Paper Group ANR 1043
Learning-Based Dequantization For Image Restoration Against Extremely Poor Illumination. On the Relationship between Data Efficiency and Error for Uncertainty Sampling. End-to-End Learning of Driving Models with Surround-View Cameras and Route Planners. A simple blind-denoising filter inspired by electrically coupled photoreceptors in the retina. O …
Learning-Based Dequantization For Image Restoration Against Extremely Poor Illumination
| Title | Learning-Based Dequantization For Image Restoration Against Extremely Poor Illumination |
| Authors | Chang Liu, Xiaolin Wu, Xiao Shu |
| Abstract | All existing image enhancement methods, such as HDR tone mapping, cannot recover A/D quantization losses due to insufficient or excessive lighting, (underflow and overflow problems). The loss of image details due to A/D quantization is complete and it cannot be recovered by traditional image processing methods, but the modern data-driven machine learning approach offers a much needed cure to the problem. In this work we propose a novel approach to restore and enhance images acquired in low and uneven lighting. First, the ill illumination is algorithmically compensated by emulating the effects of artificial supplementary lighting. Then a DCNN trained using only synthetic data recovers the missing detail caused by quantization. |
| Tasks | Image Enhancement, Image Restoration, Quantization |
| Published | 2018-03-05 |
| URL | http://arxiv.org/abs/1803.01532v2 |
| http://arxiv.org/pdf/1803.01532v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-based-dequantization-for-image |
| Repo | |
| Framework | |
On the Relationship between Data Efficiency and Error for Uncertainty Sampling
| Title | On the Relationship between Data Efficiency and Error for Uncertainty Sampling |
| Authors | Stephen Mussmann, Percy Liang |
| Abstract | While active learning offers potential cost savings, the actual data efficiency—the reduction in amount of labeled data needed to obtain the same error rate—observed in practice is mixed. This paper poses a basic question: when is active learning actually helpful? We provide an answer for logistic regression with the popular active learning algorithm, uncertainty sampling. Empirically, on 21 datasets from OpenML, we find a strong inverse correlation between data efficiency and the error rate of the final classifier. Theoretically, we show that for a variant of uncertainty sampling, the asymptotic data efficiency is within a constant factor of the inverse error rate of the limiting classifier. |
| Tasks | Active Learning |
| Published | 2018-06-15 |
| URL | http://arxiv.org/abs/1806.06123v1 |
| http://arxiv.org/pdf/1806.06123v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-relationship-between-data-efficiency |
| Repo | |
| Framework | |
End-to-End Learning of Driving Models with Surround-View Cameras and Route Planners
| Title | End-to-End Learning of Driving Models with Surround-View Cameras and Route Planners |
| Authors | Simon Hecker, Dengxin Dai, Luc Van Gool |
| Abstract | For human drivers, having rear and side-view mirrors is vital for safe driving. They deliver a more complete view of what is happening around the car. Human drivers also heavily exploit their mental map for navigation. Nonetheless, several methods have been published that learn driving models with only a front-facing camera and without a route planner. This lack of information renders the self-driving task quite intractable. We investigate the problem in a more realistic setting, which consists of a surround-view camera system with eight cameras, a route planner, and a CAN bus reader. In particular, we develop a sensor setup that provides data for a 360-degree view of the area surrounding the vehicle, the driving route to the destination, and low-level driving maneuvers (e.g. steering angle and speed) by human drivers. With such a sensor setup we collect a new driving dataset, covering diverse driving scenarios and varying weather/illumination conditions. Finally, we learn a novel driving model by integrating information from the surround-view cameras and the route planner. Two route planners are exploited: 1) by representing the planned routes on OpenStreetMap as a stack of GPS coordinates, and 2) by rendering the planned routes on TomTom Go Mobile and recording the progression into a video. Our experiments show that: 1) 360-degree surround-view cameras help avoid failures made with a single front-view camera, in particular for city driving and intersection scenarios; and 2) route planners help the driving task significantly, especially for steering angle prediction. |
| Tasks | |
| Published | 2018-03-27 |
| URL | http://arxiv.org/abs/1803.10158v2 |
| http://arxiv.org/pdf/1803.10158v2.pdf | |
