Paper Group ANR 24
SyncGAN: Synchronize the Latent Space of Cross-modal Generative Adversarial Networks. SLIC Based Digital Image Enlargement. Title-Guided Encoding for Keyphrase Generation. Neural-Augmented Static Analysis of Android Communication. Image contrast enhancement using fuzzy logic. Variational Approximation Error in Bayesian Non-negative Matrix Factoriza …
SyncGAN: Synchronize the Latent Space of Cross-modal Generative Adversarial Networks
| Title | SyncGAN: Synchronize the Latent Space of Cross-modal Generative Adversarial Networks |
| Authors | Wen-Cheng Chen, Chien-Wen Chen, Min-Chun Hu |
| Abstract | Generative adversarial network (GAN) has achieved impressive success on cross-domain generation, but it faces difficulty in cross-modal generation due to the lack of a common distribution between heterogeneous data. Most existing methods of conditional based cross-modal GANs adopt the strategy of one-directional transfer and have achieved preliminary success on text-to-image transfer. Instead of learning the transfer between different modalities, we aim to learn a synchronous latent space representing the cross-modal common concept. A novel network component named synchronizer is proposed in this work to judge whether the paired data is synchronous/corresponding or not, which can constrain the latent space of generators in the GANs. Our GAN model, named as SyncGAN, can successfully generate synchronous data (e.g., a pair of image and sound) from identical random noise. For transforming data from one modality to another, we recover the latent code by inverting the mappings of a generator and use it to generate data of different modality. In addition, the proposed model can achieve semi-supervised learning, which makes our model more flexible for practical applications. |
| Tasks | |
| Published | 2018-04-02 |
| URL | http://arxiv.org/abs/1804.00410v1 |
| http://arxiv.org/pdf/1804.00410v1.pdf | |
| PWC | https://paperswithcode.com/paper/syncgan-synchronize-the-latent-space-of-cross |
| Repo | |
| Framework | |
SLIC Based Digital Image Enlargement
| Title | SLIC Based Digital Image Enlargement |
| Authors | M. Z. F. Amara, R. Bandara, Thushari Silva |
| Abstract | Low resolution image enhancement is a classical computer vision problem. Selecting the best method to reconstruct an image to a higher resolution with the limited data available in the low-resolution image is quite a challenge. A major drawback from the existing enlargement techniques is the introduction of color bleeding while interpolating pixels over the edges that separate distinct colors in an image. The color bleeding causes to accentuate the edges with new colors as a result of blending multiple colors over adjacent regions. This paper proposes a novel approach to mitigate the color bleeding by segmenting the homogeneous color regions of the image using Simple Linear Iterative Clustering (SLIC) and applying a higher order interpolation technique separately on the isolated segments. The interpolation at the boundaries of each of the isolated segments is handled by using a morphological operation. The approach is evaluated by comparing against several frequently used image enlargement methods such as bilinear and bicubic interpolation by means of Peak Signal-to-Noise-Ratio (PSNR) value. The results obtained exhibit that the proposed method outperforms the baseline methods by means of PSNR and also mitigates the color bleeding at the edges which improves the overall appearance. |
| Tasks | Image Enhancement |
| Published | 2018-10-05 |
| URL | http://arxiv.org/abs/1810.02643v1 |
| http://arxiv.org/pdf/1810.02643v1.pdf | |
| PWC | https://paperswithcode.com/paper/slic-based-digital-image-enlargement |
| Repo | |
| Framework | |
Title-Guided Encoding for Keyphrase Generation
| Title | Title-Guided Encoding for Keyphrase Generation |
| Authors | Wang Chen, Yifan Gao, Jiani Zhang, Irwin King, Michael R. Lyu |
