels, we augment the deep model with Weakly Supervised learning (WSL) that results in an increase in performance to 76.2%. Finally, we show some qualitative results to provide insights into the performance improvements using the proposed ideas. |
| Tasks | |
| Published | 2017-12-23 |
| URL | http://arxiv.org/abs/1712.08730v1 |
| http://arxiv.org/pdf/1712.08730v1.pdf | |
| PWC | https://paperswithcode.com/paper/combining-weakly-and-webly-supervised |
| Repo | |
| Framework | |
A Framework for Enriching Lexical Semantic Resources with Distributional Semantics
| Title | A Framework for Enriching Lexical Semantic Resources with Distributional Semantics |
| Authors | Chris Biemann, Stefano Faralli, Alexander Panchenko, Simone Paolo Ponzetto |
| Abstract | We present an approach to combining distributional semantic representations induced from text corpora with manually constructed lexical-semantic networks. While both kinds of semantic resources are available with high lexical coverage, our aligned resource combines the domain specificity and availability of contextual information from distributional models with the conciseness and high quality of manually crafted lexical networks. We start with a distributional representation of induced senses of vocabulary terms, which are accompanied with rich context information given by related lexical items. We then automatically disambiguate such representations to obtain a full-fledged proto-conceptualization, i.e. a typed graph of induced word senses. In a final step, this proto-conceptualization is aligned to a lexical ontology, resulting in a hybrid aligned resource. Moreover, unmapped induced senses are associated with a semantic type in order to connect them to the core resource. Manual evaluations against ground-truth judgments for different stages of our method as well as an extrinsic evaluation on a knowledge-based Word Sense Disambiguation benchmark all indicate the high quality of the new hybrid resource. Additionally, we show the benefits of enriching top-down lexical knowledge resources with bottom-up distributional information from text for addressing high-end knowledge acquisition tasks such as cleaning hypernym graphs and learning taxonomies from scratch. |
| Tasks | Word Sense Disambiguation |
| Published | 2017-12-23 |
| URL | http://arxiv.org/abs/1712.08819v1 |
| http://arxiv.org/pdf/1712.08819v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-framework-for-enriching-lexical-semantic |
| Repo | |
| Framework | |
On Loss Functions for Deep Neural Networks in Classification
| Title | On Loss Functions for Deep Neural Networks in Classification |
| Authors | Katarzyna Janocha, Wojciech Marian Czarnecki |
| Abstract | Deep neural networks are currently among the most commonly used classifiers. Despite easily achieving very good performance, one of the best selling points of these models is their modular design - one can conveniently adapt their architecture to specific needs, change connectivity patterns, attach specialised layers, experiment with a large amount of activation functions, normalisation schemes and many others. While one can find impressively wide spread of various configurations of almost every aspect of the deep nets, one element is, in authors’ opinion, underrepresented - while solving classification problems, vast majority of papers and applications simply use log loss. In this paper we try to investigate how particular choices of loss functions affect deep models and their learning dynamics, as well as resulting classifiers robustness to various effects. We perform experiments on classical datasets, as well as provide some additional, theoretical insights into the problem. In particular we show that L1 and L2 losses are, quite surprisingly, justified classification objectives for deep nets, by providing probabilistic interpretation in terms of expected misclassification. We also introduce two losses which are not typically used as deep nets objectives and show that they are viable alternatives to the existing ones. |
| Tasks | |
| Published | 2017-02-18 |
| URL | http://arxiv.org/abs/1702.05659v1 |
| http://arxiv.org/pdf/1702.05659v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-loss-functions-for-deep-neural-networks-in |
| Repo | |
| Framework | |
Predictive modeling of die filling of the pharmaceutical granules using the flexible neural tree
| Title | Predictive modeling of die filling of the pharmaceutical granules using the flexible neural tree |
| Authors | Varun Kumar Ojha, Serena Schiano, Chuan-Yu Wu, Václav Snášel, Ajith Abraham |
