Paper Group ANR 593
Leveraging Sparse and Dense Feature Combinations for Sentiment Classification. The origins of Zipf’s meaning-frequency law. Bayesian Optimisation for Safe Navigation under Localisation Uncertainty. Consistent Kernel Density Estimation with Non-Vanishing Bandwidth. Learning to Factor Policies and Action-Value Functions: Factored Action Space Represe …
Leveraging Sparse and Dense Feature Combinations for Sentiment Classification
| Title | Leveraging Sparse and Dense Feature Combinations for Sentiment Classification |
| Authors | Tao Yu, Christopher Hidey, Owen Rambow, Kathleen McKeown |
| Abstract | Neural networks are one of the most popular approaches for many natural language processing tasks such as sentiment analysis. They often outperform traditional machine learning models and achieve the state-of-art results on most tasks. However, many existing deep learning models are complex, difficult to train and provide a limited improvement over simpler methods. We propose a simple, robust and powerful model for sentiment classification. This model outperforms many deep learning models and achieves comparable results to other deep learning models with complex architectures on sentiment analysis datasets. We publish the code online. |
| Tasks | Sentiment Analysis |
| Published | 2017-08-13 |
| URL | http://arxiv.org/abs/1708.03940v1 |
| http://arxiv.org/pdf/1708.03940v1.pdf | |
| PWC | https://paperswithcode.com/paper/leveraging-sparse-and-dense-feature |
| Repo | |
| Framework | |
The origins of Zipf’s meaning-frequency law
| Title | The origins of Zipf’s meaning-frequency law |
| Authors | Ramon Ferrer-i-Cancho, Michael S. Vitevitch |
| Abstract | In his pioneering research, G. K. Zipf observed that more frequent words tend to have more meanings, and showed that the number of meanings of a word grows as the square root of its frequency. He derived this relationship from two assumptions: that words follow Zipf’s law for word frequencies (a power law dependency between frequency and rank) and Zipf’s law of meaning distribution (a power law dependency between number of meanings and rank). Here we show that a single assumption on the joint probability of a word and a meaning suffices to infer Zipf’s meaning-frequency law or relaxed versions. Interestingly, this assumption can be justified as the outcome of a biased random walk in the process of mental exploration. |
| Tasks | |
| Published | 2017-12-30 |
| URL | http://arxiv.org/abs/1801.00168v1 |
| http://arxiv.org/pdf/1801.00168v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-origins-of-zipfs-meaning-frequency-law |
| Repo | |
| Framework | |
Bayesian Optimisation for Safe Navigation under Localisation Uncertainty
| Title | Bayesian Optimisation for Safe Navigation under Localisation Uncertainty |
| Authors | Rafael Oliveira, Lionel Ott, Vitor Guizilini, Fabio Ramos |
| Abstract | In outdoor environments, mobile robots are required to navigate through terrain with varying characteristics, some of which might significantly affect the integrity of the platform. Ideally, the robot should be able to identify areas that are safe for navigation based on its own percepts about the environment while avoiding damage to itself. Bayesian optimisation (BO) has been successfully applied to the task of learning a model of terrain traversability while guiding the robot through more traversable areas. An issue, however, is that localisation uncertainty can end up guiding the robot to unsafe areas and distort the model being learnt. In this paper, we address this problem and present a novel method that allows BO to consider localisation uncertainty by applying a Gaussian process model for uncertain inputs as a prior. We evaluate the proposed method in simulation and in experiments with a real robot navigating over rough terrain and compare it against standard BO methods. |
| Tasks | Bayesian Optimisation |
| Published | 2017-09-07 |
| URL | http://arxiv.org/abs/1709.02169v2 |
| http://arxiv.org/pdf/1709.02169v2.pdf | |
| PWC | https://paperswithcode.com/paper/bayesian-optimisation-for-safe-navigation |
| Repo | |
| Framework | |
Consistent Kernel Density Estimation with Non-Vanishing Bandwidth
| Title | Consistent Kernel Density Estimation with Non-Vanishing Bandwidth |
| Authors | Efrén Cruz Cortés, Clayton Scott |
