Paper Group ANR 1148
Deep Semantic Face Deblurring. A High-Order Scheme for Image Segmentation via a modified Level-Set method. Few-shot learning with attention-based sequence-to-sequence models. MACRO: A Meta-Algorithm for Conditional Risk Minimization. Social Algorithms. Multi-View Fuzzy Logic System with the Cooperation between Visible and Hidden Views. A relativist …
Deep Semantic Face Deblurring
| Title | Deep Semantic Face Deblurring |
| Authors | Ziyi Shen, Wei-Sheng Lai, Tingfa Xu, Jan Kautz, Ming-Hsuan Yang |
| Abstract | In this paper, we present an effective and efficient face deblurring algorithm by exploiting semantic cues via deep convolutional neural networks (CNNs). As face images are highly structured and share several key semantic components (e.g., eyes and mouths), the semantic information of a face provides a strong prior for restoration. As such, we propose to incorporate global semantic priors as input and impose local structure losses to regularize the output within a multi-scale deep CNN. We train the network with perceptual and adversarial losses to generate photo-realistic results and develop an incremental training strategy to handle random blur kernels in the wild. Quantitative and qualitative evaluations demonstrate that the proposed face deblurring algorithm restores sharp images with more facial details and performs favorably against state-of-the-art methods in terms of restoration quality, face recognition and execution speed. |
| Tasks | Deblurring, Face Recognition |
| Published | 2018-03-09 |
| URL | http://arxiv.org/abs/1803.03345v2 |
| http://arxiv.org/pdf/1803.03345v2.pdf | |
| PWC | https://paperswithcode.com/paper/deep-semantic-face-deblurring |
| Repo | |
| Framework | |
A High-Order Scheme for Image Segmentation via a modified Level-Set method
| Title | A High-Order Scheme for Image Segmentation via a modified Level-Set method |
| Authors | Maurizio Falcone, Giulio Paolucci, Silvia Tozza |
| Abstract | In this paper we propose a high-order accurate scheme for image segmentation based on the level-set method. In this approach, the curve evolution is described as the 0-level set of a representation function but we modify the velocity that drives the curve to the boundary of the object in order to obtain a new velocity with additional properties that are extremely useful to develop a more stable high-order approximation with a small additional cost. The approximation scheme proposed here is the first 2D version of an adaptive “filtered” scheme recently introduced and analyzed by the authors in 1D. This approach is interesting since the implementation of the filtered scheme is rather efficient and easy. The scheme combines two building blocks (a monotone scheme and a high-order scheme) via a filter function and smoothness indicators that allow to detect the regularity of the approximate solution adapting the scheme in an automatic way. Some numerical tests on synthetic and real images confirm the accuracy of the proposed method and the advantages given by the new velocity. |
| Tasks | Semantic Segmentation |
| Published | 2018-12-07 |
| URL | https://arxiv.org/abs/1812.03026v2 |
| https://arxiv.org/pdf/1812.03026v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-high-order-scheme-for-image-segmentation |
| Repo | |
| Framework | |
Few-shot learning with attention-based sequence-to-sequence models
| Title | Few-shot learning with attention-based sequence-to-sequence models |
| Authors | Bertrand Higy, Peter Bell |
| Abstract | End-to-end approaches have recently become popular as a means of simplifying the training and deployment of speech recognition systems. However, they often require large amounts of data to perform well on large vocabulary tasks. With the aim of making end-to-end approaches usable by a broader range of researchers, we explore the potential to use end-to-end methods in small vocabulary contexts where smaller datasets may be used. A significant drawback of small-vocabulary systems is the difficulty of expanding the vocabulary beyond the original training samples – therefore we also study strategies to extend the vocabulary with only few examples per new class (few-shot learning). Our results show that an attention-based encoder-decoder can be competitive against a strong baseline on a small vocabulary keyword classification task, reaching 97.5% of accuracy on Tensorflow’s Speech Commands dataset. It also shows promising results on the few-shot learning problem where a simple strategy achieved 68.8% of accuracy on new keywords with only 10 examples for each new class. This score goes up to 88.4% with a larger set of 100 examples. |