| Abstract | In this work, a computational intelligence (CI) technique named flexible neural tree (FNT) was developed to predict die filling performance of pharmaceutical granules and to identify significant die filling process variables. FNT resembles feedforward neural network, which creates a tree-like structure by using genetic programming. To improve accuracy, FNT parameters were optimized by using differential evolution algorithm. The performance of the FNT-based CI model was evaluated and compared with other CI techniques: multilayer perceptron, Gaussian process regression, and reduced error pruning tree. The accuracy of the CI model was evaluated experimentally using die filling as a case study. The die filling experiments were performed using a model shoe system and three different grades of microcrystalline cellulose (MCC) powders (MCC PH 101, MCC PH 102, and MCC DG). The feed powders were roll-compacted and milled into granules. The granules were then sieved into samples of various size classes. The mass of granules deposited into the die at different shoe speeds was measured. From these experiments, a dataset consisting true density, mean diameter (d50), granule size, and shoe speed as the inputs and the deposited mass as the output was generated. Cross-validation (CV) methods such as 10FCV and 5x2FCV were applied to develop and to validate the predictive models. It was found that the FNT-based CI model (for both CV methods) performed much better than other CI models. Additionally, it was observed that process variables such as the granule size and the shoe speed had a higher impact on the predictability than that of the powder property such as d50. Furthermore, validation of model prediction with experimental data showed that the die filling behavior of coarse granules could be better predicted than that of fine granules. |
| Tasks | |
| Published | 2017-05-16 |
| URL | http://arxiv.org/abs/1709.04318v1 |
| http://arxiv.org/pdf/1709.04318v1.pdf | |
| PWC | https://paperswithcode.com/paper/predictive-modeling-of-die-filling-of-the |
| Repo | |
| Framework | |
Cheshire: An Online Algorithm for Activity Maximization in Social Networks
| Title | Cheshire: An Online Algorithm for Activity Maximization in Social Networks |
| Authors | Ali Zarezade, Abir De, Hamid Rabiee, Manuel Gomez Rodriguez |
| Abstract | User engagement in social networks depends critically on the number of online actions their users take in the network. Can we design an algorithm that finds when to incentivize users to take actions to maximize the overall activity in a social network? In this paper, we model the number of online actions over time using multidimensional Hawkes processes, derive an alternate representation of these processes based on stochastic differential equations (SDEs) with jumps and, exploiting this alternate representation, address the above question from the perspective of stochastic optimal control of SDEs with jumps. We find that the optimal level of incentivized actions depends linearly on the current level of overall actions. Moreover, the coefficients of this linear relationship can be found by solving a matrix Riccati differential equation, which can be solved efficiently, and a first order differential equation, which has a closed form solution. As a result, we are able to design an efficient online algorithm, Cheshire, to sample the optimal times of the users’ incentivized actions. Experiments on both synthetic and real data gathered from Twitter show that our algorithm is able to consistently maximize the number of online actions more effectively than the state of the art. |
| Tasks | |
| Published | 2017-03-06 |
| URL | http://arxiv.org/abs/1703.02059v1 |
| http://arxiv.org/pdf/1703.02059v1.pdf | |
| PWC | https://paperswithcode.com/paper/cheshire-an-online-algorithm-for-activity |
| Repo | |
| Framework | |
Gene Ontology (GO) Prediction using Machine Learning Methods
| Title | Gene Ontology (GO) Prediction using Machine Learning Methods |
| Authors | Haoze Wu, Yangyu Zhou |
| Abstract | We applied machine learning to predict whether a gene is involved in axon regeneration. We extracted 31 features from different databases and trained five machine learning models. Our optimal model, a Random Forest Classifier with 50 submodels, yielded a test score of 85.71%, which is 4.1% higher than the baseline score. We concluded that our models have some predictive capability. Similar methodology and features could be applied to predict other Gene Ontology (GO) terms. |
| Tasks | |
| Published | 2017-10-30 |
| URL | https://arxiv.org/abs/1711.00001v2 |
| https://arxiv.org/pdf/1711.00001v2.pdf | |
| PWC | https://paperswithcode.com/paper/gene-ontology-go-prediction-using-machine |
| Repo | |
| Framework | |
Prior matters: simple and general methods for evaluating and improving topic quality in topic modeling
