Paper Group ANR 22
Gradient-based Representational Similarity Analysis with Searchlight for Analyzing fMRI Data. Coordinate-based Texture Inpainting for Pose-Guided Image Generation. A post-processing method to improve the white matter hyperintensity segmentation accuracy for randomly-initialized U-net. From Face Recognition to Models of Identity: A Bayesian Approach …
Gradient-based Representational Similarity Analysis with Searchlight for Analyzing fMRI Data
Title | Gradient-based Representational Similarity Analysis with Searchlight for Analyzing fMRI Data |
Authors | Xiaoliang Sheng, Muhammad Yousefnezhad, Tonglin Xu, Ning Yuan, Daoqiang Zhang |
Abstract | Representational Similarity Analysis (RSA) aims to explore similarities between neural activities of different stimuli. Classical RSA techniques employ the inverse of the covariance matrix to explore a linear model between the neural activities and task events. However, calculating the inverse of a large-scale covariance matrix is time-consuming and can reduce the stability and robustness of the final analysis. Notably, it becomes severe when the number of samples is too large. For facing this shortcoming, this paper proposes a novel RSA method called gradient-based RSA (GRSA). Moreover, the proposed method is not restricted to a linear model. In fact, there is a growing interest in finding more effective ways of using multi-subject and whole-brain fMRI data. Searchlight technique can extend RSA from the localized brain regions to the whole-brain regions with smaller memory footprint in each process. Based on Searchlight, we propose a new method called Spatiotemporal Searchlight GRSA (SSL-GRSA) that generalizes our ROI-based GRSA algorithm to the whole-brain data. Further, our approach can handle some computational challenges while dealing with large-scale, multi-subject fMRI data. Experimental studies on multi-subject datasets confirm that both proposed approaches achieve superior performance to other state-of-the-art RSA algorithms. |
Tasks | |
Published | 2018-09-12 |
URL | http://arxiv.org/abs/1809.04429v1 |
http://arxiv.org/pdf/1809.04429v1.pdf | |
PWC | https://paperswithcode.com/paper/gradient-based-representational-similarity |
Repo | |
Framework | |
Coordinate-based Texture Inpainting for Pose-Guided Image Generation
Title | Coordinate-based Texture Inpainting for Pose-Guided Image Generation |
Authors | Artur Grigorev, Artem Sevastopolsky, Alexander Vakhitov, Victor Lempitsky |
Abstract | We present a new deep learning approach to pose-guided resynthesis of human photographs. At the heart of the new approach is the estimation of the complete body surface texture based on a single photograph. Since the input photograph always observes only a part of the surface, we suggest a new inpainting method that completes the texture of the human body. Rather than working directly with colors of texture elements, the inpainting network estimates an appropriate source location in the input image for each element of the body surface. This correspondence field between the input image and the texture is then further warped into the target image coordinate frame based on the desired pose, effectively establishing the correspondence between the source and the target view even when the pose change is drastic. The final convolutional network then uses the established correspondence and all other available information to synthesize the output image. A fully-convolutional architecture with deformable skip connections guided by the estimated correspondence field is used. We show state-of-the-art result for pose-guided image synthesis. Additionally, we demonstrate the performance of our system for garment transfer and pose-guided face resynthesis. |
Tasks | Image Generation, Pose-Guided Image Generation |
Published | 2018-11-28 |
URL | https://arxiv.org/abs/1811.11459v2 |
https://arxiv.org/pdf/1811.11459v2.pdf | |
PWC | https://paperswithcode.com/paper/coordinate-based-texture-inpainting-for-pose |
Repo | |
Framework | |
A post-processing method to improve the white matter hyperintensity segmentation accuracy for randomly-initialized U-net
Title | A post-processing method to improve the white matter hyperintensity segmentation accuracy for randomly-initialized U-net |
Authors | Yue Zhang, Wanli Chen, Yifan Chen, Xiaoying Tang |