| Abstract | Consistency of the kernel density estimator requires that the kernel bandwidth tends to zero as the sample size grows. In this paper we investigate the question of whether consistency is possible when the bandwidth is fixed, if we consider a more general class of weighted KDEs. To answer this question in the affirmative, we introduce the fixed-bandwidth KDE (fbKDE), obtained by solving a quadratic program, and prove that it consistently estimates any continuous square-integrable density. We also establish rates of convergence for the fbKDE with radial kernels and the box kernel under appropriate smoothness assumptions. Furthermore, in an experimental study we demonstrate that the fbKDE compares favorably to the standard KDE and the previously proposed variable bandwidth KDE. |
| Tasks | Density Estimation |
| Published | 2017-05-24 |
| URL | http://arxiv.org/abs/1705.08921v2 |
| http://arxiv.org/pdf/1705.08921v2.pdf | |
| PWC | https://paperswithcode.com/paper/consistent-kernel-density-estimation-with-non |
| Repo | |
| Framework | |
Learning to Factor Policies and Action-Value Functions: Factored Action Space Representations for Deep Reinforcement learning
| Title | Learning to Factor Policies and Action-Value Functions: Factored Action Space Representations for Deep Reinforcement learning |
| Authors | Sahil Sharma, Aravind Suresh, Rahul Ramesh, Balaraman Ravindran |
| Abstract | Deep Reinforcement Learning (DRL) methods have performed well in an increasing numbering of high-dimensional visual decision making domains. Among all such visual decision making problems, those with discrete action spaces often tend to have underlying compositional structure in the said action space. Such action spaces often contain actions such as go left, go up as well as go diagonally up and left (which is a composition of the former two actions). The representations of control policies in such domains have traditionally been modeled without exploiting this inherent compositional structure in the action spaces. We propose a new learning paradigm, Factored Action space Representations (FAR) wherein we decompose a control policy learned using a Deep Reinforcement Learning Algorithm into independent components, analogous to decomposing a vector in terms of some orthogonal basis vectors. This architectural modification of the control policy representation allows the agent to learn about multiple actions simultaneously, while executing only one of them. We demonstrate that FAR yields considerable improvements on top of two DRL algorithms in Atari 2600: FARA3C outperforms A3C (Asynchronous Advantage Actor Critic) in 9 out of 14 tasks and FARAQL outperforms AQL (Asynchronous n-step Q-Learning) in 9 out of 13 tasks. |
| Tasks | Decision Making, Q-Learning |
| Published | 2017-05-20 |
| URL | http://arxiv.org/abs/1705.07269v1 |
| http://arxiv.org/pdf/1705.07269v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-to-factor-policies-and-action-value |
| Repo | |
| Framework | |
Asynchronous Parallel Bayesian Optimisation via Thompson Sampling
| Title | Asynchronous Parallel Bayesian Optimisation via Thompson Sampling |
| Authors | Kirthevasan Kandasamy, Akshay Krishnamurthy, Jeff Schneider, Barnabas Poczos |
| Abstract | We design and analyse variations of the classical Thompson sampling (TS) procedure for Bayesian optimisation (BO) in settings where function evaluations are expensive, but can be performed in parallel. Our theoretical analysis shows that a direct application of the sequential Thompson sampling algorithm in either synchronous or asynchronous parallel settings yields a surprisingly powerful result: making $n$ evaluations distributed among $M$ workers is essentially equivalent to performing $n$ evaluations in sequence. Further, by modeling the time taken to complete a function evaluation, we show that, under a time constraint, asynchronously parallel TS achieves asymptotically lower regret than both the synchronous and sequential versions. These results are complemented by an experimental analysis, showing that asynchronous TS outperforms a suite of existing parallel BO algorithms in simulations and in a hyper-parameter tuning application in convolutional neural networks. In addition to these, the proposed procedure is conceptually and computationally much simpler than existing work for parallel BO. |
| Tasks | Bayesian Optimisation |
| Published | 2017-05-25 |
| URL | http://arxiv.org/abs/1705.09236v1 |
| http://arxiv.org/pdf/1705.09236v1.pdf | |
| PWC | https://paperswithcode.com/paper/asynchronous-parallel-bayesian-optimisation |
| Repo | |
| Framework | |
Improved Neural Text Attribute Transfer with Non-parallel Data
