Paper Group ANR 940
Sequence-based Person Attribute Recognition with Joint CTC-Attention Model. Gaussian process classification using posterior linearisation. Bias Mitigation Post-processing for Individual and Group Fairness. Localization-Aware Active Learning for Object Detection. Singular Value Decomposition of Operators on Reproducing Kernel Hilbert Spaces. Multiba …
Sequence-based Person Attribute Recognition with Joint CTC-Attention Model
| Title | Sequence-based Person Attribute Recognition with Joint CTC-Attention Model |
| Authors | Hao Liu, Jingjing Wu, Jianguo Jiang, Meibin Qi, Bo Ren |
| Abstract | Attribute recognition has become crucial because of its wide applications in many computer vision tasks, such as person re-identification. Like many object recognition problems, variations in viewpoints, illumination, and recognition at far distance, all make this task challenging. In this work, we propose a joint CTC-Attention model (JCM), which maps attribute labels into sequences to learn the semantic relationship among attributes. Besides, this network uses neural network to encode images into sequences, and employs connectionist temporal classification (CTC) loss to train the network with the aim of improving the encoding performance of the network. At the same time, it adopts the attention model to decode the sequences, which can realize aligning the sequences and better learning the semantic information from attributes. Extensive experiments on three public datasets, i.e., Market-1501 attribute dataset, Duke attribute dataset and PETA dataset, demonstrate the effectiveness of the proposed method. |
| Tasks | Object Recognition, Person Re-Identification |
| Published | 2018-11-20 |
| URL | http://arxiv.org/abs/1811.08115v2 |
| http://arxiv.org/pdf/1811.08115v2.pdf | |
| PWC | https://paperswithcode.com/paper/sequence-based-person-attribute-recognition |
| Repo | |
| Framework | |
Gaussian process classification using posterior linearisation
| Title | Gaussian process classification using posterior linearisation |
| Authors | Ángel F. García-Fernández, Filip Tronarp, Simo Särkkä |
| Abstract | This paper proposes a new algorithm for Gaussian process classification based on posterior linearisation (PL). In PL, a Gaussian approximation to the posterior density is obtained iteratively using the best possible linearisation of the conditional mean of the labels and accounting for the linearisation error. PL has some theoretical advantages over expectation propagation (EP): all calculated covariance matrices are positive definite and there is a local convergence theorem. In experimental data, PL has better performance than EP with the noisy threshold likelihood and the parallel implementation of the algorithms. |
| Tasks | |
| Published | 2018-09-13 |
| URL | http://arxiv.org/abs/1809.04967v3 |
| http://arxiv.org/pdf/1809.04967v3.pdf | |
| PWC | https://paperswithcode.com/paper/gaussian-process-classification-using |
| Repo | |
| Framework | |
Bias Mitigation Post-processing for Individual and Group Fairness
| Title | Bias Mitigation Post-processing for Individual and Group Fairness |
| Authors | Pranay K. Lohia, Karthikeyan Natesan Ramamurthy, Manish Bhide, Diptikalyan Saha, Kush R. Varshney, Ruchir Puri |
| Abstract | Whereas previous post-processing approaches for increasing the fairness of predictions of biased classifiers address only group fairness, we propose a method for increasing both individual and group fairness. Our novel framework includes an individual bias detector used to prioritize data samples in a bias mitigation algorithm aiming to improve the group fairness measure of disparate impact. We show superior performance to previous work in the combination of classification accuracy, individual fairness and group fairness on several real-world datasets in applications such as credit, employment, and criminal justice. |
| Tasks | |
| Published | 2018-12-14 |
| URL | http://arxiv.org/abs/1812.06135v1 |
| http://arxiv.org/pdf/1812.06135v1.pdf | |
| PWC | https://paperswithcode.com/paper/bias-mitigation-post-processing-for |
| Repo | |
| Framework | |
Localization-Aware Active Learning for Object Detection
| Title | Localization-Aware Active Learning for Object Detection |
| Authors | Chieh-Chi Kao, Teng-Yok Lee, Pradeep Sen, Ming-Yu Liu |