Abstract | White matter hyperintensity (WMH) is commonly found in elder individuals and appears to be associated with brain diseases. U-net is a convolutional network that has been widely used for biomedical image segmentation. Recently, U-net has been successfully applied to WMH segmentation. Random initialization is usally used to initialize the model weights in the U-net. However, the model may coverage to different local optima with different randomly initialized weights. We find a combination of thresholding and averaging the outputs of U-nets with different random initializations can largely improve the WMH segmentation accuracy. Based on this observation, we propose a post-processing technique concerning the way how averaging and thresholding are conducted. Specifically, we first transfer the score maps from three U-nets to binary masks via thresholding and then average those binary masks to obtain the final WMH segmentation. Both quantitative analysis (via the Dice similarity coefficient) and qualitative analysis (via visual examinations) reveal the superior performance of the proposed method. This post-processing technique is independent of the model used. As such, it can also be applied to situations where other deep learning models are employed, especially when random initialization is adopted and pre-training is unavailable. |
Tasks | Semantic Segmentation |
Published | 2018-07-21 |
URL | http://arxiv.org/abs/1807.10600v1 |
http://arxiv.org/pdf/1807.10600v1.pdf | |
PWC | https://paperswithcode.com/paper/a-post-processing-method-to-improve-the-white |
Repo | |
Framework | |
From Face Recognition to Models of Identity: A Bayesian Approach to Learning about Unknown Identities from Unsupervised Data
Title | From Face Recognition to Models of Identity: A Bayesian Approach to Learning about Unknown Identities from Unsupervised Data |
Authors | Daniel C. Castro, Sebastian Nowozin |
Abstract | Current face recognition systems robustly recognize identities across a wide variety of imaging conditions. In these systems recognition is performed via classification into known identities obtained from supervised identity annotations. There are two problems with this current paradigm: (1) current systems are unable to benefit from unlabelled data which may be available in large quantities; and (2) current systems equate successful recognition with labelling a given input image. Humans, on the other hand, regularly perform identification of individuals completely unsupervised, recognising the identity of someone they have seen before even without being able to name that individual. How can we go beyond the current classification paradigm towards a more human understanding of identities? We propose an integrated Bayesian model that coherently reasons about the observed images, identities, partial knowledge about names, and the situational context of each observation. While our model achieves good recognition performance against known identities, it can also discover new identities from unsupervised data and learns to associate identities with different contexts depending on which identities tend to be observed together. In addition, the proposed semi-supervised component is able to handle not only acquaintances, whose names are known, but also unlabelled familiar faces and complete strangers in a unified framework. |
Tasks | Face Recognition |
Published | 2018-07-20 |
URL | http://arxiv.org/abs/1807.07872v1 |
http://arxiv.org/pdf/1807.07872v1.pdf | |
PWC | https://paperswithcode.com/paper/from-face-recognition-to-models-of-identity-a |
Repo | |
Framework | |
A Hassle-Free Machine Learning Method for Cohort Selection of Clinical Trials
Title | A Hassle-Free Machine Learning Method for Cohort Selection of Clinical Trials |
Authors | Liu Man |
Abstract | Traditional text classification techniques in clinical domain have heavily relied on the manually extracted textual cues. This paper proposes a generally supervised machine learning method that is equally hassle-free and does not use clinical knowledge. The employed methods were simple to implement, fast to run and yet effective. This paper proposes a novel named entity recognition (NER) based an ensemble system capable of learning the keyword features in the document. Instead of merely considering the whole sentence/paragraph for analysis, the NER based keyword features can stress the important clinic relevant phases more. In addition, to capture the semantic information in the documents, the FastText features originating from the document level FastText classification results are exploited. |
Tasks | Named Entity Recognition, Text Classification |
Published | 2018-08-10 |
URL | http://arxiv.org/abs/1808.04694v1 |
http://arxiv.org/pdf/1808.04694v1.pdf | |
PWC | https://paperswithcode.com/paper/a-hassle-free-machine-learning-method-for |