| Title | Improved Neural Text Attribute Transfer with Non-parallel Data |
| Authors | Igor Melnyk, Cicero Nogueira dos Santos, Kahini Wadhawan, Inkit Padhi, Abhishek Kumar |
| Abstract | Text attribute transfer using non-parallel data requires methods that can perform disentanglement of content and linguistic attributes. In this work, we propose multiple improvements over the existing approaches that enable the encoder-decoder framework to cope with the text attribute transfer from non-parallel data. We perform experiments on the sentiment transfer task using two datasets. For both datasets, our proposed method outperforms a strong baseline in two of the three employed evaluation metrics. |
| Tasks | Text Attribute Transfer |
| Published | 2017-11-26 |
| URL | http://arxiv.org/abs/1711.09395v2 |
| http://arxiv.org/pdf/1711.09395v2.pdf | |
| PWC | https://paperswithcode.com/paper/improved-neural-text-attribute-transfer-with |
| Repo | |
| Framework | |
Deep artifact learning for compressed sensing and parallel MRI
| Title | Deep artifact learning for compressed sensing and parallel MRI |
| Authors | Dongwook Lee, Jaejun Yoo, Jong Chul Ye |
| Abstract | Purpose: Compressed sensing MRI (CS-MRI) from single and parallel coils is one of the powerful ways to reduce the scan time of MR imaging with performance guarantee. However, the computational costs are usually expensive. This paper aims to propose a computationally fast and accurate deep learning algorithm for the reconstruction of MR images from highly down-sampled k-space data. Theory: Based on the topological analysis, we show that the data manifold of the aliasing artifact is easier to learn from a uniform subsampling pattern with additional low-frequency k-space data. Thus, we develop deep aliasing artifact learning networks for the magnitude and phase images to estimate and remove the aliasing artifacts from highly accelerated MR acquisition. Methods: The aliasing artifacts are directly estimated from the distorted magnitude and phase images reconstructed from subsampled k-space data so that we can get an aliasing-free images by subtracting the estimated aliasing artifact from corrupted inputs. Moreover, to deal with the globally distributed aliasing artifact, we develop a multi-scale deep neural network with a large receptive field. Results: The experimental results confirm that the proposed deep artifact learning network effectively estimates and removes the aliasing artifacts. Compared to existing CS methods from single and multi-coli data, the proposed network shows minimal errors by removing the coherent aliasing artifacts. Furthermore, the computational time is by order of magnitude faster. Conclusion: As the proposed deep artifact learning network immediately generates accurate reconstruction, it has great potential for clinical applications. |
| Tasks | |
| Published | 2017-03-03 |
| URL | http://arxiv.org/abs/1703.01120v1 |
| http://arxiv.org/pdf/1703.01120v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-artifact-learning-for-compressed-sensing |
| Repo | |
| Framework | |
Spectral-Spatial Feature Extraction and Classification by ANN Supervised with Center Loss in Hyperspectral Imagery
| Title | Spectral-Spatial Feature Extraction and Classification by ANN Supervised with Center Loss in Hyperspectral Imagery |
| Authors | Alan J. X. Guo, Fei Zhu |
| Abstract | In this paper, we propose a spectral-spatial feature extraction and classification framework based on artificial neuron network (ANN) in the context of hyperspectral imagery. With limited labeled samples, only spectral information is exploited for training and spatial context is integrated posteriorly at the testing stage. Taking advantage of recent advances in face recognition, a joint supervision symbol that combines softmax loss and center loss is adopted to train the proposed network, by which intra-class features are gathered while inter-class variations are enlarged. Based on the learned architecture, the extracted spectrum-based features are classified by a center classifier. Moreover, to fuse the spectral and spatial information, an adaptive spectral-spatial center classifier is developed, where multiscale neighborhoods are considered simultaneously, and the final label is determined using an adaptive voting strategy. Finally, experimental results on three well-known datasets validate the effectiveness of the proposed methods compared with the state-of-the-art approaches. |
| Tasks | Face Recognition |
| Published | 2017-11-20 |