| Abstract | Keyphrase generation (KG) aims to generate a set of keyphrases given a document, which is a fundamental task in natural language processing (NLP). Most previous methods solve this problem in an extractive manner, while recently, several attempts are made under the generative setting using deep neural networks. However, the state-of-the-art generative methods simply treat the document title and the document main body equally, ignoring the leading role of the title to the overall document. To solve this problem, we introduce a new model called Title-Guided Network (TG-Net) for automatic keyphrase generation task based on the encoder-decoder architecture with two new features: (i) the title is additionally employed as a query-like input, and (ii) a title-guided encoder gathers the relevant information from the title to each word in the document. Experiments on a range of KG datasets demonstrate that our model outperforms the state-of-the-art models with a large margin, especially for documents with either very low or very high title length ratios. |
| Tasks | |
| Published | 2018-08-26 |
| URL | http://arxiv.org/abs/1808.08575v5 |
| http://arxiv.org/pdf/1808.08575v5.pdf | |
| PWC | https://paperswithcode.com/paper/title-guided-encoding-for-keyphrase |
| Repo | |
| Framework | |
Neural-Augmented Static Analysis of Android Communication
| Title | Neural-Augmented Static Analysis of Android Communication |
| Authors | Jinman Zhao, Aws Albarghouthi, Vaibhav Rastogi, Somesh Jha, Damien Octeau |
| Abstract | We address the problem of discovering communication links between applications in the popular Android mobile operating system, an important problem for security and privacy in Android. Any scalable static analysis in this complex setting is bound to produce an excessive amount of false-positives, rendering it impractical. To improve precision, we propose to augment static analysis with a trained neural-network model that estimates the probability that a communication link truly exists. We describe a neural-network architecture that encodes abstractions of communicating objects in two applications and estimates the probability with which a link indeed exists. At the heart of our architecture are type-directed encoders (TDE), a general framework for elegantly constructing encoders of a compound data type by recursively composing encoders for its constituent types. We evaluate our approach on a large corpus of Android applications, and demonstrate that it achieves very high accuracy. Further, we conduct thorough interpretability studies to understand the internals of the learned neural networks. |
| Tasks | |
| Published | 2018-09-11 |
| URL | http://arxiv.org/abs/1809.04059v1 |
| http://arxiv.org/pdf/1809.04059v1.pdf | |
| PWC | https://paperswithcode.com/paper/neural-augmented-static-analysis-of-android |
| Repo | |
| Framework | |
Image contrast enhancement using fuzzy logic
| Title | Image contrast enhancement using fuzzy logic |
| Authors | Sandeep Joshi, Samrudh Kumar |
| Abstract | Image enhancement is a method of improving the quality of an image and contrast is a major aspect. Traditional methods of contrast enhancement like histogram equalization results in over/under enhancement of the image especially a lower resolution one. This paper aims at developing a new Fuzzy Inference System to enhance the contrast of the low resolution images overcoming the shortcomings of the traditional methods. Results obtained using both the approaches are compared. |
| Tasks | Image Enhancement |
| Published | 2018-09-12 |
| URL | http://arxiv.org/abs/1809.04529v1 |
| http://arxiv.org/pdf/1809.04529v1.pdf | |
| PWC | https://paperswithcode.com/paper/image-contrast-enhancement-using-fuzzy-logic |
| Repo | |
| Framework | |
Variational Approximation Error in Bayesian Non-negative Matrix Factorization
| Title | Variational Approximation Error in Bayesian Non-negative Matrix Factorization |
| Authors | Naoki Hayashi |
| Abstract | Non-negative matrix factorization (NMF) is a knowledge discovery method that is used in many fields. Variational inference and Gibbs sampling methods for it are also wellknown. However, the variational approximation error has not been clarified yet, because NMF is not statistically regular and the prior distribution used in variational Bayesian NMF (VBNMF) has zero or divergence points. In this paper, using algebraic geometrical methods, we theoretically analyze the difference in negative log evidence (a.k.a. free energy) between VBNMF and Bayesian NMF, i.e., the Kullback-Leibler divergence between the variational posterior and the true posterior. We derive an upper bound for the learning coefficient (a.k.a. the real log canonical threshold) in Bayesian NMF. By using the upper bound, we find a lower bound for the approximation error, asymptotically. The result quantitatively shows how well the VBNMF algorithm can approximate Bayesian NMF; the lower bound depends on the hyperparameters and the true nonnegative rank. A numerical experiment demonstrates the theoretical result. |
