Paper Group ANR 299
Valid Simultaneous Inference in High-Dimensional Settings (with the hdm package for R). No-Reference Color Image Quality Assessment: From Entropy to Perceptual Quality. A Library for Constraint Consistent Learning. Comparing approaches for mitigating intergroup variability in personality recognition. The Distribution of Reversible Functions is Norm …
Valid Simultaneous Inference in High-Dimensional Settings (with the hdm package for R)
| Title | Valid Simultaneous Inference in High-Dimensional Settings (with the hdm package for R) |
| Authors | Philipp Bach, Victor Chernozhukov, Martin Spindler |
| Abstract | Due to the increasing availability of high-dimensional empirical applications in many research disciplines, valid simultaneous inference becomes more and more important. For instance, high-dimensional settings might arise in economic studies due to very rich data sets with many potential covariates or in the analysis of treatment heterogeneities. Also the evaluation of potentially more complicated (non-linear) functional forms of the regression relationship leads to many potential variables for which simultaneous inferential statements might be of interest. Here we provide a review of classical and modern methods for simultaneous inference in (high-dimensional) settings and illustrate their use by a case study using the R package hdm. The R package hdm implements valid joint powerful and efficient hypothesis tests for a potentially large number of coeffcients as well as the construction of simultaneous confidence intervals and, therefore, provides useful methods to perform valid post-selection inference based on the LASSO. |
| Tasks | |
| Published | 2018-09-13 |
| URL | http://arxiv.org/abs/1809.04951v1 |
| http://arxiv.org/pdf/1809.04951v1.pdf | |
| PWC | https://paperswithcode.com/paper/valid-simultaneous-inference-in-high |
| Repo | |
| Framework | |
No-Reference Color Image Quality Assessment: From Entropy to Perceptual Quality
| Title | No-Reference Color Image Quality Assessment: From Entropy to Perceptual Quality |
| Authors | Xiaoqiao Chen, Qingyi Zhang, Manhui Lin, Guangyi Yang, Chu He |
| Abstract | This paper presents a high-performance general-purpose no-reference (NR) image quality assessment (IQA) method based on image entropy. The image features are extracted from two domains. In the spatial domain, the mutual information between the color channels and the two-dimensional entropy are calculated. In the frequency domain, the two-dimensional entropy and the mutual information of the filtered sub-band images are computed as the feature set of the input color image. Then, with all the extracted features, the support vector classifier (SVC) for distortion classification and support vector regression (SVR) are utilized for the quality prediction, to obtain the final quality assessment score. The proposed method, which we call entropy-based no-reference image quality assessment (ENIQA), can assess the quality of different categories of distorted images, and has a low complexity. The proposed ENIQA method was assessed on the LIVE and TID2013 databases and showed a superior performance. The experimental results confirmed that the proposed ENIQA method has a high consistency of objective and subjective assessment on color images, which indicates the good overall performance and generalization ability of ENIQA. The source code is available on github https://github.com/jacob6/ENIQA. |
| Tasks | Image Quality Assessment, No-Reference Image Quality Assessment |
| Published | 2018-12-27 |
| URL | http://arxiv.org/abs/1812.10695v1 |
| http://arxiv.org/pdf/1812.10695v1.pdf | |
| PWC | https://paperswithcode.com/paper/no-reference-color-image-quality-assessment |
| Repo | |
| Framework | |
A Library for Constraint Consistent Learning
| Title | A Library for Constraint Consistent Learning |
| Authors | Yuchen Zhao, Jeevan Manavalan, Prabhakar Ray, Hsiu-Chin Lin, Matthew Howard |
| Abstract | This paper introduces the first, open source software library for Constraint Consistent Learning (CCL). It implements a family of data-driven methods that are capable of (i) learning state-independent and -dependent constraints, (ii) decomposing the behaviour of redundant systems into task- and null-space parts, and (iii) uncovering the underlying null space control policy. It is a tool to analyse and decompose many everyday tasks, such as wiping, reaching and drawing. The library also includes several tutorials that demonstrate its use with both simulated and real world data in a systematic way. This paper documents the implementation of the library, tutorials and associated helper methods. The software is made freely available to the community, to enable code reuse and allow users to gain in-depth experience in statistical learning in this area. |