| Abstract | Active learning - a class of algorithms that iteratively searches for the most informative samples to include in a training dataset - has been shown to be effective at annotating data for image classification. However, the use of active learning for object detection is still largely unexplored as determining informativeness of an object-location hypothesis is more difficult. In this paper, we address this issue and present two metrics for measuring the informativeness of an object hypothesis, which allow us to leverage active learning to reduce the amount of annotated data needed to achieve a target object detection performance. Our first metric measures ‘localization tightness’ of an object hypothesis, which is based on the overlapping ratio between the region proposal and the final prediction. Our second metric measures ‘localization stability’ of an object hypothesis, which is based on the variation of predicted object locations when input images are corrupted by noise. Our experimental results show that by augmenting a conventional active-learning algorithm designed for classification with the proposed metrics, the amount of labeled training data required can be reduced up to 25%. Moreover, on PASCAL 2007 and 2012 datasets our localization-stability method has an average relative improvement of 96.5% and 81.9% over the baseline method using classification only. |
| Tasks | Active Learning, Image Classification, Object Detection |
| Published | 2018-01-16 |
| URL | http://arxiv.org/abs/1801.05124v1 |
| http://arxiv.org/pdf/1801.05124v1.pdf | |
| PWC | https://paperswithcode.com/paper/localization-aware-active-learning-for-object |
| Repo | |
| Framework | |
Singular Value Decomposition of Operators on Reproducing Kernel Hilbert Spaces
| Title | Singular Value Decomposition of Operators on Reproducing Kernel Hilbert Spaces |
| Authors | Mattes Mollenhauer, Ingmar Schuster, Stefan Klus, Christof Schütte |
| Abstract | Reproducing kernel Hilbert spaces (RKHSs) play an important role in many statistics and machine learning applications ranging from support vector machines to Gaussian processes and kernel embeddings of distributions. Operators acting on such spaces are, for instance, required to embed conditional probability distributions in order to implement the kernel Bayes rule and build sequential data models. It was recently shown that transfer operators such as the Perron-Frobenius or Koopman operator can also be approximated in a similar fashion using covariance and cross-covariance operators and that eigenfunctions of these operators can be obtained by solving associated matrix eigenvalue problems. The goal of this paper is to provide a solid functional analytic foundation for the eigenvalue decomposition of RKHS operators and to extend the approach to the singular value decomposition. The results are illustrated with simple guiding examples. |
| Tasks | Gaussian Processes |
| Published | 2018-07-24 |
| URL | https://arxiv.org/abs/1807.09331v2 |
| https://arxiv.org/pdf/1807.09331v2.pdf | |
| PWC | https://paperswithcode.com/paper/singular-value-decomposition-of-operators-on |
| Repo | |
| Framework | |
Multiband SAS Imagery
| Title | Multiband SAS Imagery |
| Authors | Isaac D Gerg |
| Abstract | Advances in unmanned synthetic aperture sonar (SAS) imaging platforms allow for the simultaneous collection of multiband SAS imagery. The imagery is collected over several octaves and the phenomenology’s interactions with the sea floor vary greatly over this range – higher frequencies resolve proud and fine structure of the seafloor while lower frequencies resolve subsurface features and often induce internal resonance in man-made objects. Currently, analysts examine multiband imagery by viewing a single band at a time. This method makes it difficult to ascertain correlations between any pair of bands collected over the same location. To mitigate this issue, we propose methods which ingest high frequency (HF) and low frequency (LF) SAS imagery and generates a color composite creating what we call a multiband SAS (MSAS) image. The MSAS image contains the relevant portions of the HF and LF images required by an analyst to interpret the scene and are defined using a spatial saliency metric computed for each image. We then combine the saliency and acoustic backscatter measures to form the final MSAS image. |
| Tasks | |
| Published | 2018-08-08 |
| URL | http://arxiv.org/abs/1808.02792v1 |
| http://arxiv.org/pdf/1808.02792v1.pdf | |
| PWC | https://paperswithcode.com/paper/multiband-sas-imagery |
| Repo | |
| Framework | |
Spatial-Spectral Fusion by Combining Deep Learning and Variation Model
| Title | Spatial-Spectral Fusion by Combining Deep Learning and Variation Model |
| Authors | Huanfeng Shen, Menghui Jiang, Jie Li, Qiangqiang Yuan, Yanchong Wei, Liangpei Zhang |