| PWC | https://paperswithcode.com/paper/end-to-end-learning-of-driving-models-with |
| Repo | |
| Framework | |
A simple blind-denoising filter inspired by electrically coupled photoreceptors in the retina
| Title | A simple blind-denoising filter inspired by electrically coupled photoreceptors in the retina |
| Authors | Yang Yue, Liuyuan He, Gan He, Jian. K. Liu, Kai Du, Yonghong Tian, Tiejun Huang |
| Abstract | Photoreceptors in the retina are coupled by electrical synapses called “gap junctions”. It has long been established that gap junctions increase the signal-to-noise ratio of photoreceptors. Inspired by electrically coupled photoreceptors, we introduced a simple filter, the PR-filter, with only one variable. On BSD68 dataset, PR-filter showed outstanding performance in SSIM during blind denoising tasks. It also significantly improved the performance of state-of-the-art convolutional neural network blind denosing on non-Gaussian noise. The performance of keeping more details might be attributed to small receptive field of the photoreceptors. |
| Tasks | Denoising |
| Published | 2018-06-15 |
| URL | http://arxiv.org/abs/1806.05882v4 |
| http://arxiv.org/pdf/1806.05882v4.pdf | |
| PWC | https://paperswithcode.com/paper/a-simple-blind-denoising-filter-inspired-by |
| Repo | |
| Framework | |
Optimized Computation Offloading Performance in Virtual Edge Computing Systems via Deep Reinforcement Learning
| Title | Optimized Computation Offloading Performance in Virtual Edge Computing Systems via Deep Reinforcement Learning |
| Authors | Xianfu Chen, Honggang Zhang, Celimuge Wu, Shiwen Mao, Yusheng Ji, Mehdi Bennis |
| Abstract | To improve the quality of computation experience for mobile devices, mobile-edge computing (MEC) is a promising paradigm by providing computing capabilities in close proximity within a sliced radio access network (RAN), which supports both traditional communication and MEC services. Nevertheless, the design of computation offloading policies for a virtual MEC system remains challenging. Specifically, whether to execute a computation task at the mobile device or to offload it for MEC server execution should adapt to the time-varying network dynamics. In this paper, we consider MEC for a representative mobile user in an ultra-dense sliced RAN, where multiple base stations (BSs) are available to be selected for computation offloading. The problem of solving an optimal computation offloading policy is modelled as a Markov decision process, where our objective is to maximize the long-term utility performance whereby an offloading decision is made based on the task queue state, the energy queue state as well as the channel qualities between MU and BSs. To break the curse of high dimensionality in state space, we first propose a double deep Q-network (DQN) based strategic computation offloading algorithm to learn the optimal policy without knowing a priori knowledge of network dynamics. Then motivated by the additive structure of the utility function, a Q-function decomposition technique is combined with the double DQN, which leads to novel learning algorithm for the solving of stochastic computation offloading. Numerical experiments show that our proposed learning algorithms achieve a significant improvement in computation offloading performance compared with the baseline policies. |
| Tasks | |
| Published | 2018-05-16 |
| URL | http://arxiv.org/abs/1805.06146v1 |
| http://arxiv.org/pdf/1805.06146v1.pdf | |
| PWC | https://paperswithcode.com/paper/optimized-computation-offloading-performance |
| Repo | |
| Framework | |
Situated Mapping of Sequential Instructions to Actions with Single-step Reward Observation
| Title | Situated Mapping of Sequential Instructions to Actions with Single-step Reward Observation |
| Authors | Alane Suhr, Yoav Artzi |
| Abstract | We propose a learning approach for mapping context-dependent sequential instructions to actions. We address the problem of discourse and state dependencies with an attention-based model that considers both the history of the interaction and the state of the world. To train from start and goal states without access to demonstrations, we propose SESTRA, a learning algorithm that takes advantage of single-step reward observations and immediate expected reward maximization. We evaluate on the SCONE domains, and show absolute accuracy improvements of 9.8%-25.3% across the domains over approaches that use high-level logical representations. |
| Tasks | |
| Published | 2018-05-25 |
| URL | http://arxiv.org/abs/1805.10209v2 |
| http://arxiv.org/pdf/1805.10209v2.pdf | |
| PWC | https://paperswithcode.com/paper/situated-mapping-of-sequential-instructions |
| Repo | |
| Framework | |
Butterfly-Net: Optimal Function Representation Based on Convolutional Neural Networks