| Tasks | |
| Published | 2018-07-12 |
| URL | https://arxiv.org/abs/1807.04676v2 |
| https://arxiv.org/pdf/1807.04676v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-library-for-constraint-consistent-learning |
| Repo | |
| Framework | |
Comparing approaches for mitigating intergroup variability in personality recognition
| Title | Comparing approaches for mitigating intergroup variability in personality recognition |
| Authors | Guozhen An, Rivka Levitan |
| Abstract | Personality have been found to predict many life outcomes, and there have been huge interests on automatic personality recognition from a speaker’s utterance. Previously, we achieved accuracies between 37%-44% for three-way classification of high, medium or low for each of the Big Five personality traits (Openness to Experience, Conscientiousness, Extraversion, Agreeableness, Neuroticism). We show here that we can improve performance on this task by accounting for heterogeneity of gender and L1 in our data, which has English speech from female and male native speakers of Chinese and Standard American English (SAE). We experiment with personalizing models by L1 and gender and normalizing features by speaker, L1 group, and/or gender. |
| Tasks | |
| Published | 2018-01-31 |
| URL | http://arxiv.org/abs/1802.01405v1 |
| http://arxiv.org/pdf/1802.01405v1.pdf | |
| PWC | https://paperswithcode.com/paper/comparing-approaches-for-mitigating |
| Repo | |
| Framework | |
The Distribution of Reversible Functions is Normal
| Title | The Distribution of Reversible Functions is Normal |
| Authors | W. B. Langdon |
| Abstract | The distribution of reversible programs tends to a limit as their size increases. For problems with a Hamming distance fitness function the limiting distribution is binomial with an exponentially small chance (but non~zero) chance of perfect solution. Sufficiently good reversible circuits are more common. Expected RMS error is also calculated. Random unitary matrices may suggest possible extension to quantum computing. Using the genetic programming (GP) benchmark, the six multiplexor, circuits of Toffoli gates are shown to give a fitness landscape amenable to evolutionary search. Minimal CCNOT solutions to the six multiplexer are found but larger circuits are more evolvable. |
| Tasks | |
| Published | 2018-08-18 |
| URL | http://arxiv.org/abs/1808.06928v1 |
| http://arxiv.org/pdf/1808.06928v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-distribution-of-reversible-functions-is |
| Repo | |
| Framework | |
How to augment a small learning set for improving the performances of a CNN-based steganalyzer?
| Title | How to augment a small learning set for improving the performances of a CNN-based steganalyzer? |
| Authors | Mehdi Yedroudj, Marc Chaumont, Frédéric Comby |
| Abstract | Deep learning and convolutional neural networks (CNN) have been intensively used in many image processing topics during last years. As far as steganalysis is concerned, the use of CNN allows reaching the state-of-the-art results. The performances of such networks often rely on the size of their learning database. An obvious preliminary assumption could be considering that “the bigger a database is, the better the results are”. However, it appears that cautions have to be taken when increasing the database size if one desire to improve the classification accuracy i.e. enhance the steganalysis efficiency. To our knowledge, no study has been performed on the enrichment impact of a learning database on the steganalysis performance. What kind of images can be added to the initial learning set? What are the sensitive criteria: the camera models used for acquiring the images, the treatments applied to the images, the cameras proportions in the database, etc? This article continues the work carried out in a previous paper, and explores the ways to improve the performances of CNN. It aims at studying the effects of “base augmentation” on the performance of steganalysis using a CNN. We present the results of this study using various experimental protocols and various databases to define the good practices in base augmentation for steganalysis. |
| Tasks | |
| Published | 2018-01-12 |
| URL | http://arxiv.org/abs/1801.04076v2 |
| http://arxiv.org/pdf/1801.04076v2.pdf | |
| PWC | https://paperswithcode.com/paper/how-to-augment-a-small-learning-set-for |
| Repo | |
| Framework | |
Direct Training for Spiking Neural Networks: Faster, Larger, Better