Repo | |
Framework | |
Effect of Hyper-Parameter Optimization on the Deep Learning Model Proposed for Distributed Attack Detection in Internet of Things Environment
Title | Effect of Hyper-Parameter Optimization on the Deep Learning Model Proposed for Distributed Attack Detection in Internet of Things Environment |
Authors | Md Mohaimenuzzaman, Zahraa Said Abdallah, Joarder Kamruzzaman, Bala Srinivasan |
Abstract | This paper studies the effect of various hyper-parameters and their selection for the best performance of the deep learning model proposed in [1] for distributed attack detection in the Internet of Things (IoT). The findings show that there are three hyper-parameters that have more influence on the best performance achieved by the model. As a consequence, this study shows that the model’s accuracy as reported in the paper is not achievable, based on the best selections of parameters, which is also supported by another recent publication [2]. |
Tasks | |
Published | 2018-06-19 |
URL | http://arxiv.org/abs/1806.07057v1 |
http://arxiv.org/pdf/1806.07057v1.pdf | |
PWC | https://paperswithcode.com/paper/effect-of-hyper-parameter-optimization-on-the |
Repo | |
Framework | |
Improving Orbit Prediction Accuracy through Supervised Machine Learning
Title | Improving Orbit Prediction Accuracy through Supervised Machine Learning |
Authors | Hao Peng, Xiaoli Bai |
Abstract | Due to the lack of information such as the space environment condition and resident space objects’ (RSOs’) body characteristics, current orbit predictions that are solely grounded on physics-based models may fail to achieve required accuracy for collision avoidance and have led to satellite collisions already. This paper presents a methodology to predict RSOs’ trajectories with higher accuracy than that of the current methods. Inspired by the machine learning (ML) theory through which the models are learned based on large amounts of observed data and the prediction is conducted without explicitly modeling space objects and space environment, the proposed ML approach integrates physics-based orbit prediction algorithms with a learning-based process that focuses on reducing the prediction errors. Using a simulation-based space catalog environment as the test bed, the paper demonstrates three types of generalization capability for the proposed ML approach: 1) the ML model can be used to improve the same RSO’s orbit information that is not available during the learning process but shares the same time interval as the training data; 2) the ML model can be used to improve predictions of the same RSO at future epochs; and 3) the ML model based on a RSO can be applied to other RSOs that share some common features. |
Tasks | |
Published | 2018-01-15 |
URL | http://arxiv.org/abs/1801.04856v1 |
http://arxiv.org/pdf/1801.04856v1.pdf | |
PWC | https://paperswithcode.com/paper/improving-orbit-prediction-accuracy-through |
Repo | |
Framework | |
The Foundations of Deep Learning with a Path Towards General Intelligence
Title | The Foundations of Deep Learning with a Path Towards General Intelligence |
Authors | Eray Özkural |
Abstract | Like any field of empirical science, AI may be approached axiomatically. We formulate requirements for a general-purpose, human-level AI system in terms of postulates. We review the methodology of deep learning, examining the explicit and tacit assumptions in deep learning research. Deep Learning methodology seeks to overcome limitations in traditional machine learning research as it combines facets of model richness, generality, and practical applicability. The methodology so far has produced outstanding results due to a productive synergy of function approximation, under plausible assumptions of irreducibility and the efficiency of back-propagation family of algorithms. We examine these winning traits of deep learning, and also observe the various known failure modes of deep learning. We conclude by giving recommendations on how to extend deep learning methodology to cover the postulates of general-purpose AI including modularity, and cognitive architecture. We also relate deep learning to advances in theoretical neuroscience research. |
Tasks | |
Published | 2018-06-22 |
URL | http://arxiv.org/abs/1806.08874v1 |
http://arxiv.org/pdf/1806.08874v1.pdf | |
PWC | https://paperswithcode.com/paper/the-foundations-of-deep-learning-with-a-path |
Repo | |
Framework | |
A Two-Step Learning and Interpolation Method for Location-Based Channel Database
Title | A Two-Step Learning and Interpolation Method for Location-Based Channel Database |