| Title | Prior matters: simple and general methods for evaluating and improving topic quality in topic modeling |
| Authors | Angela Fan, Finale Doshi-Velez, Luke Miratrix |
| Abstract | Latent Dirichlet Allocation (LDA) models trained without stopword removal often produce topics with high posterior probabilities on uninformative words, obscuring the underlying corpus content. Even when canonical stopwords are manually removed, uninformative words common in that corpus will still dominate the most probable words in a topic. In this work, we first show how the standard topic quality measures of coherence and pointwise mutual information act counter-intuitively in the presence of common but irrelevant words, making it difficult to even quantitatively identify situations in which topics may be dominated by stopwords. We propose an additional topic quality metric that targets the stopword problem, and show that it, unlike the standard measures, correctly correlates with human judgements of quality. We also propose a simple-to-implement strategy for generating topics that are evaluated to be of much higher quality by both human assessment and our new metric. This approach, a collection of informative priors easily introduced into most LDA-style inference methods, automatically promotes terms with domain relevance and demotes domain-specific stop words. We demonstrate this approach’s effectiveness in three very different domains: Department of Labor accident reports, online health forum posts, and NIPS abstracts. Overall we find that current practices thought to solve this problem do not do so adequately, and that our proposal offers a substantial improvement for those interested in interpreting their topics as objects in their own right. |
| Tasks | |
| Published | 2017-01-12 |
| URL | http://arxiv.org/abs/1701.03227v3 |
| http://arxiv.org/pdf/1701.03227v3.pdf | |
| PWC | https://paperswithcode.com/paper/prior-matters-simple-and-general-methods-for |
| Repo | |
| Framework | |
Denoising Adversarial Autoencoders
| Title | Denoising Adversarial Autoencoders |
| Authors | Antonia Creswell, Anil Anthony Bharath |
| Abstract | Unsupervised learning is of growing interest because it unlocks the potential held in vast amounts of unlabelled data to learn useful representations for inference. Autoencoders, a form of generative model, may be trained by learning to reconstruct unlabelled input data from a latent representation space. More robust representations may be produced by an autoencoder if it learns to recover clean input samples from corrupted ones. Representations may be further improved by introducing regularisation during training to shape the distribution of the encoded data in latent space. We suggest denoising adversarial autoencoders, which combine denoising and regularisation, shaping the distribution of latent space using adversarial training. We introduce a novel analysis that shows how denoising may be incorporated into the training and sampling of adversarial autoencoders. Experiments are performed to assess the contributions that denoising makes to the learning of representations for classification and sample synthesis. Our results suggest that autoencoders trained using a denoising criterion achieve higher classification performance, and can synthesise samples that are more consistent with the input data than those trained without a corruption process. |
| Tasks | Denoising |
| Published | 2017-03-03 |
| URL | http://arxiv.org/abs/1703.01220v4 |
| http://arxiv.org/pdf/1703.01220v4.pdf | |
| PWC | https://paperswithcode.com/paper/denoising-adversarial-autoencoders |
| Repo | |
| Framework | |
Instance Flow Based Online Multiple Object Tracking
| Title | Instance Flow Based Online Multiple Object Tracking |
| Authors | Sebastian Bullinger, Christoph Bodensteiner, Michael Arens |
| Abstract | We present a method to perform online Multiple Object Tracking (MOT) of known object categories in monocular video data. Current Tracking-by-Detection MOT approaches build on top of 2D bounding box detections. In contrast, we exploit state-of-the-art instance aware semantic segmentation techniques to compute 2D shape representations of target objects in each frame. We predict position and shape of segmented instances in subsequent frames by exploiting optical flow cues. We define an affinity matrix between instances of subsequent frames which reflects locality and visual similarity. The instance association is solved by applying the Hungarian method. We evaluate different configurations of our algorithm using the MOT 2D 2015 train dataset. The evaluation shows that our tracking approach is able to track objects with high relative motions. In addition, we provide results of our approach on the MOT 2D 2015 test set for comparison with previous works. We achieve a MOTA score of 32.1. |
