Paper Group ANR 779
Blind Motion Deblurring with Cycle Generative Adversarial Networks. Variational approach to unsupervised learning. A Collaborative Approach using Ridge-Valley Minutiae for More Accurate Contactless Fingerprint Identification. Making a Case for Social Media Corpus for Detecting Depression. Rapid Learning or Feature Reuse? Towards Understanding the E …
Blind Motion Deblurring with Cycle Generative Adversarial Networks
| Title | Blind Motion Deblurring with Cycle Generative Adversarial Networks |
| Authors | Quan Yuan, Junxia Li, Lingwei Zhang, Zhefu Wu, Guangyu Liu |
| Abstract | Blind motion deblurring is one of the most basic and challenging problems in image processing and computer vision. It aims to recover a sharp image from its blurred version knowing nothing about the blur process. Many existing methods use Maximum A Posteriori (MAP) or Expectation Maximization (EM) frameworks to deal with this kind of problems, but they cannot handle well the figh frequency features of natural images. Most recently, deep neural networks have been emerging as a powerful tool for image deblurring. In this paper, we prove that encoder-decoder architecture gives better results for image deblurring tasks. In addition, we propose a novel end-to-end learning model which refines generative adversarial network by many novel training strategies so as to tackle the problem of deblurring. Experimental results show that our model can capture high frequency features well, and the results on benchmark dataset show that proposed model achieves the competitive performance. |
| Tasks | Deblurring |
| Published | 2019-01-07 |
| URL | http://arxiv.org/abs/1901.01641v2 |
| http://arxiv.org/pdf/1901.01641v2.pdf | |
| PWC | https://paperswithcode.com/paper/blind-motion-deblurring-with-cycle-generative |
| Repo | |
| Framework | |
Variational approach to unsupervised learning
| Title | Variational approach to unsupervised learning |
| Authors | Swapnil Nitin Shah |
| Abstract | Deep belief networks are used extensively for unsupervised stochastic learning on large datasets. Compared to other deep learning approaches their layer-by-layer learning makes them highly scalable. Unfortunately, the principles by which they achieve efficient learning are not well understood. Numerous attempts have been made to explain their efficiency and applicability to a wide class of learning problems in terms of principles drawn from cognitive psychology, statistics, information theory, and more recently physics, but quite often these imported principles lack strong scientific foundation. Here we demonstrate how one can arrive at convolutional deep belief networks as potential solution to unsupervised learning problems without making assumptions about the underlying framework. To do this, we exploit the notion of symmetry that is fundamental in machine learning, physics and other fields, utilizing the particular form of the functional renormalization group in physics. |
| Tasks | |
| Published | 2019-04-24 |
| URL | http://arxiv.org/abs/1904.10869v1 |
| http://arxiv.org/pdf/1904.10869v1.pdf | |
| PWC | https://paperswithcode.com/paper/variational-approach-to-unsupervised-learning |
| Repo | |
| Framework | |
A Collaborative Approach using Ridge-Valley Minutiae for More Accurate Contactless Fingerprint Identification
| Title | A Collaborative Approach using Ridge-Valley Minutiae for More Accurate Contactless Fingerprint Identification |
| Authors | Ritesh Vyas, Ajay Kumar |
| Abstract | Contactless fingerprint identification has emerged as an reliable and user friendly alternative for the personal identification in a range of e-business and law-enforcement applications. It is however quite known from the literature that the contactless fingerprint images deliver remarkably low matching accuracies as compared with those obtained from the contact-based fingerprint sensors. This paper develops a new approach to significantly improve contactless fingerprint matching capabilities available today. We systematically analyze the extent of complimentary ridge-valley information and introduce new approaches to achieve significantly higher matching accuracy over state-of-art fingerprint matchers commonly employed today. We also investigate least explored options for the fingerprint color-space conversions, which can play a key-role for more accurate contactless fingerprint matching. This paper presents experimental results from different publicly available contactless fingerprint databases using NBIS, MCC and COTS matchers. Our consistently outperforming results validate the effectiveness of the proposed approach for more accurate contactless fingerprint identification. |
| Tasks | |
| Published | 2019-09-13 |
| URL | https://arxiv.org/abs/1909.06045v2 |
