Paper Group ANR 215
Semi and Weakly Supervised Semantic Segmentation Using Generative Adversarial Network. Phonetic Temporal Neural Model for Language Identification. Sampling and multilevel coarsening algorithms for fast matrix approximations. Path-Based Spectral Clustering: Guarantees, Robustness to Outliers, and Fast Algorithms. Where to Focus: Deep Attention-based …
Semi and Weakly Supervised Semantic Segmentation Using Generative Adversarial Network
| Title | Semi and Weakly Supervised Semantic Segmentation Using Generative Adversarial Network |
| Authors | Nasim Souly, Concetto Spampinato, Mubarak Shah |
| Abstract | Semantic segmentation has been a long standing challenging task in computer vision. It aims at assigning a label to each image pixel and needs significant number of pixellevel annotated data, which is often unavailable. To address this lack, in this paper, we leverage, on one hand, massive amount of available unlabeled or weakly labeled data, and on the other hand, non-real images created through Generative Adversarial Networks. In particular, we propose a semi-supervised framework ,based on Generative Adversarial Networks (GANs), which consists of a generator network to provide extra training examples to a multi-class classifier, acting as discriminator in the GAN framework, that assigns sample a label y from the K possible classes or marks it as a fake sample (extra class). The underlying idea is that adding large fake visual data forces real samples to be close in the feature space, enabling a bottom-up clustering process, which, in turn, improves multiclass pixel classification. To ensure higher quality of generated images for GANs with consequent improved pixel classification, we extend the above framework by adding weakly annotated data, i.e., we provide class level information to the generator. We tested our approaches on several challenging benchmarking visual datasets, i.e. PASCAL, SiftFLow, Stanford and CamVid, achieving competitive performance also compared to state-of-the-art semantic segmentation method |
| Tasks | Semantic Segmentation, Weakly-Supervised Semantic Segmentation |
| Published | 2017-03-28 |
| URL | http://arxiv.org/abs/1703.09695v1 |
| http://arxiv.org/pdf/1703.09695v1.pdf | |
| PWC | https://paperswithcode.com/paper/semi-and-weakly-supervised-semantic |
| Repo | |
| Framework | |
Phonetic Temporal Neural Model for Language Identification
| Title | Phonetic Temporal Neural Model for Language Identification |
| Authors | Zhiyuan Tang, Dong Wang, Yixiang Chen, Lantian Li, Andrew Abel |
| Abstract | Deep neural models, particularly the LSTM-RNN model, have shown great potential for language identification (LID). However, the use of phonetic information has been largely overlooked by most existing neural LID methods, although this information has been used very successfully in conventional phonetic LID systems. We present a phonetic temporal neural model for LID, which is an LSTM-RNN LID system that accepts phonetic features produced by a phone-discriminative DNN as the input, rather than raw acoustic features. This new model is similar to traditional phonetic LID methods, but the phonetic knowledge here is much richer: it is at the frame level and involves compacted information of all phones. Our experiments conducted on the Babel database and the AP16-OLR database demonstrate that the temporal phonetic neural approach is very effective, and significantly outperforms existing acoustic neural models. It also outperforms the conventional i-vector approach on short utterances and in noisy conditions. |
| Tasks | Language Identification |
| Published | 2017-05-09 |
| URL | http://arxiv.org/abs/1705.03151v3 |
| http://arxiv.org/pdf/1705.03151v3.pdf | |
| PWC | https://paperswithcode.com/paper/phonetic-temporal-neural-model-for-language |
| Repo | |
| Framework | |
Sampling and multilevel coarsening algorithms for fast matrix approximations
| Title | Sampling and multilevel coarsening algorithms for fast matrix approximations |
| Authors | Shashanka Ubaru, Yousef Saad |