| Title | Butterfly-Net: Optimal Function Representation Based on Convolutional Neural Networks |
| Authors | Yingzhou Li, Xiuyuan Cheng, Jianfeng Lu |
| Abstract | Deep networks, especially Convolutional Neural Networks (CNNs), have been successfully applied in various areas of machine learning as well as to challenging problems in other scientific and engineering fields. This paper introduces Butterfly-net, a low-complexity CNN with structured and sparse across-channel connections, which aims at an optimal hierarchical function representation of the input signal. Theoretical analysis of the approximation power of Butterfly-net to the Fourier representation of input data shows that the error decays exponentially as the depth increases. Due to the ability of Butterfly-net to approximate Fourier and local Fourier transforms, the result can be used for approximation upper bound for CNNs in a large class of problems. The analytical results are validated by numerical experiments on the approximation of a 1D Fourier kernel and of the energy of 1D and 2D Poisson’s equations. Butterfly-net with trained parameters outperforms the hard-coded Butterfly-net and achieves similar accuracy as the trained CNN but with much less parameters. In addition, better robustness of Butterfly-net against CNN is demonstrated when the distribution of the input data has domain shift. |
| Tasks | |
| Published | 2018-05-18 |
| URL | https://arxiv.org/abs/1805.07451v3 |
| https://arxiv.org/pdf/1805.07451v3.pdf | |
| PWC | https://paperswithcode.com/paper/butterfly-net-optimal-function-representation |
| Repo | |
| Framework | |
Towards Robust Neural Machine Translation
| Title | Towards Robust Neural Machine Translation |
| Authors | Yong Cheng, Zhaopeng Tu, Fandong Meng, Junjie Zhai, Yang Liu |
| Abstract | Small perturbations in the input can severely distort intermediate representations and thus impact translation quality of neural machine translation (NMT) models. In this paper, we propose to improve the robustness of NMT models with adversarial stability training. The basic idea is to make both the encoder and decoder in NMT models robust against input perturbations by enabling them to behave similarly for the original input and its perturbed counterpart. Experimental results on Chinese-English, English-German and English-French translation tasks show that our approaches can not only achieve significant improvements over strong NMT systems but also improve the robustness of NMT models. |
| Tasks | Machine Translation |
| Published | 2018-05-16 |
| URL | http://arxiv.org/abs/1805.06130v1 |
| http://arxiv.org/pdf/1805.06130v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-robust-neural-machine-translation |
| Repo | |
| Framework | |
Homonym Detection in Curated Bibliographies: Learning from dblp’s Experience (full version)
| Title | Homonym Detection in Curated Bibliographies: Learning from dblp’s Experience (full version) |
| Authors | Marcel R. Ackermann, Florian Reitz |
| Abstract | Identifying (and fixing) homonymous and synonymous author profiles is one of the major tasks of curating personalized bibliographic metadata repositories like the dblp computer science bibliography. In this paper, we present and evaluate a machine learning approach to identify homonymous author bibliographies using a simple multilayer perceptron setup. We train our model on a novel gold-standard data set derived from the past years of active, manual curation at the dblp computer science bibliography. |
| Tasks | |
| Published | 2018-06-15 |
| URL | http://arxiv.org/abs/1806.06017v1 |
| http://arxiv.org/pdf/1806.06017v1.pdf | |
| PWC | https://paperswithcode.com/paper/homonym-detection-in-curated-bibliographies |
| Repo | |
| Framework | |
Optimal Data Driven Resource Allocation under Multi-Armed Bandit Observations
| Title | Optimal Data Driven Resource Allocation under Multi-Armed Bandit Observations |
| Authors | Apostolos N. Burnetas, Odysseas Kanavetas, Michael N. Katehakis |
| Abstract | This paper introduces the first asymptotically optimal strategy for a multi armed bandit (MAB) model under side constraints. The side constraints model situations in which bandit activations are limited by the availability of certain resources that are replenished at a constant rate. The main result involves the derivation of an asymptotic lower bound for the regret of feasible uniformly fast policies and the construction of policies that achieve this lower bound, under pertinent conditions. Further, we provide the explicit form of such policies for the case in which the unknown distributions are Normal with unknown means and known variances, for the case of Normal distributions with unknown means and unknown variances and for the case of arbitrary discrete distributions with finite support. |
| Tasks | |
| Published | 2018-11-30 |