| Title | Direct Training for Spiking Neural Networks: Faster, Larger, Better |
| Authors | Yujie Wu, Lei Deng, Guoqi Li, Jun Zhu, Luping Shi |
| Abstract | Spiking neural networks (SNNs) that enables energy efficient implementation on emerging neuromorphic hardware are gaining more attention. Yet now, SNNs have not shown competitive performance compared with artificial neural networks (ANNs), due to the lack of effective learning algorithms and efficient programming frameworks. We address this issue from two aspects: (1) We propose a neuron normalization technique to adjust the neural selectivity and develop a direct learning algorithm for deep SNNs. (2) Via narrowing the rate coding window and converting the leaky integrate-and-fire (LIF) model into an explicitly iterative version, we present a Pytorch-based implementation method towards the training of large-scale SNNs. In this way, we are able to train deep SNNs with tens of times speedup. As a result, we achieve significantly better accuracy than the reported works on neuromorphic datasets (N-MNIST and DVS-CIFAR10), and comparable accuracy as existing ANNs and pre-trained SNNs on non-spiking datasets (CIFAR10). {To our best knowledge, this is the first work that demonstrates direct training of deep SNNs with high performance on CIFAR10, and the efficient implementation provides a new way to explore the potential of SNNs. |
| Tasks | |
| Published | 2018-09-16 |
| URL | http://arxiv.org/abs/1809.05793v2 |
| http://arxiv.org/pdf/1809.05793v2.pdf | |
| PWC | https://paperswithcode.com/paper/direct-training-for-spiking-neural-networks |
| Repo | |
| Framework | |
Representational Issues in the Debate on the Standard Model of the Mind
| Title | Representational Issues in the Debate on the Standard Model of the Mind |
| Authors | Antonio Chella, Marcello Frixione, Antonio Lieto |
| Abstract | In this paper we discuss some of the issues concerning the Memory and Content aspects in the recent debate on the identification of a Standard Model of the Mind (Laird, Lebiere, and Rosenbloom in press). In particular, we focus on the representational models concerning the Declarative Memories of current Cognitive Architectures (CAs). In doing so we outline some of the main problems affecting the current CAs and suggest that the Conceptual Spaces, a representational framework developed by Gardenfors, is worth-considering to address such problems. Finally, we briefly analyze the alternative representational assumptions employed in the three CAs constituting the current baseline for the Standard Model (i.e. SOAR, ACT-R and Sigma). In doing so, we point out the respective differences and discuss their implications in the light of the analyzed problems. |
| Tasks | |
| Published | 2018-04-23 |
| URL | http://arxiv.org/abs/1804.08299v1 |
| http://arxiv.org/pdf/1804.08299v1.pdf | |
| PWC | https://paperswithcode.com/paper/representational-issues-in-the-debate-on-the |
| Repo | |
| Framework | |
Scalable Deep $k$-Subspace Clustering
| Title | Scalable Deep $k$-Subspace Clustering |
| Authors | Tong Zhang, Pan Ji, Mehrtash Harandi, Richard Hartley, Ian Reid |
| Abstract | Subspace clustering algorithms are notorious for their scalability issues because building and processing large affinity matrices are demanding. In this paper, we introduce a method that simultaneously learns an embedding space along subspaces within it to minimize a notion of reconstruction error, thus addressing the problem of subspace clustering in an end-to-end learning paradigm. To achieve our goal, we propose a scheme to update subspaces within a deep neural network. This in turn frees us from the need of having an affinity matrix to perform clustering. Unlike previous attempts, our method can easily scale up to large datasets, making it unique in the context of unsupervised learning with deep architectures. Our experiments show that our method significantly improves the clustering accuracy while enjoying cheaper memory footprints. |
| Tasks | |
| Published | 2018-11-02 |
| URL | http://arxiv.org/abs/1811.01045v1 |
| http://arxiv.org/pdf/1811.01045v1.pdf | |
| PWC | https://paperswithcode.com/paper/scalable-deep-k-subspace-clustering |
| Repo | |
| Framework | |
Deep Learning Framework for Multi-class Breast Cancer Histology Image Classification
| Title | Deep Learning Framework for Multi-class Breast Cancer Histology Image Classification |
| Authors | Yeeleng S. Vang, Zhen Chen, Xiaohui Xie |