| Abstract | In the field of spatial-spectral fusion, the model-based method and the deep learning (DL)-based method are state-of-the-art. This paper presents a fusion method that incorporates the deep neural network into the model-based method for the most common case in the spatial-spectral fusion: PAN/multispectral (MS) fusion. Specifically, we first map the gradient of the high spatial resolution panchromatic image (HR-PAN) and the low spatial resolution multispectral image (LR-MS) to the gradient of the high spatial resolution multispectral image (HR-MS) via a deep residual convolutional neural network (CNN). Then we construct a fusion framework by the LR-MS image, the gradient prior learned from the gradient network, and the ideal fused image. Finally, an iterative optimization algorithm is used to solve the fusion model. Both quantitative and visual assessments on high-quality images from various sources demonstrate that the proposed fusion method is superior to all the mainstream algorithms included in the comparison in terms of overall fusion accuracy. |
| Tasks | |
| Published | 2018-09-04 |
| URL | http://arxiv.org/abs/1809.00764v1 |
| http://arxiv.org/pdf/1809.00764v1.pdf | |
| PWC | https://paperswithcode.com/paper/spatial-spectral-fusion-by-combining-deep |
| Repo | |
| Framework | |
Life-Long Disentangled Representation Learning with Cross-Domain Latent Homologies
| Title | Life-Long Disentangled Representation Learning with Cross-Domain Latent Homologies |
| Authors | Alessandro Achille, Tom Eccles, Loic Matthey, Christopher P. Burgess, Nick Watters, Alexander Lerchner, Irina Higgins |
| Abstract | Intelligent behaviour in the real-world requires the ability to acquire new knowledge from an ongoing sequence of experiences while preserving and reusing past knowledge. We propose a novel algorithm for unsupervised representation learning from piece-wise stationary visual data: Variational Autoencoder with Shared Embeddings (VASE). Based on the Minimum Description Length principle, VASE automatically detects shifts in the data distribution and allocates spare representational capacity to new knowledge, while simultaneously protecting previously learnt representations from catastrophic forgetting. Our approach encourages the learnt representations to be disentangled, which imparts a number of desirable properties: VASE can deal sensibly with ambiguous inputs, it can enhance its own representations through imagination-based exploration, and most importantly, it exhibits semantically meaningful sharing of latents between different datasets. Compared to baselines with entangled representations, our approach is able to reason beyond surface-level statistics and perform semantically meaningful cross-domain inference. |
| Tasks | Representation Learning, Unsupervised Representation Learning |
| Published | 2018-08-20 |
| URL | http://arxiv.org/abs/1808.06508v1 |
| http://arxiv.org/pdf/1808.06508v1.pdf | |
| PWC | https://paperswithcode.com/paper/life-long-disentangled-representation |
| Repo | |
| Framework | |
Bayesian Distance Clustering
| Title | Bayesian Distance Clustering |
| Authors | Leo L Duan, David B Dunson |
| Abstract | Model-based clustering is widely-used in a variety of application areas. However, fundamental concerns remain about robustness. In particular, results can be sensitive to the choice of kernel representing the within-cluster data density. Leveraging on properties of pairwise differences between data points, we propose a class of Bayesian distance clustering methods, which rely on modeling the likelihood of the pairwise distances in place of the original data. Although some information in the data is discarded, we gain substantial robustness to modeling assumptions. The proposed approach represents an appealing middle ground between distance- and model-based clustering, drawing advantages from each of these canonical approaches. We illustrate dramatic gains in the ability to infer clusters that are not well represented by the usual choices of kernel. A simulation study is included to assess performance relative to competitors, and we apply the approach to clustering of brain genome expression data. Keywords: Distance-based clustering; Mixture model; Model-based clustering; Model misspecification; Pairwise distance matrix; Partial likelihood; Robustness. |
| Tasks | |
| Published | 2018-10-19 |
| URL | https://arxiv.org/abs/1810.08537v2 |
| https://arxiv.org/pdf/1810.08537v2.pdf | |
| PWC | https://paperswithcode.com/paper/bayesian-distance-clustering |
| Repo | |
| Framework | |
Model-free Training of End-to-end Communication Systems
| Title | Model-free Training of End-to-end Communication Systems |
| Authors | Fayçal Ait Aoudia, Jakob Hoydis |