| Tasks | |
| Published | 2018-09-09 |
| URL | https://arxiv.org/abs/1809.02963v4 |
| https://arxiv.org/pdf/1809.02963v4.pdf | |
| PWC | https://paperswithcode.com/paper/variational-approximation-accuracy-in |
| Repo | |
| Framework | |
Adversarial Training of End-to-end Speech Recognition Using a Criticizing Language Model
| Title | Adversarial Training of End-to-end Speech Recognition Using a Criticizing Language Model |
| Authors | Alexander H. Liu, Hung-yi Lee, Lin-shan Lee |
| Abstract | In this paper we proposed a novel Adversarial Training (AT) approach for end-to-end speech recognition using a Criticizing Language Model (CLM). In this way the CLM and the automatic speech recognition (ASR) model can challenge and learn from each other iteratively to improve the performance. Since the CLM only takes the text as input, huge quantities of unpaired text data can be utilized in this approach within end-to-end training. Moreover, AT can be applied to any end-to-end ASR model using any deep-learning-based language modeling frameworks, and compatible with any existing end-to-end decoding method. Initial results with an example experimental setup demonstrated the proposed approach is able to gain consistent improvements efficiently from auxiliary text data under different scenarios. |
| Tasks | End-To-End Speech Recognition, Language Modelling, Speech Recognition |
| Published | 2018-11-02 |
| URL | http://arxiv.org/abs/1811.00787v1 |
| http://arxiv.org/pdf/1811.00787v1.pdf | |
| PWC | https://paperswithcode.com/paper/adversarial-training-of-end-to-end-speech |
| Repo | |
| Framework | |
Flatland: a Lightweight First-Person 2-D Environment for Reinforcement Learning
| Title | Flatland: a Lightweight First-Person 2-D Environment for Reinforcement Learning |
| Authors | Hugo Caselles-Dupré, Louis Annabi, Oksana Hagen, Michael Garcia-Ortiz, David Filliat |
| Abstract | Flatland is a simple, lightweight environment for fast prototyping and testing of reinforcement learning agents. It is of lower complexity compared to similar 3D platforms (e.g. DeepMind Lab or VizDoom), but emulates physical properties of the real world, such as continuity, multi-modal partially-observable states with first-person view and coherent physics. We propose to use it as an intermediary benchmark for problems related to Lifelong Learning. Flatland is highly customizable and offers a wide range of task difficulty to extensively evaluate the properties of artificial agents. We experiment with three reinforcement learning baseline agents and show that they can rapidly solve a navigation task in Flatland. A video of an agent acting in Flatland is available here: https://youtu.be/I5y6Y2ZypdA. |
| Tasks | |
| Published | 2018-09-03 |
| URL | http://arxiv.org/abs/1809.00510v2 |
| http://arxiv.org/pdf/1809.00510v2.pdf | |
| PWC | https://paperswithcode.com/paper/flatland-a-lightweight-first-person-2-d |
| Repo | |
| Framework | |
Reinforcement Learning in R
| Title | Reinforcement Learning in R |
| Authors | Nicolas Pröllochs, Stefan Feuerriegel |
| Abstract | Reinforcement learning refers to a group of methods from artificial intelligence where an agent performs learning through trial and error. It differs from supervised learning, since reinforcement learning requires no explicit labels; instead, the agent interacts continuously with its environment. That is, the agent starts in a specific state and then performs an action, based on which it transitions to a new state and, depending on the outcome, receives a reward. Different strategies (e.g. Q-learning) have been proposed to maximize the overall reward, resulting in a so-called policy, which defines the best possible action in each state. Mathematically, this process can be formalized by a Markov decision process and it has been implemented by packages in R; however, there is currently no package available for reinforcement learning. As a remedy, this paper demonstrates how to perform reinforcement learning in R and, for this purpose, introduces the ReinforcementLearning package. The package provides a remarkably flexible framework and is easily applied to a wide range of different problems. We demonstrate its use by drawing upon common examples from the literature (e.g. finding optimal game strategies). |