| Abstract | In this work, we present a deep learning framework for multi-class breast cancer image classification as our submission to the International Conference on Image Analysis and Recognition (ICIAR) 2018 Grand Challenge on BreAst Cancer Histology images (BACH). As these histology images are too large to fit into GPU memory, we first propose using Inception V3 to perform patch level classification. The patch level predictions are then passed through an ensemble fusion framework involving majority voting, gradient boosting machine (GBM), and logistic regression to obtain the image level prediction. We improve the sensitivity of the Normal and Benign predicted classes by designing a Dual Path Network (DPN) to be used as a feature extractor where these extracted features are further sent to a second layer of ensemble prediction fusion using GBM, logistic regression, and support vector machine (SVM) to refine predictions. Experimental results demonstrate our framework shows a 12.5$%$ improvement over the state-of-the-art model. |
| Tasks | Breast Cancer Histology Image Classification, Image Classification |
| Published | 2018-02-03 |
| URL | http://arxiv.org/abs/1802.00931v1 |
| http://arxiv.org/pdf/1802.00931v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-framework-for-multi-class |
| Repo | |
| Framework | |
Identifying the sentiment styles of YouTube’s vloggers
| Title | Identifying the sentiment styles of YouTube’s vloggers |
| Authors | Bennett Kleinberg, Maximilian Mozes, Isabelle van der Vegt |
| Abstract | Vlogs provide a rich public source of data in a novel setting. This paper examined the continuous sentiment styles employed in 27,333 vlogs using a dynamic intra-textual approach to sentiment analysis. Using unsupervised clustering, we identified seven distinct continuous sentiment trajectories characterized by fluctuations of sentiment throughout a vlog’s narrative time. We provide a taxonomy of these seven continuous sentiment styles and found that vlogs whose sentiment builds up towards a positive ending are the most prevalent in our sample. Gender was associated with preferences for different continuous sentiment trajectories. This paper discusses the findings with respect to previous work and concludes with an outlook towards possible uses of the corpus, method and findings of this paper for related areas of research. |
| Tasks | Sentiment Analysis |
| Published | 2018-08-29 |
| URL | http://arxiv.org/abs/1808.09722v1 |
| http://arxiv.org/pdf/1808.09722v1.pdf | |
| PWC | https://paperswithcode.com/paper/identifying-the-sentiment-styles-of-youtubes |
| Repo | |
| Framework | |
Iris Recognition After Death
| Title | Iris Recognition After Death |
| Authors | Mateusz Trokielewicz, Adam Czajka, Piotr Maciejewicz |
| Abstract | This paper presents a comprehensive study of post-mortem human iris recognition carried out for 1,200 near-infrared and 1,787 visible-light samples collected from 37 deceased individuals kept in the mortuary conditions. We used four independent iris recognition methods (three commercial and one academic) to analyze genuine and impostor comparison scores and check the dynamics of iris quality decay over a period of up to 814 hours after death. This study shows that post-mortem iris recognition may be close-to-perfect approximately 5 to 7 hours after death and occasionally is still viable even 21 days after death. These conclusions contradict the statements present in past literature that the iris is unusable as a biometrics shortly after death, and show that the dynamics of post-mortem changes to the iris that are important for biometric identification are more moderate than previously hypothesized. The paper contains a thorough medical commentary that helps to understand which post-mortem metamorphoses of the eye may impact the performance of automatic iris recognition. We also show that post-mortem iris recognition works equally well for images taken in near-infrared and when the red channel of visible-light sample is used. However, cross-wavelength matching presents significantly worse performance. This paper conforms to reproducible research and the database used in this study is made publicly available to facilitate research of post-mortem iris recognition. To our knowledge, this paper offers the most comprehensive evaluation of post-mortem iris recognition and the largest database of post-mortem iris images. |
| Tasks | Iris Recognition |
| Published | 2018-04-05 |
| URL | http://arxiv.org/abs/1804.01962v2 |
| http://arxiv.org/pdf/1804.01962v2.pdf | |
| PWC | https://paperswithcode.com/paper/iris-recognition-after-death |
| Repo | |
| Framework | |
Recurrent Fusion Network for Image Captioning
| Title | Recurrent Fusion Network for Image Captioning |
| Authors | Wenhao Jiang, Lin Ma, Yu-Gang Jiang, Wei Liu, Tong Zhang |