| Abstract | The idea of end-to-end learning of communication systems through neural network-based autoencoders has the shortcoming that it requires a differentiable channel model. We present in this paper a novel learning algorithm which alleviates this problem. The algorithm enables training of communication systems with an unknown channel model or with non-differentiable components. It iterates between training of the receiver using the true gradient, and training of the transmitter using an approximation of the gradient. We show that this approach works as well as model-based training for a variety of channels and tasks. Moreover, we demonstrate the algorithm’s practical viability through hardware implementation on software-defined radios where it achieves state-of-the-art performance over a coaxial cable and wireless channel. |
| Tasks | |
| Published | 2018-12-14 |
| URL | https://arxiv.org/abs/1812.05929v3 |
| https://arxiv.org/pdf/1812.05929v3.pdf | |
| PWC | https://paperswithcode.com/paper/model-free-training-of-end-to-end |
| Repo | |
| Framework | |
TOMAAT: volumetric medical image analysis as a cloud service
| Title | TOMAAT: volumetric medical image analysis as a cloud service |
| Authors | Fausto Milletari, Johann Frei, Seyed-Ahmad Ahmadi |
| Abstract | Deep learning has been recently applied to a multitude of computer vision and medical image analysis problems. Although recent research efforts have improved the state of the art, most of the methods cannot be easily accessed, compared or used by either researchers or the general public. Researchers often publish their code and trained models on the internet, but this does not always enable these approaches to be easily used or integrated in stand-alone applications and existing workflows. In this paper we propose a framework which allows easy deployment and access of deep learning methods for segmentation through a cloud-based architecture. Our approach comprises three parts: a server, which wraps trained deep learning models and their pre- and post-processing data pipelines and makes them available on the cloud; a client which interfaces with the server to obtain predictions on user data; a service registry that informs clients about available prediction endpoints that are available in the cloud. These three parts constitute the open-source TOMAAT framework. |
| Tasks | |
| Published | 2018-03-19 |
| URL | http://arxiv.org/abs/1803.06784v2 |
| http://arxiv.org/pdf/1803.06784v2.pdf | |
| PWC | https://paperswithcode.com/paper/tomaat-volumetric-medical-image-analysis-as-a |
| Repo | |
| Framework | |
Multiple Manifold Clustering Using Curvature Constrained Path
| Title | Multiple Manifold Clustering Using Curvature Constrained Path |
| Authors | Amir Babaeian |
| Abstract | The problem of multiple surface clustering is a challenging task, particularly when the surfaces intersect. Available methods such as Isomap fail to capture the true shape of the surface nearby the intersection and result in incorrect clustering. The Isomap algorithm uses the shortest path between points. The main draw back of the shortest path algorithm is due to the lack of curvature constrained where causes to have a path between points on different surfaces. In this paper, we tackle this problem by imposing a curvature constraint to the shortest path algorithm used in Isomap. The algorithm chooses several landmark nodes at random and then checks whether there is a curvature constrained path between each landmark node and every other node in the neighbourhood graph. We build a binary feature vector for each point where each entry represents the connectivity of that point to a particular landmark. Then the binary feature vectors could be used as an input of conventional clustering algorithm such as hierarchical clustering. We apply our method to simulated and some real datasets and show, it performs comparably to the best methods such as K-manifold and spectral multi-manifold clustering. |
| Tasks | |
| Published | 2018-12-04 |
| URL | http://arxiv.org/abs/1812.02327v1 |
| http://arxiv.org/pdf/1812.02327v1.pdf | |
| PWC | https://paperswithcode.com/paper/multiple-manifold-clustering-using-curvature |
| Repo | |
| Framework | |
Learning associations between clinical information and motion-based descriptors using a large scale MR-derived cardiac motion atlas
| Title | Learning associations between clinical information and motion-based descriptors using a large scale MR-derived cardiac motion atlas |
| Authors | Esther Puyol-Anton, Bram Ruijsink, Helene Langet, Mathieu De Craene, Paolo Piro, Julia A. Schnabel, Andrew P. King |