| Abstract | This paper addresses matrix approximation problems for matrices that are large, sparse and/or that are representations of large graphs. To tackle these problems, we consider algorithms that are based primarily on coarsening techniques, possibly combined with random sampling. A multilevel coarsening technique is proposed which utilizes a hypergraph associated with the data matrix and a graph coarsening strategy based on column matching. Theoretical results are established that characterize the quality of the dimension reduction achieved by a coarsening step, when a proper column matching strategy is employed. We consider a number of standard applications of this technique as well as a few new ones. Among the standard applications we first consider the problem of computing the partial SVD for which a combination of sampling and coarsening yields significantly improved SVD results relative to sampling alone. We also consider the Column subset selection problem, a popular low rank approximation method used in data related applications, and show how multilevel coarsening can be adapted for this problem. Similarly, we consider the problem of graph sparsification and show how coarsening techniques can be employed to solve it. Numerical experiments illustrate the performances of the methods in various applications. |
| Tasks | Dimensionality Reduction |
| Published | 2017-11-01 |
| URL | http://arxiv.org/abs/1711.00439v2 |
| http://arxiv.org/pdf/1711.00439v2.pdf | |
| PWC | https://paperswithcode.com/paper/sampling-and-multilevel-coarsening-algorithms |
| Repo | |
| Framework | |
Path-Based Spectral Clustering: Guarantees, Robustness to Outliers, and Fast Algorithms
| Title | Path-Based Spectral Clustering: Guarantees, Robustness to Outliers, and Fast Algorithms |
| Authors | Anna Little, Mauro Maggioni, James M. Murphy |
| Abstract | We consider the problem of clustering with the longest-leg path distance (LLPD) metric, which is informative for elongated and irregularly shaped clusters. We prove finite-sample guarantees on the performance of clustering with respect to this metric when random samples are drawn from multiple intrinsically low-dimensional clusters in high-dimensional space, in the presence of a large number of high-dimensional outliers. By combining these results with spectral clustering with respect to LLPD, we provide conditions under which the Laplacian eigengap statistic correctly determines the number of clusters for a large class of data sets, and prove guarantees on the labeling accuracy of the proposed algorithm. Our methods are quite general and provide performance guarantees for spectral clustering with any ultrametric. We also introduce an efficient, easy to implement approximation algorithm for the LLPD based on a multiscale analysis of adjacency graphs, which allows for the runtime of LLPD spectral clustering to be quasilinear in the number of data points. |
| Tasks | |
| Published | 2017-12-17 |
| URL | http://arxiv.org/abs/1712.06206v2 |
| http://arxiv.org/pdf/1712.06206v2.pdf | |
| PWC | https://paperswithcode.com/paper/path-based-spectral-clustering-guarantees |
| Repo | |
| Framework | |
Where to Focus: Deep Attention-based Spatially Recurrent Bilinear Networks for Fine-Grained Visual Recognition
| Title | Where to Focus: Deep Attention-based Spatially Recurrent Bilinear Networks for Fine-Grained Visual Recognition |
| Authors | Lin Wu, Yang Wang |
| Abstract | Fine-grained visual recognition typically depends on modeling subtle difference from object parts. However, these parts often exhibit dramatic visual variations such as occlusions, viewpoints, and spatial transformations, making it hard to detect. In this paper, we present a novel attention-based model to automatically, selectively and accurately focus on critical object regions with higher importance against appearance variations. Given an image, two different Convolutional Neural Networks (CNNs) are constructed, where the outputs of two CNNs are correlated through bilinear pooling to simultaneously focus on discriminative regions and extract relevant features. To capture spatial distributions among the local regions with visual attention, soft attention based spatial Long-Short Term Memory units (LSTMs) are incorporated to realize spatially recurrent yet visually selective over local input patterns. All the above intuitions equip our network with the following novel model: two-stream CNN layers, bilinear pooling layer, spatial recurrent layer with location attention are jointly trained via an end-to-end fashion to serve as the part detector and feature extractor, whereby relevant features are localized and extracted attentively. We show the significance of our network against two well-known visual recognition tasks: fine-grained image classification and person re-identification. |
| Tasks | Deep Attention, Fine-Grained Image Classification, Fine-Grained Visual Recognition, Image Classification, Person Re-Identification |
| Published | 2017-09-18 |
| URL | http://arxiv.org/abs/1709.05769v1 |
| http://arxiv.org/pdf/1709.05769v1.pdf | |
| PWC | https://paperswithcode.com/paper/where-to-focus-deep-attention-based-spatially |
| Repo | |
| Framework | |