| Tasks | Multiple Object Tracking, Object Tracking, Optical Flow Estimation, Semantic Segmentation |
| Published | 2017-03-03 |
| URL | http://arxiv.org/abs/1703.01289v2 |
| http://arxiv.org/pdf/1703.01289v2.pdf | |
| PWC | https://paperswithcode.com/paper/instance-flow-based-online-multiple-object |
| Repo | |
| Framework | |
Nonparametric Marginal Analysis of Recurrent Events Data under Competing Risks
| Title | Nonparametric Marginal Analysis of Recurrent Events Data under Competing Risks |
| Authors | Bowen Li |
| Abstract | This project was motivated by a dialysis study in northern Taiwan. Dialysis patients, after shunt implantation, may experience two types (“acute” or “non-acute”) of shunt thrombosis, both of which may recur. We formulate the problem under the framework of recurrent events data in the presence of competing risks. In particular we focus on marginal inference for the gap time variable of specific type. The functions of interest are the cumulative incidence function and cause-specific hazard function. The major challenge of nonparametric inference is the problem of induced dependent censoring. We apply the technique of inverse probability of censoring weighting (IPCW) to adjust for the selection bias. Besides point estimation, we apply the bootstrap re-sampling method for further inference. Large sample properties of the proposed estimators are derived. Simulations are performed to examine the finite-sample performances of the proposed methods. Finally we apply the proposed methodology to analyze the dialysis data. |
| Tasks | |
| Published | 2017-07-06 |
| URL | http://arxiv.org/abs/1707.01822v1 |
| http://arxiv.org/pdf/1707.01822v1.pdf | |
| PWC | https://paperswithcode.com/paper/nonparametric-marginal-analysis-of-recurrent |
| Repo | |
| Framework | |
Turkish PoS Tagging by Reducing Sparsity with Morpheme Tags in Small Datasets
| Title | Turkish PoS Tagging by Reducing Sparsity with Morpheme Tags in Small Datasets |
| Authors | Burcu Can, Ahmet Üstün, Murathan Kurfalı |
| Abstract | Sparsity is one of the major problems in natural language processing. The problem becomes even more severe in agglutinating languages that are highly prone to be inflected. We deal with sparsity in Turkish by adopting morphological features for part-of-speech tagging. We learn inflectional and derivational morpheme tags in Turkish by using conditional random fields (CRF) and we employ the morpheme tags in part-of-speech (PoS) tagging by using hidden Markov models (HMMs) to mitigate sparsity. Results show that using morpheme tags in PoS tagging helps alleviate the sparsity in emission probabilities. Our model outperforms other hidden Markov model based PoS tagging models for small training datasets in Turkish. We obtain an accuracy of 94.1% in morpheme tagging and 89.2% in PoS tagging on a 5K training dataset. |
| Tasks | Part-Of-Speech Tagging |
| Published | 2017-03-09 |
| URL | http://arxiv.org/abs/1703.03200v2 |
| http://arxiv.org/pdf/1703.03200v2.pdf | |
| PWC | https://paperswithcode.com/paper/turkish-pos-tagging-by-reducing-sparsity-with |
| Repo | |
| Framework | |
Optimization Beyond the Convolution: Generalizing Spatial Relations with End-to-End Metric Learning
| Title | Optimization Beyond the Convolution: Generalizing Spatial Relations with End-to-End Metric Learning |
| Authors | Philipp Jund, Andreas Eitel, Nichola Abdo, Wolfram Burgard |
| Abstract | To operate intelligently in domestic environments, robots require the ability to understand arbitrary spatial relations between objects and to generalize them to objects of varying sizes and shapes. In this work, we present a novel end-to-end approach to generalize spatial relations based on distance metric learning. We train a neural network to transform 3D point clouds of objects to a metric space that captures the similarity of the depicted spatial relations, using only geometric models of the objects. Our approach employs gradient-based optimization to compute object poses in order to imitate an arbitrary target relation by reducing the distance to it under the learned metric. Our results based on simulated and real-world experiments show that the proposed method enables robots to generalize spatial relations to unknown objects over a continuous spectrum. |
| Tasks | Metric Learning |
| Published | 2017-07-04 |
| URL | https://arxiv.org/abs/1707.00893v4 |
| https://arxiv.org/pdf/1707.00893v4.pdf | |
| PWC | https://paperswithcode.com/paper/optimization-beyond-the-convolution |
| Repo | |
| Framework | |
Consensus-Based Transfer Linear Support Vector Machines for Decentralized Multi-Task Multi-Agent Learning