| Abstract | The availability of large scale databases containing imaging and non-imaging data, such as the UK Biobank, represents an opportunity to improve our understanding of healthy and diseased bodily function. Cardiac motion atlases provide a space of reference in which the motion fields of a cohort of subjects can be directly compared. In this work, a cardiac motion atlas is built from cine MR data from the UK Biobank (~ 6000 subjects). Two automated quality control strategies are proposed to reject subjects with insufficient image quality. Based on the atlas, three dimensionality reduction algorithms are evaluated to learn data-driven cardiac motion descriptors, and statistical methods used to study the association between these descriptors and non-imaging data. Results show a positive correlation between the atlas motion descriptors and body fat percentage, basal metabolic rate, hypertension, smoking status and alcohol intake frequency. The proposed method outperforms the ability to identify changes in cardiac function due to these known cardiovascular risk factors compared to ejection fraction, the most commonly used descriptor of cardiac function. In conclusion, this work represents a framework for further investigation of the factors influencing cardiac health. |
| Tasks | Dimensionality Reduction |
| Published | 2018-07-27 |
| URL | http://arxiv.org/abs/1807.10653v1 |
| http://arxiv.org/pdf/1807.10653v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-associations-between-clinical |
| Repo | |
| Framework | |
Predicting County Level Corn Yields Using Deep Long Short Term Memory Models
| Title | Predicting County Level Corn Yields Using Deep Long Short Term Memory Models |
| Authors | Zehui Jiang, Chao Liu, Nathan P. Hendricks, Baskar Ganapathysubramanian, Dermot J. Hayes, Soumik Sarkar |
| Abstract | Corn yield prediction is beneficial as it provides valuable information about production and prices prior the harvest. Publicly available high-quality corn yield prediction can help address emergent information asymmetry problems and in doing so improve price efficiency in futures markets. This paper is the first to employ Long Short-Term Memory (LSTM), a special form of Recurrent Neural Network (RNN) method to predict corn yields. A cross sectional time series of county-level corn yield and hourly weather data made the sample space large enough to use deep learning technics. LSTM is efficient in time series prediction with complex inner relations, which makes it suitable for this task. The empirical results from county level data in Iowa show promising predictive power relative to existing survey based methods. |
| Tasks | Time Series, Time Series Prediction |
| Published | 2018-05-30 |
| URL | http://arxiv.org/abs/1805.12044v1 |
| http://arxiv.org/pdf/1805.12044v1.pdf | |
| PWC | https://paperswithcode.com/paper/predicting-county-level-corn-yields-using |
| Repo | |
| Framework | |
Random Fourier Features for Kernel Ridge Regression: Approximation Bounds and Statistical Guarantees
| Title | Random Fourier Features for Kernel Ridge Regression: Approximation Bounds and Statistical Guarantees |
| Authors | Haim Avron, Michael Kapralov, Cameron Musco, Christopher Musco, Ameya Velingker, Amir Zandieh |
| Abstract | Random Fourier features is one of the most popular techniques for scaling up kernel methods, such as kernel ridge regression. However, despite impressive empirical results, the statistical properties of random Fourier features are still not well understood. In this paper we take steps toward filling this gap. Specifically, we approach random Fourier features from a spectral matrix approximation point of view, give tight bounds on the number of Fourier features required to achieve a spectral approximation, and show how spectral matrix approximation bounds imply statistical guarantees for kernel ridge regression. Qualitatively, our results are twofold: on the one hand, we show that random Fourier feature approximation can provably speed up kernel ridge regression under reasonable assumptions. At the same time, we show that the method is suboptimal, and sampling from a modified distribution in Fourier space, given by the leverage function of the kernel, yields provably better performance. We study this optimal sampling distribution for the Gaussian kernel, achieving a nearly complete characterization for the case of low-dimensional bounded datasets. Based on this characterization, we propose an efficient sampling scheme with guarantees superior to random Fourier features in this regime. |
| Tasks | |
| Published | 2018-04-26 |
| URL | http://arxiv.org/abs/1804.09893v2 |
| http://arxiv.org/pdf/1804.09893v2.pdf | |
| PWC | https://paperswithcode.com/paper/random-fourier-features-for-kernel-ridge |
| Repo | |
| Framework | |