| https://arxiv.org/pdf/1909.06045v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-collaborative-approach-using-ridge-valley |
| Repo | |
| Framework | |
Making a Case for Social Media Corpus for Detecting Depression
| Title | Making a Case for Social Media Corpus for Detecting Depression |
| Authors | Adil Rajput, Samara Ahmed |
| Abstract | The social media platform provides an opportunity to gain valuable insights into user behaviour. Users mimic their internal feelings and emotions in a disinhibited fashion using natural language. Techniques in Natural Language Processing have helped researchers decipher standard documents and cull together inferences from massive amount of data. A representative corpus is a prerequisite for NLP and one of the challenges we face today is the non-standard and noisy language that exists on the internet. Our work focuses on building a corpus from social media that is focused on detecting mental illness. We use depression as a case study and demonstrate the effectiveness of using such a corpus for helping practitioners detect such cases. Our results show a high correlation between our Social Media Corpus and the standard corpus for depression. |
| Tasks | |
| Published | 2019-02-02 |
| URL | http://arxiv.org/abs/1902.00702v1 |
| http://arxiv.org/pdf/1902.00702v1.pdf | |
| PWC | https://paperswithcode.com/paper/making-a-case-for-social-media-corpus-for |
| Repo | |
| Framework | |
Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAML
| Title | Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAML |
| Authors | Aniruddh Raghu, Maithra Raghu, Samy Bengio, Oriol Vinyals |
| Abstract | An important research direction in machine learning has centered around developing meta-learning algorithms to tackle few-shot learning. An especially successful algorithm has been Model Agnostic Meta-Learning (MAML), a method that consists of two optimization loops, with the outer loop finding a meta-initialization, from which the inner loop can efficiently learn new tasks. Despite MAML’s popularity, a fundamental open question remains – is the effectiveness of MAML due to the meta-initialization being primed for rapid learning (large, efficient changes in the representations) or due to feature reuse, with the meta initialization already containing high quality features? We investigate this question, via ablation studies and analysis of the latent representations, finding that feature reuse is the dominant factor. This leads to the ANIL (Almost No Inner Loop) algorithm, a simplification of MAML where we remove the inner loop for all but the (task-specific) head of a MAML-trained network. ANIL matches MAML’s performance on benchmark few-shot image classification and RL and offers computational improvements over MAML. We further study the precise contributions of the head and body of the network, showing that performance on the test tasks is entirely determined by the quality of the learned features, and we can remove even the head of the network (the NIL algorithm). We conclude with a discussion of the rapid learning vs feature reuse question for meta-learning algorithms more broadly. |
| Tasks | Few-Shot Image Classification, Few-Shot Learning, Image Classification, Meta-Learning |
| Published | 2019-09-19 |
| URL | https://arxiv.org/abs/1909.09157v2 |
| https://arxiv.org/pdf/1909.09157v2.pdf | |
| PWC | https://paperswithcode.com/paper/rapid-learning-or-feature-reuse-towards |
| Repo | |
| Framework | |
Investigating Constraint Programming and Hybrid Methods for Real World Industrial Test Laboratory Scheduling
| Title | Investigating Constraint Programming and Hybrid Methods for Real World Industrial Test Laboratory Scheduling |
| Authors | Tobias Geibinger, Florian Mischek, Nysret Musliu |
| Abstract | In this paper we deal with a complex real world scheduling problem closely related to the well-known Resource-Constrained Project Scheduling Problem (RCPSP). The problem concerns industrial test laboratories in which a large number of tests has to be performed by qualified personnel using specialised equipment, while respecting deadlines and other constraints. We present different constraint programming models and search strategies for this problem. Furthermore, we propose a Very Large Neighborhood Search approach based on our CP methods. Our models are evaluated using CP solvers and a MIP solver both on real-world test laboratory data and on a set of generated instances of different sizes based on the real-world data. Further, we compare the exact approaches with VLNS and a Simulated Annealing heuristic. We could find feasible solutions for all instances and several optimal solutions and we show that using VLNS we can improve upon the results of the other approaches. |
| Tasks | |
| Published | 2019-11-12 |
| URL | https://arxiv.org/abs/1911.04766v1 |