| URL | http://arxiv.org/abs/1811.12852v2 |
| http://arxiv.org/pdf/1811.12852v2.pdf | |
| PWC | https://paperswithcode.com/paper/optimal-data-driven-resource-allocation-under |
| Repo | |
| Framework | |
AiDroid: When Heterogeneous Information Network Marries Deep Neural Network for Real-time Android Malware Detection
| Title | AiDroid: When Heterogeneous Information Network Marries Deep Neural Network for Real-time Android Malware Detection |
| Authors | Yanfang Ye, Shifu Hou, Lingwei Chen, Jingwei Lei, Wenqiang Wan, Jiabin Wang, Qi Xiong, Fudong Shao |
| Abstract | The explosive growth and increasing sophistication of Android malware call for new defensive techniques that are capable of protecting mobile users against novel threats. In this paper, we first extract the runtime Application Programming Interface (API) call sequences from Android apps, and then analyze higher-level semantic relations within the ecosystem to comprehensively characterize the apps. To model different types of entities (i.e., app, API, IMEI, signature, affiliation) and the rich semantic relations among them, we then construct a structural heterogeneous information network (HIN) and present meta-path based approach to depict the relatedness over apps. To efficiently classify nodes (e.g., apps) in the constructed HIN, we propose the HinLearning method to first obtain in-sample node embeddings and then learn representations of out-of-sample nodes without rerunning/adjusting HIN embeddings at the first attempt. Afterwards, we design a deep neural network (DNN) classifier taking the learned HIN representations as inputs for Android malware detection. A comprehensive experimental study on the large-scale real sample collections from Tencent Security Lab is performed to compare various baselines. Promising experimental results demonstrate that our developed system AiDroid which integrates our proposed method outperforms others in real-time Android malware detection. AiDroid has already been incorporated into Tencent Mobile Security product that serves millions of users worldwide. |
| Tasks | Android Malware Detection, Malware Detection, Mobile Security |
| Published | 2018-11-02 |
| URL | https://arxiv.org/abs/1811.01027v2 |
| https://arxiv.org/pdf/1811.01027v2.pdf | |
| PWC | https://paperswithcode.com/paper/aidroid-when-heterogeneous-information |
| Repo | |
| Framework | |
Neural Semi-Markov Conditional Random Fields for Robust Character-Based Part-of-Speech Tagging
| Title | Neural Semi-Markov Conditional Random Fields for Robust Character-Based Part-of-Speech Tagging |
| Authors | Apostolos Kemos, Heike Adel, Hinrich Schütze |
| Abstract | Character-level models of tokens have been shown to be effective at dealing with within-token noise and out-of-vocabulary words. But these models still rely on correct token boundaries. In this paper, we propose a novel end-to-end character-level model and demonstrate its effectiveness in multilingual settings and when token boundaries are noisy. Our model is a semi-Markov conditional random field with neural networks for character and segment representation. It requires no tokenizer. The model matches state-of-the-art baselines for various languages and significantly outperforms them on a noisy English version of a part-of-speech tagging benchmark dataset. Our code and the noisy dataset are publicly available at http://cistern.cis.lmu.de/semiCRF. |
| Tasks | Part-Of-Speech Tagging |
| Published | 2018-08-13 |
| URL | https://arxiv.org/abs/1808.04208v3 |
| https://arxiv.org/pdf/1808.04208v3.pdf | |
| PWC | https://paperswithcode.com/paper/neural-semi-markov-conditional-random-fields |
| Repo | |
| Framework | |
Exploring Adversarial Examples in Malware Detection
| Title | Exploring Adversarial Examples in Malware Detection |
| Authors | Octavian Suciu, Scott E. Coull, Jeffrey Johns |
| Abstract | The convolutional neural network (CNN) architecture is increasingly being applied to new domains, such as malware detection, where it is able to learn malicious behavior from raw bytes extracted from executables. These architectures reach impressive performance with no feature engineering effort involved, but their robustness against active attackers is yet to be understood. Such malware detectors could face a new attack vector in the form of adversarial interference with the classification model. Existing evasion attacks intended to cause misclassification on test-time instances, which have been extensively studied for image classifiers, are not applicable because of the input semantics that prevents arbitrary changes to the binaries. This paper explores the area of adversarial examples for malware detection. By training an existing model on a production-scale dataset, we show that some previous attacks are less effective than initially reported, while simultaneously highlighting architectural weaknesses that facilitate new attack strategies for malware classification. Finally, we explore how generalizable different attack strategies are, the trade-offs when aiming to increase their effectiveness, and the transferability of single-step attacks. |