Information Pursuit: A Bayesian Framework for Sequential Scene Parsing
| Title | Information Pursuit: A Bayesian Framework for Sequential Scene Parsing |
| Authors | Ehsan Jahangiri, Erdem Yoruk, Rene Vidal, Laurent Younes, Donald Geman |
| Abstract | Despite enormous progress in object detection and classification, the problem of incorporating expected contextual relationships among object instances into modern recognition systems remains a key challenge. In this work we propose Information Pursuit, a Bayesian framework for scene parsing that combines prior models for the geometry of the scene and the spatial arrangement of objects instances with a data model for the output of high-level image classifiers trained to answer specific questions about the scene. In the proposed framework, the scene interpretation is progressively refined as evidence accumulates from the answers to a sequence of questions. At each step, we choose the question to maximize the mutual information between the new answer and the full interpretation given the current evidence obtained from previous inquiries. We also propose a method for learning the parameters of the model from synthesized, annotated scenes obtained by top-down sampling from an easy-to-learn generative scene model. Finally, we introduce a database of annotated indoor scenes of dining room tables, which we use to evaluate the proposed approach. |
| Tasks | Object Detection, Scene Parsing |
| Published | 2017-01-09 |
| URL | http://arxiv.org/abs/1701.02343v1 |
| http://arxiv.org/pdf/1701.02343v1.pdf | |
| PWC | https://paperswithcode.com/paper/information-pursuit-a-bayesian-framework-for |
| Repo | |
| Framework | |
Convolutional Sparse Representations with Gradient Penalties
| Title | Convolutional Sparse Representations with Gradient Penalties |
| Authors | Brendt Wohlberg |
| Abstract | While convolutional sparse representations enjoy a number of useful properties, they have received limited attention for image reconstruction problems. The present paper compares the performance of block-based and convolutional sparse representations in the removal of Gaussian white noise. While the usual formulation of the convolutional sparse coding problem is slightly inferior to the block-based representations in this problem, the performance of the convolutional form can be boosted beyond that of the block-based form by the inclusion of suitable penalties on the gradients of the coefficient maps. |
| Tasks | Image Reconstruction |
| Published | 2017-05-12 |
| URL | http://arxiv.org/abs/1705.04407v2 |
| http://arxiv.org/pdf/1705.04407v2.pdf | |
| PWC | https://paperswithcode.com/paper/convolutional-sparse-representations-with |
| Repo | |
| Framework | |
Group-sparse block PCA and explained variance
| Title | Group-sparse block PCA and explained variance |
| Authors | Marie Chavent, Guy Chavent |
| Abstract | The paper addresses the simultneous determination of goup-sparse loadings by block optimization, and the correlated problem of defining explained variance for a set of non orthogonal components. We give in both cases a comprehensive mathematical presentation of the problem, which leads to propose i) a new formulation/algorithm for group-sparse block PCA and ii) a framework for the definition of explained variance with the analysis of five definitions. The numerical results i) confirm the superiority of block optimization over deflation for the determination of group-sparse loadings, and the importance of group information when available, and ii) show that ranking of algorithms according to explained variance is essentially independant of the definition of explained variance. These results lead to propose a new optimal variance as the definition of choice for explained variance. |
| Tasks | |
| Published | 2017-05-01 |
| URL | http://arxiv.org/abs/1705.00461v1 |
| http://arxiv.org/pdf/1705.00461v1.pdf | |
| PWC | https://paperswithcode.com/paper/group-sparse-block-pca-and-explained-variance |
| Repo | |
| Framework | |
Inspiring Computer Vision System Solutions
| Title | Inspiring Computer Vision System Solutions |
| Authors | Julian Zilly, Amit Boyarski, Micael Carvalho, Amir Atapour Abarghouei, Konstantinos Amplianitis, Aleksandr Krasnov, Massimiliano Mancini, Hernán Gonzalez, Riccardo Spezialetti, Carlos Sampedro Pérez, Hao Li |