| Title | Consensus-Based Transfer Linear Support Vector Machines for Decentralized Multi-Task Multi-Agent Learning |
| Authors | Rui Zhang, Quanyan Zhu |
| Abstract | Transfer learning has been developed to improve the performances of different but related tasks in machine learning. However, such processes become less efficient with the increase of the size of training data and the number of tasks. Moreover, privacy can be violated as some tasks may contain sensitive and private data, which are communicated between nodes and tasks. We propose a consensus-based distributed transfer learning framework, where several tasks aim to find the best linear support vector machine (SVM) classifiers in a distributed network. With alternating direction method of multipliers, tasks can achieve better classification accuracies more efficiently and privately, as each node and each task train with their own data, and only decision variables are transferred between different tasks and nodes. Numerical experiments on MNIST datasets show that the knowledge transferred from the source tasks can be used to decrease the risks of the target tasks that lack training data or have unbalanced training labels. We show that the risks of the target tasks in the nodes without the data of the source tasks can also be reduced using the information transferred from the nodes who contain the data of the source tasks. We also show that the target tasks can enter and leave in real-time without rerunning the whole algorithm. |
| Tasks | Transfer Learning |
| Published | 2017-06-15 |
| URL | http://arxiv.org/abs/1706.05039v2 |
| http://arxiv.org/pdf/1706.05039v2.pdf | |
| PWC | https://paperswithcode.com/paper/consensus-based-transfer-linear-support |
| Repo | |
| Framework | |
Image2song: Song Retrieval via Bridging Image Content and Lyric Words
| Title | Image2song: Song Retrieval via Bridging Image Content and Lyric Words |
| Authors | Xuelong Li, Di Hu, Xiaoqiang Lu |
| Abstract | Image is usually taken for expressing some kinds of emotions or purposes, such as love, celebrating Christmas. There is another better way that combines the image and relevant song to amplify the expression, which has drawn much attention in the social network recently. Hence, the automatic selection of songs should be expected. In this paper, we propose to retrieve semantic relevant songs just by an image query, which is named as the image2song problem. Motivated by the requirements of establishing correlation in semantic/content, we build a semantic-based song retrieval framework, which learns the correlation between image content and lyric words. This model uses a convolutional neural network to generate rich tags from image regions, a recurrent neural network to model lyric, and then establishes correlation via a multi-layer perceptron. To reduce the content gap between image and lyric, we propose to make the lyric modeling focus on the main image content via a tag attention. We collect a dataset from the social-sharing multimodal data to study the proposed problem, which consists of (image, music clip, lyric) triplets. We demonstrate that our proposed model shows noticeable results in the image2song retrieval task and provides suitable songs. Besides, the song2image task is also performed. |
| Tasks | |
| Published | 2017-08-19 |
| URL | http://arxiv.org/abs/1708.05851v1 |
| http://arxiv.org/pdf/1708.05851v1.pdf | |
| PWC | https://paperswithcode.com/paper/image2song-song-retrieval-via-bridging-image |
| Repo | |
| Framework | |
Multi-view Regularized Gaussian Processes
| Title | Multi-view Regularized Gaussian Processes |
| Authors | Qiuyang Liu, Shiliang Sun |
| Abstract | Gaussian processes (GPs) have been proven to be powerful tools in various areas of machine learning. However, there are very few applications of GPs in the scenario of multi-view learning. In this paper, we present a new GP model for multi-view learning. Unlike existing methods, it combines multiple views by regularizing marginal likelihood with the consistency among the posterior distributions of latent functions from different views. Moreover, we give a general point selection scheme for multi-view learning and improve the proposed model by this criterion. Experimental results on multiple real world data sets have verified the effectiveness of the proposed model and witnessed the performance improvement through employing this novel point selection scheme. |
| Tasks | Gaussian Processes, MULTI-VIEW LEARNING |
| Published | 2017-01-17 |
| URL | http://arxiv.org/abs/1701.04532v1 |
| http://arxiv.org/pdf/1701.04532v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-view-regularized-gaussian-processes |
| Repo | |
| Framework | |