| Tasks | Few-Shot Learning, Speech Recognition |
| Published | 2018-11-08 |
| URL | http://arxiv.org/abs/1811.03519v2 |
| http://arxiv.org/pdf/1811.03519v2.pdf | |
| PWC | https://paperswithcode.com/paper/few-shot-learning-with-attention-based |
| Repo | |
| Framework | |
MACRO: A Meta-Algorithm for Conditional Risk Minimization
| Title | MACRO: A Meta-Algorithm for Conditional Risk Minimization |
| Authors | Alexander Zimin, Christoph Lampert |
| Abstract | We study conditional risk minimization (CRM), i.e. the problem of learning a hypothesis of minimal risk for prediction at the next step of sequentially arriving dependent data. Despite it being a fundamental problem, successful learning in the CRM sense has so far only been demonstrated using theoretical algorithms that cannot be used for real problems as they would require storing all incoming data. In this work, we introduce MACRO, a meta-algorithm for CRM that does not suffer from this shortcoming, but nevertheless offers learning guarantees. Instead of storing all data it maintains and iteratively updates a set of learning subroutines. With suitable approximations, MACRO applied to real data, yielding improved prediction performance compared to traditional non-conditional learning. |
| Tasks | |
| Published | 2018-01-01 |
| URL | http://arxiv.org/abs/1801.00507v2 |
| http://arxiv.org/pdf/1801.00507v2.pdf | |
| PWC | https://paperswithcode.com/paper/macro-a-meta-algorithm-for-conditional-risk |
| Repo | |
| Framework | |
Social Algorithms
| Title | Social Algorithms |
| Authors | Xin-She Yang |
| Abstract | This article concerns the review of a special class of swarm intelligence based algorithms for solving optimization problems and these algorithms can be referred to as social algorithms. Social algorithms use multiple agents and the social interactions to design rules for algorithms so as to mimic certain successful characteristics of the social/biological systems such as ants, bees, bats, birds and animals. |
| Tasks | |
| Published | 2018-04-22 |
| URL | http://arxiv.org/abs/1805.05855v1 |
| http://arxiv.org/pdf/1805.05855v1.pdf | |
| PWC | https://paperswithcode.com/paper/social-algorithms |
| Repo | |
| Framework | |
Multi-View Fuzzy Logic System with the Cooperation between Visible and Hidden Views
| Title | Multi-View Fuzzy Logic System with the Cooperation between Visible and Hidden Views |
| Authors | Te Zhang, Zhaohong Deng, Dongrui Wu, Shitong Wang |
| Abstract | Multi-view datasets are frequently encountered in learning tasks, such as web data mining and multimedia information analysis. Given a multi-view dataset, traditional learning algorithms usually decompose it into several single-view datasets, from each of which a single-view model is learned. In contrast, a multi-view learning algorithm can achieve better performance by cooperative learning on the multi-view data. However, existing multi-view approaches mainly focus on the views that are visible and ignore the hidden information behind the visible views, which usually contains some intrinsic information of the multi-view data, or vice versa. To address this problem, this paper proposes a multi-view fuzzy logic system, which utilizes both the hidden information shared by the multiple visible views and the information of each visible view. Extensive experiments were conducted to validate its effectiveness. |
| Tasks | MULTI-VIEW LEARNING |
| Published | 2018-07-23 |
| URL | http://arxiv.org/abs/1807.08595v1 |
| http://arxiv.org/pdf/1807.08595v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-view-fuzzy-logic-system-with-the |
| Repo | |
| Framework | |
A relativistic extension of Hopfield neural networks via the mechanical analogy
| Title | A relativistic extension of Hopfield neural networks via the mechanical analogy |
| Authors | Adriano Barra, Matteo Beccaria, Alberto Fachechi |