| Abstract | The “digital Michelangelo project” was a seminal computer vision project in the early 2000’s that pushed the capabilities of acquisition systems and involved multiple people from diverse fields, many of whom are now leaders in industry and academia. Reviewing this project with modern eyes provides us with the opportunity to reflect on several issues, relevant now as then to the field of computer vision and research in general, that go beyond the technical aspects of the work. This article was written in the context of a reading group competition at the week-long International Computer Vision Summer School 2017 (ICVSS) on Sicily, Italy. To deepen the participants understanding of computer vision and to foster a sense of community, various reading groups were tasked to highlight important lessons which may be learned from provided literature, going beyond the contents of the paper. This report is the winning entry of this guided discourse (Fig. 1). The authors closely examined the origins, fruits and most importantly lessons about research in general which may be distilled from the “digital Michelangelo project”. Discussions leading to this report were held within the group as well as with Hao Li, the group mentor. |
| Tasks | |
| Published | 2017-07-22 |
| URL | http://arxiv.org/abs/1707.07210v1 |
| http://arxiv.org/pdf/1707.07210v1.pdf | |
| PWC | https://paperswithcode.com/paper/inspiring-computer-vision-system-solutions |
| Repo | |
| Framework | |
Integer Factorization with a Neuromorphic Sieve
| Title | Integer Factorization with a Neuromorphic Sieve |
| Authors | John V. Monaco, Manuel M. Vindiola |
| Abstract | The bound to factor large integers is dominated by the computational effort to discover numbers that are smooth, typically performed by sieving a polynomial sequence. On a von Neumann architecture, sieving has log-log amortized time complexity to check each value for smoothness. This work presents a neuromorphic sieve that achieves a constant time check for smoothness by exploiting two characteristic properties of neuromorphic architectures: constant time synaptic integration and massively parallel computation. The approach is validated by modifying msieve, one of the fastest publicly available integer factorization implementations, to use the IBM Neurosynaptic System (NS1e) as a coprocessor for the sieving stage. |
| Tasks | |
| Published | 2017-03-10 |
| URL | http://arxiv.org/abs/1703.03768v2 |
| http://arxiv.org/pdf/1703.03768v2.pdf | |
| PWC | https://paperswithcode.com/paper/integer-factorization-with-a-neuromorphic |
| Repo | |
| Framework | |
Declarative Sequential Pattern Mining of Care Pathways
| Title | Declarative Sequential Pattern Mining of Care Pathways |
| Authors | Thomas Guyet, André Happe, Yann Dauxais |
| Abstract | Sequential pattern mining algorithms are widely used to explore care pathways database, but they generate a deluge of patterns, mostly redundant or useless. Clinicians need tools to express complex mining queries in order to generate less but more significant patterns. These algorithms are not versatile enough to answer complex clinician queries. This article proposes to apply a declarative pattern mining approach based on Answer Set Programming paradigm. It is exemplified by a pharmaco-epidemiological study investigating the possible association between hospitalization for seizure and antiepileptic drug switch from a french medico-administrative database. |
| Tasks | Sequential Pattern Mining |
| Published | 2017-07-26 |
| URL | http://arxiv.org/abs/1707.08342v1 |
| http://arxiv.org/pdf/1707.08342v1.pdf | |
| PWC | https://paperswithcode.com/paper/declarative-sequential-pattern-mining-of-care |
| Repo | |
| Framework | |
Sparse Named Entity Classification using Factorization Machines
| Title | Sparse Named Entity Classification using Factorization Machines |
| Authors | Ai Hirata, Mamoru Komachi |
| Abstract | Named entity classification is the task of classifying text-based elements into various categories, including places, names, dates, times, and monetary values. A bottleneck in named entity classification, however, is the data problem of sparseness, because new named entities continually emerge, making it rather difficult to maintain a dictionary for named entity classification. Thus, in this paper, we address the problem of named entity classification using matrix factorization to overcome the problem of feature sparsity. Experimental results show that our proposed model, with fewer features and a smaller size, achieves competitive accuracy to state-of-the-art models. |
| Tasks | |
| Published | 2017-03-15 |
| URL | http://arxiv.org/abs/1703.04879v1 |
| http://arxiv.org/pdf/1703.04879v1.pdf | |
| PWC | https://paperswithcode.com/paper/sparse-named-entity-classification-using |
| Repo | |
| Framework | |
Compact Environment-Invariant Codes for Robust Visual Place Recognition
| Title | Compact Environment-Invariant Codes for Robust Visual Place Recognition |