| https://arxiv.org/pdf/1911.04766v1.pdf | |
| PWC | https://paperswithcode.com/paper/investigating-constraint-programming-and |
| Repo | |
| Framework | |
Discriminative Sentence Modeling for Story Ending Prediction
| Title | Discriminative Sentence Modeling for Story Ending Prediction |
| Authors | Yiming Cui, Wanxiang Che, Wei-Nan Zhang, Ting Liu, Shijin Wang, Guoping Hu |
| Abstract | Story Ending Prediction is a task that needs to select an appropriate ending for the given story, which requires the machine to understand the story and sometimes needs commonsense knowledge. To tackle this task, we propose a new neural network called Diff-Net for better modeling the differences of each ending in this task. The proposed model could discriminate two endings in three semantic levels: contextual representation, story-aware representation, and discriminative representation. Experimental results on the Story Cloze Test dataset show that the proposed model siginificantly outperforms various systems by a large margin, and detailed ablation studies are given for better understanding our model. We also carefully examine the traditional and BERT-based models on both SCT v1.0 and v1.5 with interesting findings that may potentially help future studies. |
| Tasks | |
| Published | 2019-12-19 |
| URL | https://arxiv.org/abs/1912.09008v1 |
| https://arxiv.org/pdf/1912.09008v1.pdf | |
| PWC | https://paperswithcode.com/paper/discriminative-sentence-modeling-for-story |
| Repo | |
| Framework | |
Selective Brain Damage: Measuring the Disparate Impact of Model Pruning
| Title | Selective Brain Damage: Measuring the Disparate Impact of Model Pruning |
| Authors | Sara Hooker, Aaron Courville, Yann Dauphin, Andrea Frome |
| Abstract | Neural network pruning techniques have demonstrated it is possible to remove the majority of weights in a network with surprisingly little degradation to test set accuracy. However, this measure of performance conceals significant differences in how different classes and images are impacted by pruning. We find that certain examples, which we term pruning identified exemplars (PIEs), and classes are systematically more impacted by the introduction of sparsity. Removing PIE images from the test-set greatly improves top-1 accuracy for both pruned and non-pruned models. These hard-to-generalize-to images tend to be mislabelled, of lower image quality, depict multiple objects or require fine-grained classification. These findings shed light on previously unknown trade-offs, and suggest that a high degree of caution should be exercised before pruning is used in sensitive domains. |
| Tasks | Network Pruning |
| Published | 2019-11-13 |
| URL | https://arxiv.org/abs/1911.05248v1 |
| https://arxiv.org/pdf/1911.05248v1.pdf | |
| PWC | https://paperswithcode.com/paper/selective-brain-damage-measuring-the |
| Repo | |
| Framework | |
Detecting Target-Area Link-Flooding DDoS Attacks using Traffic Analysis and Supervised Learning
| Title | Detecting Target-Area Link-Flooding DDoS Attacks using Traffic Analysis and Supervised Learning |
| Authors | Mostafa Rezazad, Matthias R. Brust, Mohammad Akbari, Pascal Bouvry, Ngai-Man Cheung |
| Abstract | A novel class of extreme link-flooding DDoS (Distributed Denial of Service) attacks is designed to cut off entire geographical areas such as cities and even countries from the Internet by simultaneously targeting a selected set of network links. The Crossfire attack is a target-area link-flooding attack, which is orchestrated in three complex phases. The attack uses a massively distributed large-scale botnet to generate low-rate benign traffic aiming to congest selected network links, so-called target links. The adoption of benign traffic, while simultaneously targeting multiple network links, makes detecting the Crossfire attack a serious challenge. In this paper, we present analytical and emulated results showing hitherto unidentified vulnerabilities in the execution of the attack, such as a correlation between coordination of the botnet traffic and the quality of the attack, and a correlation between the attack distribution and detectability of the attack. Additionally, we identified a warm-up period due to the bot synchronization. For attack detection, we report results of using two supervised machine learning approaches: Support Vector Machine (SVM) and Random Forest (RF) for classification of network traffic to normal and abnormal traffic, i.e, attack traffic. These machine learning models have been trained in various scenarios using the link volume as the main feature set. |
| Tasks | |
| Published | 2019-03-01 |
| URL | http://arxiv.org/abs/1903.01550v1 |
| http://arxiv.org/pdf/1903.01550v1.pdf | |
| PWC | https://paperswithcode.com/paper/detecting-target-area-link-flooding-ddos |
| Repo | |
| Framework | |