| Abstract | We propose a modification of the cost function of the Hopfield model whose salient features shine in its Taylor expansion and result in more than pairwise interactions with alternate signs, suggesting a unified framework for handling both with deep learning and network pruning. In our analysis, we heavily rely on the Hamilton-Jacobi correspondence relating the statistical model with a mechanical system. In this picture, our model is nothing but the relativistic extension of the original Hopfield model (whose cost function is a quadratic form in the Mattis magnetization which mimics the non-relativistic Hamiltonian for a free particle). We focus on the low-storage regime and solve the model analytically by taking advantage of the mechanical analogy, thus obtaining a complete characterization of the free energy and the associated self-consistency equations in the thermodynamic limit. On the numerical side, we test the performances of our proposal with MC simulations, showing that the stability of spurious states (limiting the capabilities of the standard Hebbian construction) is sensibly reduced due to presence of unlearning contributions in this extended framework. |
| Tasks | Network Pruning |
| Published | 2018-01-05 |
| URL | http://arxiv.org/abs/1801.01743v1 |
| http://arxiv.org/pdf/1801.01743v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-relativistic-extension-of-hopfield-neural |
| Repo | |
| Framework | |
Detecting Memorization in ReLU Networks
| Title | Detecting Memorization in ReLU Networks |
| Authors | Edo Collins, Siavash Arjomand Bigdeli, Sabine Süsstrunk |
| Abstract | We propose a new notion of `non-linearity’ of a network layer with respect to an input batch that is based on its proximity to a linear system, which is reflected in the non-negative rank of the activation matrix. We measure this non-linearity by applying non-negative factorization to the activation matrix. Considering batches of similar samples, we find that high non-linearity in deep layers is indicative of memorization. Furthermore, by applying our approach layer-by-layer, we find that the mechanism for memorization consists of distinct phases. We perform experiments on fully-connected and convolutional neural networks trained on several image and audio datasets. Our results demonstrate that as an indicator for memorization, our technique can be used to perform early stopping. | |
| Tasks | |
| Published | 2018-10-08 |
| URL | http://arxiv.org/abs/1810.03372v1 |
| http://arxiv.org/pdf/1810.03372v1.pdf | |
| PWC | https://paperswithcode.com/paper/detecting-memorization-in-relu-networks |
| Repo | |
| Framework | |
Dynamic voting in multi-view learning for radiomics applications
| Title | Dynamic voting in multi-view learning for radiomics applications |
| Authors | Hongliu Cao, Simon Bernard, Laurent Heutte, Robert Sabourin |
| Abstract | Cancer diagnosis and treatment often require a personalized analysis for each patient nowadays, due to the heterogeneity among the different types of tumor and among patients. Radiomics is a recent medical imaging field that has shown during the past few years to be promising for achieving this personalization. However, a recent study shows that most of the state-of-the-art works in Radiomics fail to identify this problem as a multi-view learning task and that multi-view learning techniques are generally more efficient. In this work, we propose to further investigate the potential of one family of multi-view learning methods based on Multiple Classifiers Systems where one classifier is learnt on each view and all classifiers are combined afterwards. In particular, we propose a random forest based dynamic weighted voting scheme, which personalizes the combination of views for each new patient for classification tasks. The proposed method is validated on several real-world Radiomics problems. |
| Tasks | MULTI-VIEW LEARNING |
| Published | 2018-06-20 |
| URL | http://arxiv.org/abs/1806.07686v2 |
| http://arxiv.org/pdf/1806.07686v2.pdf | |
| PWC | https://paperswithcode.com/paper/dynamic-voting-in-multi-view-learning-for |
| Repo | |
| Framework | |
Local Causal States and Discrete Coherent Structures
| Title | Local Causal States and Discrete Coherent Structures |
| Authors | Adam Rupe, James P. Crutchfield |
| Abstract | Coherent structures form spontaneously in nonlinear spatiotemporal systems and are found at all spatial scales in natural phenomena from laboratory hydrodynamic flows and chemical reactions to ocean, atmosphere, and planetary climate dynamics. Phenomenologically, they appear as key components that organize the macroscopic behaviors in such systems. Despite a century of effort, they have eluded rigorous analysis and empirical prediction, with progress being made only recently. As a step in this, we present a formal theory of coherent structures in fully-discrete dynamical field theories. It builds on the notion of structure introduced by computational mechanics, generalizing it to a local spatiotemporal