Authors | Ruichen Deng, Zhiyuan Jiang, Sheng Zhou, Shuguang Cui, Zhisheng Niu |
Abstract | Timely and accurate knowledge of channel state information (CSI) is necessary to support scheduling operations at both physical and network layers. In order to support pilot-free channel estimation in cell sleeping scenarios, we propose to adopt a channel database that stores the CSI as a function of geographic locations. Such a channel database is generated from historical user records, which usually can not cover all the locations in the cell. Therefore, we develop a two-step interpolation method to infer the channels at the uncovered locations. The method firstly applies the K-nearest-neighbor method to form a coarse database and then refines it with a deep convolutional neural network. When applied to the channel data generated by ray tracing software, our method shows a great advantage in performance over the conventional interpolation methods. |
Tasks | |
Published | 2018-12-04 |
URL | http://arxiv.org/abs/1812.01247v1 |
http://arxiv.org/pdf/1812.01247v1.pdf | |
PWC | https://paperswithcode.com/paper/a-two-step-learning-and-interpolation-method |
Repo | |
Framework | |
Transformer for Emotion Recognition
Title | Transformer for Emotion Recognition |
Authors | Jean-Benoit Delbrouck |
Abstract | This paper describes the UMONS solution for the OMG-Emotion Challenge. We explore a context-dependent architecture where the arousal and valence of an utterance are predicted according to its surrounding context (i.e. the preceding and following utterances of the video). We report an improvement when taking into account context for both unimodal and multimodal predictions. |
Tasks | Emotion Recognition |
Published | 2018-05-03 |
URL | http://arxiv.org/abs/1805.02489v2 |
http://arxiv.org/pdf/1805.02489v2.pdf | |
PWC | https://paperswithcode.com/paper/transformer-for-emotion-recognition |
Repo | |
Framework | |
Structured-based Curriculum Learning for End-to-end English-Japanese Speech Translation
Title | Structured-based Curriculum Learning for End-to-end English-Japanese Speech Translation |
Authors | Takatomo Kano, Sakriani Sakti, Satoshi Nakamura |
Abstract | Sequence-to-sequence attentional-based neural network architectures have been shown to provide a powerful model for machine translation and speech recognition. Recently, several works have attempted to extend the models for end-to-end speech translation task. However, the usefulness of these models were only investigated on language pairs with similar syntax and word order (e.g., English-French or English-Spanish). In this work, we focus on end-to-end speech translation tasks on syntactically distant language pairs (e.g., English-Japanese) that require distant word reordering. To guide the encoder-decoder attentional model to learn this difficult problem, we propose a structured-based curriculum learning strategy. Unlike conventional curriculum learning that gradually emphasizes difficult data examples, we formalize learning strategies from easier network structures to more difficult network structures. Here, we start the training with end-to-end encoder-decoder for speech recognition or text-based machine translation task then gradually move to end-to-end speech translation task. The experiment results show that the proposed approach could provide significant improvements in comparison with the one without curriculum learning. |
Tasks | Machine Translation, Speech Recognition |
Published | 2018-02-13 |
URL | http://arxiv.org/abs/1802.06003v1 |
http://arxiv.org/pdf/1802.06003v1.pdf | |
PWC | https://paperswithcode.com/paper/structured-based-curriculum-learning-for-end |
Repo | |
Framework | |
ADNet: A Deep Network for Detecting Adverts
Title | ADNet: A Deep Network for Detecting Adverts |
Authors | Murhaf Hossari, Soumyabrata Dev, Matthew Nicholson, Killian McCabe, Atul Nautiyal, Clare Conran, Jian Tang, Wei Xu, François Pitié |
Abstract | Online video advertising gives content providers the ability to deliver compelling content, reach a growing audience, and generate additional revenue from online media. Recently, advertising strategies are designed to look for original advert(s) in a video frame, and replacing them with new adverts. These strategies, popularly known as product placement or embedded marketing, greatly help the marketing agencies to reach out to a wider audience. However, in the existing literature, such detection of candidate frames in a video sequence for the purpose of advert integration, is done manually. In this paper, we propose a deep-learning architecture called ADNet, that automatically detects the presence of advertisements in video frames. Our approach is the first of its kind that automatically detects the presence of adverts in a video frame, and achieves state-of-the-art results on a public dataset. |