One-Pass Incomplete Multi-view Clustering
| Title | One-Pass Incomplete Multi-view Clustering |
| Authors | Menglei Hu, Songcan Chen |
| Abstract | Real data are often with multiple modalities or from multiple heterogeneous sources, thus forming so-called multi-view data, which receives more and more attentions in machine learning. Multi-view clustering (MVC) becomes its important paradigm. In real-world applications, some views often suffer from instances missing. Clustering on such multi-view datasets is called incomplete multi-view clustering (IMC) and quite challenging. To date, though many approaches have been developed, most of them are offline and have high computational and memory costs especially for large scale datasets. To address this problem, in this paper, we propose an One-Pass Incomplete Multi-view Clustering framework (OPIMC). With the help of regularized matrix factorization and weighted matrix factorization, OPIMC can relatively easily deal with such problem. Different from the existing and sole online IMC method, OPIMC can directly get clustering results and effectively determine the termination of iteration process by introducing two global statistics. Finally, extensive experiments conducted on four real datasets demonstrate the efficiency and effectiveness of the proposed OPIMC method. |
| Tasks | |
| Published | 2019-03-02 |
| URL | http://arxiv.org/abs/1903.00637v1 |
| http://arxiv.org/pdf/1903.00637v1.pdf | |
| PWC | https://paperswithcode.com/paper/one-pass-incomplete-multi-view-clustering |
| Repo | |
| Framework | |
Self-Adaptive Network Pruning
| Title | Self-Adaptive Network Pruning |
| Authors | Jinting Chen, Zhaocheng Zhu, Cheng Li, Yuming Zhao |
| Abstract | Deep convolutional neural networks have been proved successful on a wide range of tasks, yet they are still hindered by their large computation cost in many industrial scenarios. In this paper, we propose to reduce such cost for CNNs through a self-adaptive network pruning method (SANP). Our method introduces a general Saliency-and-Pruning Module (SPM) for each convolutional layer, which learns to predict saliency scores and applies pruning for each channel. Given a total computation budget, SANP adaptively determines the pruning strategy with respect to each layer and each sample, such that the average computation cost meets the budget. This design allows SANP to be more efficient in computation, as well as more robust to datasets and backbones. Extensive experiments on 2 datasets and 3 backbones show that SANP surpasses state-of-the-art methods in both classification accuracy and pruning rate. |
| Tasks | Network Pruning |
| Published | 2019-10-20 |
| URL | https://arxiv.org/abs/1910.08906v1 |
| https://arxiv.org/pdf/1910.08906v1.pdf | |
| PWC | https://paperswithcode.com/paper/self-adaptive-network-pruning |
| Repo | |
| Framework | |
Learning Matchable Image Transformations for Long-term Metric Visual Localization
| Title | Learning Matchable Image Transformations for Long-term Metric Visual Localization |
| Authors | Lee Clement, Mona Gridseth, Justin Tomasi, Jonathan Kelly |
| Abstract | Long-term metric self-localization is an essential capability of autonomous mobile robots, but remains challenging for vision-based systems due to appearance changes caused by lighting, weather, or seasonal variations. While experience-based mapping has proven to be an effective technique for bridging the `appearance gap,’ the number of experiences required for reliable metric localization over days or months can be very large, and methods for reducing the necessary number of experiences are needed for this approach to scale. Taking inspiration from color constancy theory, we learn a nonlinear RGB-to-grayscale mapping that explicitly maximizes the number of inlier feature matches for images captured under different lighting and weather conditions, and use it as a pre-processing step in a conventional single-experience localization pipeline to improve its robustness to appearance change. We train this mapping by approximating the target non-differentiable localization pipeline with a deep neural network, and find that incorporating a learned low-dimensional context feature can further improve cross-appearance feature matching. Using synthetic and real-world datasets, we demonstrate substantial improvements in localization performance across day-night cycles, enabling continuous metric localization over a 30-hour period using a single mapping experience, and allowing experience-based localization to scale to long deployments with dramatically reduced data requirements. | |
| Tasks | Color Constancy, Visual Localization |
| Published | 2019-04-01 |
| URL | https://arxiv.org/abs/1904.01080v4 |
| https://arxiv.org/pdf/1904.01080v4.pdf | |