| Abstract | Recently, much advance has been made in image captioning, and an encoder-decoder framework has been adopted by all the state-of-the-art models. Under this framework, an input image is encoded by a convolutional neural network (CNN) and then translated into natural language with a recurrent neural network (RNN). The existing models counting on this framework merely employ one kind of CNNs, e.g., ResNet or Inception-X, which describe image contents from only one specific view point. Thus, the semantic meaning of an input image cannot be comprehensively understood, which restricts the performance of captioning. In this paper, in order to exploit the complementary information from multiple encoders, we propose a novel Recurrent Fusion Network (RFNet) for tackling image captioning. The fusion process in our model can exploit the interactions among the outputs of the image encoders and then generate new compact yet informative representations for the decoder. Experiments on the MSCOCO dataset demonstrate the effectiveness of our proposed RFNet, which sets a new state-of-the-art for image captioning. |
| Tasks | Image Captioning |
| Published | 2018-07-26 |
| URL | http://arxiv.org/abs/1807.09986v3 |
| http://arxiv.org/pdf/1807.09986v3.pdf | |
| PWC | https://paperswithcode.com/paper/recurrent-fusion-network-for-image-captioning |
| Repo | |
| Framework | |
Disentangling Multiple Conditional Inputs in GANs
| Title | Disentangling Multiple Conditional Inputs in GANs |
| Authors | Gökhan Yildirim, Calvin Seward, Urs Bergmann |
| Abstract | In this paper, we propose a method that disentangles the effects of multiple input conditions in Generative Adversarial Networks (GANs). In particular, we demonstrate our method in controlling color, texture, and shape of a generated garment image for computer-aided fashion design. To disentangle the effect of input attributes, we customize conditional GANs with consistency loss functions. In our experiments, we tune one input at a time and show that we can guide our network to generate novel and realistic images of clothing articles. In addition, we present a fashion design process that estimates the input attributes of an existing garment and modifies them using our generator. |
| Tasks | |
| Published | 2018-06-20 |
| URL | http://arxiv.org/abs/1806.07819v1 |
| http://arxiv.org/pdf/1806.07819v1.pdf | |
| PWC | https://paperswithcode.com/paper/disentangling-multiple-conditional-inputs-in |
| Repo | |
| Framework | |
Region Proposal Networks with Contextual Selective Attention for Real-Time Organ Detection
| Title | Region Proposal Networks with Contextual Selective Attention for Real-Time Organ Detection |
| Authors | Awais Mansoor, Antonio R. Porras, Marius George Linguraru |
| Abstract | State-of-the-art methods for object detection use region proposal networks (RPN) to hypothesize object location. These networks simultaneously predicts object bounding boxes and \emph{objectness} scores at each location in the image. Unlike natural images for which RPN algorithms were originally designed, most medical images are acquired following standard protocols, thus organs in the image are typically at a similar location and possess similar geometrical characteristics (e.g. scale, aspect-ratio, etc.). Therefore, medical image acquisition protocols hold critical localization and geometric information that can be incorporated for faster and more accurate detection. This paper presents a novel attention mechanism for the detection of organs by incorporating imaging protocol information. Our novel selective attention approach (i) effectively shrinks the search space inside the feature map, (ii) appends useful localization information to the hypothesized proposal for the detection architecture to learn where to look for each organ, and (iii) modifies the pyramid of regression references in the RPN by incorporating organ- and modality-specific information, which results in additional time reduction. We evaluated the proposed framework on a dataset of 768 chest X-ray images obtained from a diverse set of sources. Our results demonstrate superior performance for the detection of the lung field compared to the state-of-the-art, both in terms of detection accuracy, demonstrating an improvement of $>7%$ in Dice score, and reduced processing time by $27.53%$ due to fewer hypotheses. |
| Tasks | Object Detection, Organ Detection |
| Published | 2018-12-26 |
| URL | http://arxiv.org/abs/1812.10330v1 |
| http://arxiv.org/pdf/1812.10330v1.pdf | |
| PWC | https://paperswithcode.com/paper/region-proposal-networks-with-contextual |
| Repo | |
| Framework | |