| URL | http://arxiv.org/abs/1711.07141v1 |
| http://arxiv.org/pdf/1711.07141v1.pdf | |
| PWC | https://paperswithcode.com/paper/spectral-spatial-feature-extraction-and |
| Repo | |
| Framework | |
Deep learning: Technical introduction
| Title | Deep learning: Technical introduction |
| Authors | Thomas Epelbaum |
| Abstract | This note presents in a technical though hopefully pedagogical way the three most common forms of neural network architectures: Feedforward, Convolutional and Recurrent. For each network, their fundamental building blocks are detailed. The forward pass and the update rules for the backpropagation algorithm are then derived in full. |
| Tasks | |
| Published | 2017-09-05 |
| URL | http://arxiv.org/abs/1709.01412v2 |
| http://arxiv.org/pdf/1709.01412v2.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-technical-introduction |
| Repo | |
| Framework | |
A Finite Element Computational Framework for Active Contours on Graphs
| Title | A Finite Element Computational Framework for Active Contours on Graphs |
| Authors | Nikolaos Kolotouros, Petros Maragos |
| Abstract | In this paper we present a new framework for the solution of active contour models on graphs. With the use of the Finite Element Method we generalize active contour models on graphs and reduce the problem from a partial differential equation to the solution of a sparse non-linear system. Additionally, we extend the proposed framework to solve models where the curve evolution is locally constrained around its current location. Based on the previous extension, we propose a fast algorithm for the solution of a wide range active contour models. Last, we present a supervised extension of Geodesic Active Contours for image segmentation and provide experimental evidence for the effectiveness of our framework. |
| Tasks | Semantic Segmentation |
| Published | 2017-10-12 |
| URL | http://arxiv.org/abs/1710.04346v1 |
| http://arxiv.org/pdf/1710.04346v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-finite-element-computational-framework-for |
| Repo | |
| Framework | |
Retinal Fluid Segmentation and Detection in Optical Coherence Tomography Images using Fully Convolutional Neural Network
| Title | Retinal Fluid Segmentation and Detection in Optical Coherence Tomography Images using Fully Convolutional Neural Network |
| Authors | Donghuan Lu, Morgan Heisler, Sieun Lee, Gavin Ding, Marinko V. Sarunic, Mirza Faisal Beg |
| Abstract | As a non-invasive imaging modality, optical coherence tomography (OCT) can provide micrometer-resolution 3D images of retinal structures. Therefore it is commonly used in the diagnosis of retinal diseases associated with edema in and under the retinal layers. In this paper, a new framework is proposed for the task of fluid segmentation and detection in retinal OCT images. Based on the raw images and layers segmented by a graph-cut algorithm, a fully convolutional neural network was trained to recognize and label the fluid pixels. Random forest classification was performed on the segmented fluid regions to detect and reject the falsely labeled fluid regions. The leave-one-out cross validation experiments on the RETOUCH database show that our method performs well in both segmentation (mean Dice: 0.7317) and detection (mean AUC: 0.985) tasks. |
| Tasks | |
| Published | 2017-10-13 |
| URL | http://arxiv.org/abs/1710.04778v1 |
| http://arxiv.org/pdf/1710.04778v1.pdf | |
| PWC | https://paperswithcode.com/paper/retinal-fluid-segmentation-and-detection-in |
| Repo | |
| Framework | |
Compressed Video Action Recognition
| Title | Compressed Video Action Recognition |
| Authors | Chao-Yuan Wu, Manzil Zaheer, Hexiang Hu, R. Manmatha, Alexander J. Smola, Philipp Krähenbühl |
| Abstract | Training robust deep video representations has proven to be much more challenging than learning deep image representations. This is in part due to the enormous size of raw video streams and the high temporal redundancy; the true and interesting signal is often drowned in too much irrelevant data. Motivated by that the superfluous information can be reduced by up to two orders of magnitude by video compression (using H.264, HEVC, etc.), we propose to train a deep network directly on the compressed video. This representation has a higher information density, and we found the training to be easier. In addition, the signals in a compressed video provide free, albeit noisy, motion information. We propose novel techniques to use them effectively. Our approach is about 4.6 times faster than Res3D and 2.7 times faster than ResNet-152. On the task of action recognition, our approach outperforms all the other methods on the UCF-101, HMDB-51, and Charades dataset. |