| Tasks | Q-Learning |
| Published | 2018-09-29 |
| URL | http://arxiv.org/abs/1810.00240v1 |
| http://arxiv.org/pdf/1810.00240v1.pdf | |
| PWC | https://paperswithcode.com/paper/reinforcement-learning-in-r |
| Repo | |
| Framework | |
Real-time Progressive 3D Semantic Segmentation for Indoor Scene
| Title | Real-time Progressive 3D Semantic Segmentation for Indoor Scene |
| Authors | Quang-Hieu Pham, Binh-Son Hua, Duc Thanh Nguyen, Sai-Kit Yeung |
| Abstract | The widespread adoption of autonomous systems such as drones and assistant robots has created a need for real-time high-quality semantic scene segmentation. In this paper, we propose an efficient yet robust technique for on-the-fly dense reconstruction and semantic segmentation of 3D indoor scenes. To guarantee (near) real-time performance, our method is built atop an efficient super-voxel clustering method and a conditional random field with higher-order constraints from structural and object cues, enabling progressive dense semantic segmentation without any precomputation. We extensively evaluate our method on different indoor scenes including kitchens, offices, and bedrooms in the SceneNN and ScanNet datasets and show that our technique consistently produces state-of-the-art segmentation results in both qualitative and quantitative experiments. |
| Tasks | 3D Semantic Segmentation, Scene Segmentation, Semantic Segmentation |
| Published | 2018-04-01 |
| URL | http://arxiv.org/abs/1804.00257v5 |
| http://arxiv.org/pdf/1804.00257v5.pdf | |
| PWC | https://paperswithcode.com/paper/real-time-progressive-3d-semantic |
| Repo | |
| Framework | |
Fractional Multiscale Fusion-based De-hazing
| Title | Fractional Multiscale Fusion-based De-hazing |
| Authors | Uche A. Nnolim |
| Abstract | This report presents the results of a proposed multi-scale fusion-based single image de-hazing algorithm, which can also be used for underwater image enhancement. Furthermore, the algorithm was designed for very fast operation and minimal run-time. The proposed scheme is the faster than existing algorithms for both de-hazing and underwater image enhancement and amenable to digital hardware implementation. Results indicate mostly consistent and good results for both categories of images when compared with other algorithms from the literature. |
| Tasks | Image Enhancement |
| Published | 2018-08-29 |
| URL | http://arxiv.org/abs/1808.09697v1 |
| http://arxiv.org/pdf/1808.09697v1.pdf | |
| PWC | https://paperswithcode.com/paper/fractional-multiscale-fusion-based-de-hazing |
| Repo | |
| Framework | |
A Novel Color Image Enhancement Method by the Transformation of Color Images to 2-D Grayscale Images
| Title | A Novel Color Image Enhancement Method by the Transformation of Color Images to 2-D Grayscale Images |
| Authors | Artyom M Grigoryan, Aparna John, Sos S Agaian |
| Abstract | A novel method of color image enhancement is proposed, in which three or four color channels of the image are transformed to one channel 2-D grayscale image. This paper describes different models of such transformations in the RGB and other color models. Color image enhancement is achieved by enhancing first the transformed grayscale image and, then, transforming back the grayscale image into the colors. The color image enhancement is done on the transformed 2-D grayscale image rather than on the color image. New algorithms of color image enhancement are described in both frequency and time domains. The enhancement by this novel method shows good results. The enhancement of the image is measured with respect to the metric referred to as the Color Enhancement Measure Estimation (CEME). |
| Tasks | Image Enhancement |
| Published | 2018-07-20 |
| URL | http://arxiv.org/abs/1807.07962v1 |
| http://arxiv.org/pdf/1807.07962v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-novel-color-image-enhancement-method-by-the |
| Repo | |
| Framework | |
Efficient Rank Minimization via Solving Non-convexPenalties by Iterative Shrinkage-Thresholding Algorithm
| Title | Efficient Rank Minimization via Solving Non-convexPenalties by Iterative Shrinkage-Thresholding Algorithm |
| Authors | Zaiyi Chen |