| Authors | Unnat Jain, Vinay P. Namboodiri, Gaurav Pandey |
| Abstract | Robust visual place recognition (VPR) requires scene representations that are invariant to various environmental challenges such as seasonal changes and variations due to ambient lighting conditions during day and night. Moreover, a practical VPR system necessitates compact representations of environmental features. To satisfy these requirements, in this paper we suggest a modification to the existing pipeline of VPR systems to incorporate supervised hashing. The modified system learns (in a supervised setting) compact binary codes from image feature descriptors. These binary codes imbibe robustness to the visual variations exposed to it during the training phase, thereby, making the system adaptive to severe environmental changes. Also, incorporating supervised hashing makes VPR computationally more efficient and easy to implement on simple hardware. This is because binary embeddings can be learned over simple-to-compute features and the distance computation is also in the low-dimensional hamming space of binary codes. We have performed experiments on several challenging data sets covering seasonal, illumination and viewpoint variations. We also compare two widely used supervised hashing methods of CCAITQ and MLH and show that this new pipeline out-performs or closely matches the state-of-the-art deep learning VPR methods that are based on high-dimensional features extracted from pre-trained deep convolutional neural networks. |
| Tasks | Visual Place Recognition |
| Published | 2017-09-23 |
| URL | http://arxiv.org/abs/1709.08103v1 |
| http://arxiv.org/pdf/1709.08103v1.pdf | |
| PWC | https://paperswithcode.com/paper/compact-environment-invariant-codes-for |
| Repo | |
| Framework | |
Compression-aware Training of Deep Networks
| Title | Compression-aware Training of Deep Networks |
| Authors | Jose M. Alvarez, Mathieu Salzmann |
| Abstract | In recent years, great progress has been made in a variety of application domains thanks to the development of increasingly deeper neural networks. Unfortunately, the huge number of units of these networks makes them expensive both computationally and memory-wise. To overcome this, exploiting the fact that deep networks are over-parametrized, several compression strategies have been proposed. These methods, however, typically start from a network that has been trained in a standard manner, without considering such a future compression. In this paper, we propose to explicitly account for compression in the training process. To this end, we introduce a regularizer that encourages the parameter matrix of each layer to have low rank during training. We show that accounting for compression during training allows us to learn much more compact, yet at least as effective, models than state-of-the-art compression techniques. |
| Tasks | |
| Published | 2017-11-07 |
| URL | http://arxiv.org/abs/1711.02638v2 |
| http://arxiv.org/pdf/1711.02638v2.pdf | |
| PWC | https://paperswithcode.com/paper/compression-aware-training-of-deep-networks |
| Repo | |
| Framework | |
Connecting Software Metrics across Versions to Predict Defects
| Title | Connecting Software Metrics across Versions to Predict Defects |
| Authors | Yibin Liu, Yanhui Li, Jianbo Guo, Yuming Zhou, Baowen Xu |
| Abstract | Accurate software defect prediction could help software practitioners allocate test resources to defect-prone modules effectively and efficiently. In the last decades, much effort has been devoted to build accurate defect prediction models, including developing quality defect predictors and modeling techniques. However, current widely used defect predictors such as code metrics and process metrics could not well describe how software modules change over the project evolution, which we believe is important for defect prediction. In order to deal with this problem, in this paper, we propose to use the Historical Version Sequence of Metrics (HVSM) in continuous software versions as defect predictors. Furthermore, we leverage Recurrent Neural Network (RNN), a popular modeling technique, to take HVSM as the input to build software prediction models. The experimental results show that, in most cases, the proposed HVSM-based RNN model has a significantly better effort-aware ranking effectiveness than the commonly used baseline models. |
| Tasks | |
| Published | 2017-12-28 |
| URL | http://arxiv.org/abs/1712.09835v1 |
| http://arxiv.org/pdf/1712.09835v1.pdf | |
| PWC | https://paperswithcode.com/paper/connecting-software-metrics-across-versions |
| Repo | |
| Framework | |