| PWC | https://paperswithcode.com/paper/learning-matchable-colorspace-transformations |
| Repo | |
| Framework | |
RASNet: Segmentation for Tracking Surgical Instruments in Surgical Videos Using Refined Attention Segmentation Network
| Title | RASNet: Segmentation for Tracking Surgical Instruments in Surgical Videos Using Refined Attention Segmentation Network |
| Authors | Zhen-Liang Ni, Gui-Bin Bian, Xiao-Liang Xie, Zeng-Guang Hou, Xiao-Hu Zhou, Yan-Jie Zhou |
| Abstract | Segmentation for tracking surgical instruments plays an important role in robot-assisted surgery. Segmentation of surgical instruments contributes to capturing accurate spatial information for tracking. In this paper, a novel network, Refined Attention Segmentation Network, is proposed to simultaneously segment surgical instruments and identify their categories. The U-shape network which is popular in segmentation is used. Different from previous work, an attention module is adopted to help the network focus on key regions, which can improve the segmentation accuracy. To solve the class imbalance problem, the weighted sum of the cross entropy loss and the logarithm of the Jaccard index is used as loss function. Furthermore, transfer learning is adopted in our network. The encoder is pre-trained on ImageNet. The dataset from the MICCAI EndoVis Challenge 2017 is used to evaluate our network. Based on this dataset, our network achieves state-of-the-art performance 94.65% mean Dice and 90.33% mean IOU. |
| Tasks | Transfer Learning |
| Published | 2019-05-21 |
| URL | https://arxiv.org/abs/1905.08663v2 |
| https://arxiv.org/pdf/1905.08663v2.pdf | |
| PWC | https://paperswithcode.com/paper/rasnet-segmentation-for-tracking-surgical |
| Repo | |
| Framework | |
Probabilistic Multilayer Regularization Network for Unsupervised 3D Brain Image Registration
| Title | Probabilistic Multilayer Regularization Network for Unsupervised 3D Brain Image Registration |
| Authors | Lihao Liu, Xiaowei Hu, Lei Zhu, Pheng-Ann Heng |
| Abstract | Brain image registration transforms a pair of images into one system with the matched imaging contents, which is of essential importance for brain image analysis. This paper presents a novel framework for unsupervised 3D brain image registration by capturing the feature-level transformation relationships between the unaligned image and reference image. To achieve this, we develop a feature-level probabilistic model to provide the direct regularization to the hidden layers of two deep convolutional neural networks, which are constructed from two input images. This model design is developed into multiple layers of these two networks to capture the transformation relationships at different levels. We employ two common benchmark datasets for 3D brain image registration and perform various experiments to evaluate our method. Experimental results show that our method clearly outperforms state-of-the-art methods on both benchmark datasets by a large margin. |
| Tasks | Image Registration |
| Published | 2019-07-03 |
| URL | https://arxiv.org/abs/1907.01922v1 |
| https://arxiv.org/pdf/1907.01922v1.pdf | |
| PWC | https://paperswithcode.com/paper/probabilistic-multilayer-regularization |
| Repo | |
| Framework | |
Identity-Free Facial Expression Recognition using conditional Generative Adversarial Network
| Title | Identity-Free Facial Expression Recognition using conditional Generative Adversarial Network |
| Authors | Jie Cai, Zibo Meng, Ahmed Shehab Khan, Zhiyuan Li, James O’Reilly, Yan Tong |
| Abstract | In this paper, we proposed a novel Identity-free conditional Generative Adversarial Network (IF-GAN) to explicitly reduce inter-subject variations for facial expression recognition. Specifically, for any given input face image, a conditional generative model was developed to transform an average neutral face, which is calculated from various subjects showing neutral expressions, to an average expressive face with the same expression as the input image. Since the transformed images have the same synthetic “average” identity, they differ from each other by only their expressions and thus, can be used for identity-free expression classification. In this work, an end-to-end system was developed to perform expression transformation and expression recognition in the IF-GAN framework. Experimental results on three facial expression datasets have demonstrated that the proposed IF-GAN outperforms the baseline CNN model and achieves comparable or better performance compared with the state-of-the-art methods for facial expression recognition. |
| Tasks | Facial Expression Recognition |
| Published | 2019-03-19 |
| URL | http://arxiv.org/abs/1903.08051v1 |
| http://arxiv.org/pdf/1903.08051v1.pdf | |
| PWC | https://paperswithcode.com/paper/identity-free-facial-expression-recognition |
| Repo | |
| Framework | |