setting. The analysis’ main tool employs the \localstates, which are used to uncover a system’s hidden spatiotemporal symmetries and which identify coherent structures as spatially-localized deviations from those symmetries. The approach is behavior-driven in the sense that it does not rely on directly analyzing spatiotemporal equations of motion, rather it considers only the spatiotemporal fields a system generates. As such, it offers an unsupervised approach to discover and describe coherent structures. We illustrate the approach by analyzing coherent structures generated by elementary cellular automata, comparing the results with an earlier, dynamic-invariant-set approach that decomposes fields into domains, particles, and particle interactions. |
| Tasks | |
| Published | 2018-01-01 |
| URL | http://arxiv.org/abs/1801.00515v1 |
| http://arxiv.org/pdf/1801.00515v1.pdf | |
| PWC | https://paperswithcode.com/paper/local-causal-states-and-discrete-coherent |
| Repo | |
| Framework | |
Self-Attention Recurrent Network for Saliency Detection
| Title | Self-Attention Recurrent Network for Saliency Detection |
| Authors | Fengdong Sun, Wenhui Li, Yuanyuan Guan |
| Abstract | Feature maps in deep neural network generally contain different semantics. Existing methods often omit their characteristics that may lead to sub-optimal results. In this paper, we propose a novel end-to-end deep saliency network which could effectively utilize multi-scale feature maps according to their characteristics. Shallow layers often contain more local information, and deep layers have advantages in global semantics. Therefore, the network generates elaborate saliency maps by enhancing local and global information of feature maps in different layers. On one hand, local information of shallow layers is enhanced by a recurrent structure which shared convolution kernel at different time steps. On the other hand, global information of deep layers is utilized by a self-attention module, which generates different attention weights for salient objects and backgrounds thus achieve better performance. Experimental results on four widely used datasets demonstrate that our method has advantages in performance over existing algorithms. |
| Tasks | Saliency Detection |
| Published | 2018-08-05 |
| URL | http://arxiv.org/abs/1808.01634v1 |
| http://arxiv.org/pdf/1808.01634v1.pdf | |
| PWC | https://paperswithcode.com/paper/self-attention-recurrent-network-for-saliency |
| Repo | |
| Framework | |
Stingray Detection of Aerial Images Using Augmented Training Images Generated by A Conditional Generative Model
| Title | Stingray Detection of Aerial Images Using Augmented Training Images Generated by A Conditional Generative Model |
| Authors | Yi-Min Chou, Chien-Hung Chen, Keng-Hao Liu, Chu-Song Chen |
| Abstract | In this paper, we present an object detection method that tackles the stingray detection problem based on aerial images. In this problem, the images are aerially captured on a sea-surface area by using an Unmanned Aerial Vehicle (UAV), and the stingrays swimming under (but close to) the sea surface are the target we want to detect and locate. To this end, we use a deep object detection method, faster RCNN, to train a stingray detector based on a limited training set of images. To boost the performance, we develop a new generative approach, conditional GLO, to increase the training samples of stingray, which is an extension of the Generative Latent Optimization (GLO) approach. Unlike traditional data augmentation methods that generate new data only for image classification, our proposed method that mixes foreground and background together can generate new data for an object detection task, and thus improve the training efficacy of a CNN detector. Experimental results show that satisfiable performance can be obtained by using our approach on stingray detection in aerial images. |
| Tasks | Data Augmentation, Image Classification, Object Detection |
| Published | 2018-05-11 |
| URL | http://arxiv.org/abs/1805.04262v3 |
| http://arxiv.org/pdf/1805.04262v3.pdf | |
| PWC | https://paperswithcode.com/paper/stingray-detection-of-aerial-images-using |
| Repo | |
| Framework | |
Video Saliency Detection by 3D Convolutional Neural Networks
| Title | Video Saliency Detection by 3D Convolutional Neural Networks |
| Authors | Guanqun Ding, Yuming Fang |