| Tasks | Feature Engineering, Malware Classification, Malware Detection |
| Published | 2018-10-18 |
| URL | http://arxiv.org/abs/1810.08280v3 |
| http://arxiv.org/pdf/1810.08280v3.pdf | |
| PWC | https://paperswithcode.com/paper/exploring-adversarial-examples-in-malware |
| Repo | |
| Framework | |
Co-Clustering via Information-Theoretic Markov Aggregation
| Title | Co-Clustering via Information-Theoretic Markov Aggregation |
| Authors | Clemens Bloechl, Rana Ali Amjad, Bernhard C. Geiger |
| Abstract | We present an information-theoretic cost function for co-clustering, i.e., for simultaneous clustering of two sets based on similarities between their elements. By constructing a simple random walk on the corresponding bipartite graph, our cost function is derived from a recently proposed generalized framework for information-theoretic Markov chain aggregation. The goal of our cost function is to minimize relevant information loss, hence it connects to the information bottleneck formalism. Moreover, via the connection to Markov aggregation, our cost function is not ad hoc, but inherits its justification from the operational qualities associated with the corresponding Markov aggregation problem. We furthermore show that, for appropriate parameter settings, our cost function is identical to well-known approaches from the literature, such as Information-Theoretic Co-Clustering of Dhillon et al. Hence, understanding the influence of this parameter admits a deeper understanding of the relationship between previously proposed information-theoretic cost functions. We highlight some strengths and weaknesses of the cost function for different parameters. We also illustrate the performance of our cost function, optimized with a simple sequential heuristic, on several synthetic and real-world data sets, including the Newsgroup20 and the MovieLens100k data sets. |
| Tasks | |
| Published | 2018-01-02 |
| URL | http://arxiv.org/abs/1801.00584v2 |
| http://arxiv.org/pdf/1801.00584v2.pdf | |
| PWC | https://paperswithcode.com/paper/co-clustering-via-information-theoretic |
| Repo | |
| Framework | |
User-Guided Clustering in Heterogeneous Information Networks via Motif-Based Comprehensive Transcription
| Title | User-Guided Clustering in Heterogeneous Information Networks via Motif-Based Comprehensive Transcription |
| Authors | Yu Shi, Xinwei He, Naijing Zhang, Carl Yang, Jiawei Han |
| Abstract | Heterogeneous information networks (HINs) with rich semantics are ubiquitous in real-world applications. For a given HIN, many reasonable clustering results with distinct semantic meaning can simultaneously exist. User-guided clustering is hence of great practical value for HINs where users provide labels to a small portion of nodes. To cater to a broad spectrum of user guidance evidenced by different expected clustering results, carefully exploiting the signals residing in the data is potentially useful. Meanwhile, as one type of complex networks, HINs often encapsulate higher-order interactions that reflect the interlocked nature among nodes and edges. Network motifs, sometimes referred to as meta-graphs, have been used as tools to capture such higher-order interactions and reveal the many different semantics. We therefore approach the problem of user-guided clustering in HINs with network motifs. In this process, we identify the utility and importance of directly modeling higher-order interactions without collapsing them to pairwise interactions. To achieve this, we comprehensively transcribe the higher-order interaction signals to a series of tensors via motifs and propose the MoCHIN model based on joint non-negative tensor factorization. This approach applies to arbitrarily many, arbitrary forms of HIN motifs. An inference algorithm with speed-up methods is also proposed to tackle the challenge that tensor size grows exponentially as the number of nodes in a motif increases. We validate the effectiveness of the proposed method on two real-world datasets and three tasks, and MoCHIN outperforms all baselines in three evaluation tasks under three different metrics. Additional experiments demonstrated the utility of motifs and the benefit of directly modeling higher-order information especially when user guidance is limited. |
| Tasks | |
| Published | 2018-11-28 |
| URL | https://arxiv.org/abs/1811.11320v3 |
| https://arxiv.org/pdf/1811.11320v3.pdf | |
| PWC | https://paperswithcode.com/paper/higher-order-clustering-in-heterogeneous |
| Repo | |
| Framework | |