| Tasks | Action Classification, Action Recognition In Videos, Temporal Action Localization, Video Compression |
| Published | 2017-12-02 |
| URL | http://arxiv.org/abs/1712.00636v2 |
| http://arxiv.org/pdf/1712.00636v2.pdf | |
| PWC | https://paperswithcode.com/paper/compressed-video-action-recognition |
| Repo | |
| Framework | |
A Unified RGB-T Saliency Detection Benchmark: Dataset, Baselines, Analysis and A Novel Approach
| Title | A Unified RGB-T Saliency Detection Benchmark: Dataset, Baselines, Analysis and A Novel Approach |
| Authors | Chenglong Li, Guizhao Wang, Yunpeng Ma, Aihua Zheng, Bin Luo, Jin Tang |
| Abstract | Despite significant progress, image saliency detection still remains a challenging task in complex scenes and environments. Integrating multiple different but complementary cues, like RGB and Thermal (RGB-T), may be an effective way for boosting saliency detection performance. The current research in this direction, however, is limited by the lack of a comprehensive benchmark. This work contributes such a RGB-T image dataset, which includes 821 spatially aligned RGB-T image pairs and their ground truth annotations for saliency detection purpose. The image pairs are with high diversity recorded under different scenes and environmental conditions, and we annotate 11 challenges on these image pairs for performing the challenge-sensitive analysis for different saliency detection algorithms. We also implement 3 kinds of baseline methods with different modality inputs to provide a comprehensive comparison platform. With this benchmark, we propose a novel approach, multi-task manifold ranking with cross-modality consistency, for RGB-T saliency detection. In particular, we introduce a weight for each modality to describe the reliability, and integrate them into the graph-based manifold ranking algorithm to achieve adaptive fusion of different source data. Moreover, we incorporate the cross-modality consistent constraints to integrate different modalities collaboratively. For the optimization, we design an efficient algorithm to iteratively solve several subproblems with closed-form solutions. Extensive experiments against other baseline methods on the newly created benchmark demonstrate the effectiveness of the proposed approach, and we also provide basic insights and potential future research directions for RGB-T saliency detection. |
| Tasks | Saliency Detection |
| Published | 2017-01-11 |
| URL | http://arxiv.org/abs/1701.02829v1 |
| http://arxiv.org/pdf/1701.02829v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-unified-rgb-t-saliency-detection-benchmark |
| Repo | |
| Framework | |
Data-dependent Generalization Bounds for Multi-class Classification
| Title | Data-dependent Generalization Bounds for Multi-class Classification |
| Authors | Yunwen Lei, Urun Dogan, Ding-Xuan Zhou, Marius Kloft |
| Abstract | In this paper, we study data-dependent generalization error bounds exhibiting a mild dependency on the number of classes, making them suitable for multi-class learning with a large number of label classes. The bounds generally hold for empirical multi-class risk minimization algorithms using an arbitrary norm as regularizer. Key to our analysis are new structural results for multi-class Gaussian complexities and empirical $\ell_\infty$-norm covering numbers, which exploit the Lipschitz continuity of the loss function with respect to the $\ell_2$- and $\ell_\infty$-norm, respectively. We establish data-dependent error bounds in terms of complexities of a linear function class defined on a finite set induced by training examples, for which we show tight lower and upper bounds. We apply the results to several prominent multi-class learning machines, exhibiting a tighter dependency on the number of classes than the state of the art. For instance, for the multi-class SVM by Crammer and Singer (2002), we obtain a data-dependent bound with a logarithmic dependency which significantly improves the previous square-root dependency. Experimental results are reported to verify the effectiveness of our theoretical findings. |
| Tasks | |
| Published | 2017-06-29 |
| URL | http://arxiv.org/abs/1706.09814v2 |
| http://arxiv.org/pdf/1706.09814v2.pdf | |
| PWC | https://paperswithcode.com/paper/data-dependent-generalization-bounds-for |
| Repo | |
| Framework | |