| Abstract | Different from salient object detection methods for still images, a key challenging for video saliency detection is how to extract and combine spatial and temporal features. In this paper, we present a novel and effective approach for salient object detection for video sequences based on 3D convolutional neural networks. First, we design a 3D convolutional network (Conv3DNet) with the input as three video frame to learn the spatiotemporal features for video sequences. Then, we design a 3D deconvolutional network (Deconv3DNet) to combine the spatiotemporal features to predict the final saliency map for video sequences. Experimental results show that the proposed saliency detection model performs better in video saliency prediction compared with the state-of-the-art video saliency detection methods. |
| Tasks | Object Detection, Saliency Detection, Saliency Prediction, Salient Object Detection, Video Saliency Detection |
| Published | 2018-07-12 |
| URL | http://arxiv.org/abs/1807.04514v1 |
| http://arxiv.org/pdf/1807.04514v1.pdf | |
| PWC | https://paperswithcode.com/paper/video-saliency-detection-by-3d-convolutional |
| Repo | |
| Framework | |
Context Proposals for Saliency Detection
| Title | Context Proposals for Saliency Detection |
| Authors | Aymen Azaza, Joost van de Weijer, Ali Douik, Marc Masana |
| Abstract | One of the fundamental properties of a salient object region is its contrast with the immediate context. The problem is that numerous object regions exist which potentially can all be salient. One way to prevent an exhaustive search over all object regions is by using object proposal algorithms. These return a limited set of regions which are most likely to contain an object. Several saliency estimation methods have used object proposals. However, they focus on the saliency of the proposal only, and the importance of its immediate context has not been evaluated. In this paper, we aim to improve salient object detection. Therefore, we extend object proposal methods with context proposals, which allow to incorporate the immediate context in the saliency computation. We propose several saliency features which are computed from the context proposals. In the experiments, we evaluate five object proposal methods for the task of saliency segmentation, and find that Multiscale Combinatorial Grouping outperforms the others. Furthermore, experiments show that the proposed context features improve performance, and that our method matches results on the FT datasets and obtains competitive results on three other datasets (PASCAL-S, MSRA-B and ECSSD). |
| Tasks | Object Detection, Saliency Detection, Saliency Prediction, Salient Object Detection |
| Published | 2018-06-27 |
| URL | http://arxiv.org/abs/1806.10359v1 |
| http://arxiv.org/pdf/1806.10359v1.pdf | |
| PWC | https://paperswithcode.com/paper/context-proposals-for-saliency-detection |
| Repo | |
| Framework | |
Using Regular Languages to Explore the Representational Capacity of Recurrent Neural Architectures
| Title | Using Regular Languages to Explore the Representational Capacity of Recurrent Neural Architectures |
| Authors | Abhijit Mahalunkar, John D. Kelleher |
| Abstract | The presence of Long Distance Dependencies (LDDs) in sequential data poses significant challenges for computational models. Various recurrent neural architectures have been designed to mitigate this issue. In order to test these state-of-the-art architectures, there is growing need for rich benchmarking datasets. However, one of the drawbacks of existing datasets is the lack of experimental control with regards to the presence and/or degree of LDDs. This lack of control limits the analysis of model performance in relation to the specific challenge posed by LDDs. One way to address this is to use synthetic data having the properties of subregular languages. The degree of LDDs within the generated data can be controlled through the k parameter, length of the generated strings, and by choosing appropriate forbidden strings. In this paper, we explore the capacity of different RNN extensions to model LDDs, by evaluating these models on a sequence of SPk synthesized datasets, where each subsequent dataset exhibits a longer degree of LDD. Even though SPk are simple languages, the presence of LDDs does have significant impact on the performance of recurrent neural architectures, thus making them prime candidate in benchmarking tasks. |
| Tasks | |
| Published | 2018-08-15 |
| URL | http://arxiv.org/abs/1808.05128v1 |
| http://arxiv.org/pdf/1808.05128v1.pdf | |
| PWC | https://paperswithcode.com/paper/using-regular-languages-to-explore-the |
| Repo | |
| Framework | |