| Abstract | Rank minimization (RM) is a wildly investigated task of finding solutions by exploiting low-rank structure of parameter matrices. Recently, solving RM problem by leveraging non-convex relaxations has received significant attention. It has been demonstrated by some theoretical and experimental work that non-convex relaxation, e.g. Truncated Nuclear Norm Regularization (TNNR) and Reweighted Nuclear Norm Regularization (RNNR), can provide a better approximation of original problems than convex relaxations. However, designing an efficient algorithm with theoretical guarantee remains a challenging problem. In this paper, we propose a simple but efficient proximal-type method, namely Iterative Shrinkage-Thresholding Algorithm(ISTA), with concrete analysis to solve rank minimization problems with both non-convex weighted and reweighted nuclear norm as low-rank regularizers. Theoretically, the proposed method could converge to the critical point under very mild assumptions with the rate in the order of $O(1/T)$. Moreover, the experimental results on both synthetic data and real world data sets show that proposed algorithm outperforms state-of-arts in both efficiency and accuracy. |
| Tasks | |
| Published | 2018-09-14 |
| URL | http://arxiv.org/abs/1809.05292v1 |
| http://arxiv.org/pdf/1809.05292v1.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-rank-minimization-via-solving-non |
| Repo | |
| Framework | |
Exact Reconstruction of Euclidean Distance Geometry Problem Using Low-rank Matrix Completion
| Title | Exact Reconstruction of Euclidean Distance Geometry Problem Using Low-rank Matrix Completion |
| Authors | Abiy Tasissa, Rongjie Lai |
| Abstract | The Euclidean distance geometry problem arises in a wide variety of applications, from determining molecular conformations in computational chemistry to localization in sensor networks. When the distance information is incomplete, the problem can be formulated as a nuclear norm minimization problem. In this paper, this minimization program is recast as a matrix completion problem of a low-rank $r$ Gram matrix with respect to a suitable basis. The well known restricted isometry property can not be satisfied in this scenario. Instead, a dual basis approach is introduced to theoretically analyze the reconstruction problem. If the Gram matrix satisfies certain coherence conditions with parameter $\nu$, the main result shows that the underlying configuration of $n$ points can be recovered with very high probability from $O(nr\nu\log^{2}(n))$ uniformly random samples. Computationally, simple and fast algorithms are designed to solve the Euclidean distance geometry problem. Numerical tests on different three dimensional data and protein molecules validate effectiveness and efficiency of the proposed algorithms. |
| Tasks | Low-Rank Matrix Completion, Matrix Completion |
| Published | 2018-04-12 |
| URL | http://arxiv.org/abs/1804.04310v2 |
| http://arxiv.org/pdf/1804.04310v2.pdf | |
| PWC | https://paperswithcode.com/paper/exact-reconstruction-of-euclidean-distance |
| Repo | |
| Framework | |
A Rprop-Neural-Network-Based PV Maximum Power Point Tracking Algorithm with Short-Circuit Current Limitation
| Title | A Rprop-Neural-Network-Based PV Maximum Power Point Tracking Algorithm with Short-Circuit Current Limitation |
| Authors | Yao Cui, Zhehan Yi, Jiajun Duan, Di Shi, Zhiwei Wang |
| Abstract | This paper proposes a resilient-backpropagation-neural-network-(Rprop-NN) based algorithm for Photovoltaic (PV) maximum power point tracking (MPPT). A supervision mechanism is proposed to calibrate the Rprop-NN-MPPT reference and limit short-circuit current caused by incorrect prediction. Conventional MPPT algorithms (e.g., perturb and observe (P&O), hill climbing, and incremental conductance (Inc-Cond) etc.) are trial-and-error-based, which may result in steady-state oscillations and loss of tracking direction under fast-changing ambient environment. In addition, partial shading is also a challenge due to the difficulty of finding the global maximum power point on a multi-peak characteristic curve. As an attempt to address the aforementioned issues, a novel Rprop-NN MPPT algorithm is developed and elaborated in this work. Multiple case studies are carried out to verify the effectiveness of the proposed algorithm. |
| Tasks | |
| Published | 2018-11-29 |
| URL | http://arxiv.org/abs/1811.12541v2 |
| http://arxiv.org/pdf/1811.12541v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-rprop-neural-network-based-pv-maximum-power |
| Repo | |
| Framework | |