Tasks | Detecting Adverts |
Published | 2018-11-09 |
URL | http://arxiv.org/abs/1811.04115v1 |
http://arxiv.org/pdf/1811.04115v1.pdf | |
PWC | https://paperswithcode.com/paper/adnet-a-deep-network-for-detecting-adverts |
Repo | |
Framework | |
Cross-connected Networks for Multi-task Learning of Detection and Segmentation
Title | Cross-connected Networks for Multi-task Learning of Detection and Segmentation |
Authors | Seiichiro Fukuda, Ryota Yoshihashi, Rei Kawakami, Shaodi You, Makoto Iida, Takeshi Naemura |
Abstract | Multi-task learning improves generalization performance by sharing knowledge among related tasks. Existing models are for task combinations annotated on the same dataset, while there are cases where multiple datasets are available for each task. How to utilize knowledge of successful single-task CNNs that are trained on each dataset has been explored less than multi-task learning with a single dataset. We propose a cross-connected CNN, a new architecture that connects single-task CNNs through convolutional layers, which transfer useful information for the counterpart. We evaluated our proposed architecture on a combination of detection and segmentation using two datasets. Experiments on pedestrians show our CNN achieved a higher detection performance compared to baseline CNNs, while maintaining high quality for segmentation. It is the first known attempt to tackle multi-task learning with different training datasets between detection and segmentation. Experiments with wild birds demonstrate how our CNN learns general representations from limited datasets. |
Tasks | Multi-Task Learning |
Published | 2018-05-15 |
URL | http://arxiv.org/abs/1805.05569v1 |
http://arxiv.org/pdf/1805.05569v1.pdf | |
PWC | https://paperswithcode.com/paper/cross-connected-networks-for-multi-task |
Repo | |
Framework | |
Authorship Attribution Using the Chaos Game Representation
Title | Authorship Attribution Using the Chaos Game Representation |
Authors | Daniel Lichtblau, Catalin Stoean |
Abstract | The Chaos Game Representation, a method for creating images from nucleotide sequences, is modified to make images from chunks of text documents. Machine learning methods are then applied to train classifiers based on authorship. Experiments are conducted on several benchmark data sets in English, including the widely used Federalist Papers, and one in Portuguese. Validation results for the trained classifiers are competitive with the best methods in prior literature. The methodology is also successfully applied for text categorization with encouraging results. One classifier method is moreover seen to hold promise for the task of digital fingerprinting. |
Tasks | Text Categorization |
Published | 2018-02-14 |
URL | http://arxiv.org/abs/1802.06007v1 |
http://arxiv.org/pdf/1802.06007v1.pdf | |
PWC | https://paperswithcode.com/paper/authorship-attribution-using-the-chaos-game |
Repo | |
Framework | |
On the Optimization of Deep Networks: Implicit Acceleration by Overparameterization
Title | On the Optimization of Deep Networks: Implicit Acceleration by Overparameterization |
Authors | Sanjeev Arora, Nadav Cohen, Elad Hazan |
Abstract | Conventional wisdom in deep learning states that increasing depth improves expressiveness but complicates optimization. This paper suggests that, sometimes, increasing depth can speed up optimization. The effect of depth on optimization is decoupled from expressiveness by focusing on settings where additional layers amount to overparameterization - linear neural networks, a well-studied model. Theoretical analysis, as well as experiments, show that here depth acts as a preconditioner which may accelerate convergence. Even on simple convex problems such as linear regression with $\ell_p$ loss, $p>2$, gradient descent can benefit from transitioning to a non-convex overparameterized objective, more than it would from some common acceleration schemes. We also prove that it is mathematically impossible to obtain the acceleration effect of overparametrization via gradients of any regularizer. |
Tasks | |
Published | 2018-02-19 |
URL | http://arxiv.org/abs/1802.06509v2 |
http://arxiv.org/pdf/1802.06509v2.pdf | |
PWC | https://paperswithcode.com/paper/on-the-optimization-of-deep-networks-implicit |
Repo | |
Framework | |