October 19, 2019

2918 words 14 mins read

Paper Group ANR 375

MelanoGANs: High Resolution Skin Lesion Synthesis with GANs. Consistent CCG Parsing over Multiple Sentences for Improved Logical Reasoning. Robust Student Network Learning. Using Deep Autoencoders for Facial Expression Recognition. Single Image Dehazing Based on Generic Regularity. Learning a Latent Space of Multitrack Measures. Strategies for Lang …

MelanoGANs: High Resolution Skin Lesion Synthesis with GANs


Title	MelanoGANs: High Resolution Skin Lesion Synthesis with GANs
Authors	Christoph Baur, Shadi Albarqouni, Nassir Navab
Abstract	Generative Adversarial Networks (GANs) have been successfully used to synthesize realistically looking images of faces, scenery and even medical images. Unfortunately, they usually require large training datasets, which are often scarce in the medical field, and to the best of our knowledge GANs have been only applied for medical image synthesis at fairly low resolution. However, many state-of-the-art machine learning models operate on high resolution data as such data carries indispensable, valuable information. In this work, we try to generate realistically looking high resolution images of skin lesions with GANs, using only a small training dataset of 2000 samples. The nature of the data allows us to do a direct comparison between the image statistics of the generated samples and the real dataset. We both quantitatively and qualitatively compare state-of-the-art GAN architectures such as DCGAN and LAPGAN against a modification of the latter for the task of image generation at a resolution of 256x256px. Our investigation shows that we can approximate the real data distribution with all of the models, but we notice major differences when visually rating sample realism, diversity and artifacts. In a set of use-case experiments on skin lesion classification, we further show that we can successfully tackle the problem of heavy class imbalance with the help of synthesized high resolution melanoma samples.
Tasks	Image Generation, Skin Lesion Classification
Published	2018-04-12
URL	http://arxiv.org/abs/1804.04338v1
PDF	http://arxiv.org/pdf/1804.04338v1.pdf
PWC	https://paperswithcode.com/paper/melanogans-high-resolution-skin-lesion
Repo
Framework

Consistent CCG Parsing over Multiple Sentences for Improved Logical Reasoning


Title	Consistent CCG Parsing over Multiple Sentences for Improved Logical Reasoning
Authors	Masashi Yoshikawa, Koji Mineshima, Hiroshi Noji, Daisuke Bekki
Abstract	In formal logic-based approaches to Recognizing Textual Entailment (RTE), a Combinatory Categorial Grammar (CCG) parser is used to parse input premises and hypotheses to obtain their logical formulas. Here, it is important that the parser processes the sentences consistently; failing to recognize a similar syntactic structure results in inconsistent predicate argument structures among them, in which case the succeeding theorem proving is doomed to failure. In this work, we present a simple method to extend an existing CCG parser to parse a set of sentences consistently, which is achieved with an inter-sentence modeling with Markov Random Fields (MRF). When combined with existing logic-based systems, our method always shows improvement in the RTE experiments on English and Japanese languages.
Tasks	Automated Theorem Proving, Natural Language Inference
Published	2018-04-19
URL	http://arxiv.org/abs/1804.07068v1
PDF	http://arxiv.org/pdf/1804.07068v1.pdf
PWC	https://paperswithcode.com/paper/consistent-ccg-parsing-over-multiple
Repo
Framework

Robust Student Network Learning


Title	Robust Student Network Learning
Authors	Tianyu Guo, Chang Xu, Shiyi He, Boxin Shi, Chao Xu, Dacheng Tao
Abstract	Deep neural networks bring in impressive accuracy in various applications, but the success often relies on the heavy network architecture. Taking well-trained heavy networks as teachers, classical teacher-student learning paradigm aims to learn a student network that is lightweight yet accurate. In this way, a portable student network with significantly fewer parameters can achieve a considerable accuracy which is comparable to that of teacher network. However, beyond accuracy, robustness of the learned student network against perturbation is also essential for practical uses. Existing teacher-student learning frameworks mainly focus on accuracy and compression ratios, but ignore the robustness. In this paper, we make the student network produce more confident predictions with the help of the teacher network, and analyze the lower bound of the perturbation that will destroy the confidence of the student network. Two important objectives regarding prediction scores and gradients of examples are developed to maximize this lower bound, so as to enhance the robustness of the student network without sacrificing the performance. Experiments on benchmark datasets demonstrate the efficiency of the proposed approach to learn robust student networks which have satisfying accuracy and compact sizes.
Tasks
Published	2018-07-30
URL	http://arxiv.org/abs/1807.11158v2
PDF	http://arxiv.org/pdf/1807.11158v2.pdf
PWC	https://paperswithcode.com/paper/robust-student-network-learning
Repo
Framework

Using Deep Autoencoders for Facial Expression Recognition


Title	Using Deep Autoencoders for Facial Expression Recognition
Authors	Muhammad Usman, Siddique Latif, Junaid Qadir
Abstract	Feature descriptors involved in image processing are generally manually chosen and high dimensional in nature. Selecting the most important features is a very crucial task for systems like facial expression recognition. This paper investigates the performance of deep autoencoders for feature selection and dimension reduction for facial expression recognition on multiple levels of hidden layers. The features extracted from the stacked autoencoder outperformed when compared to other state-of-the-art feature selection and dimension reduction techniques.
Tasks	Dimensionality Reduction, Facial Expression Recognition, Feature Selection
Published	2018-01-25
URL	http://arxiv.org/abs/1801.08329v1
PDF	http://arxiv.org/pdf/1801.08329v1.pdf
PWC	https://paperswithcode.com/paper/using-deep-autoencoders-for-facial-expression
Repo
Framework

Single Image Dehazing Based on Generic Regularity


Title	Single Image Dehazing Based on Generic Regularity
Authors	Kushal Borkar, Snehasis Mukherjee
Abstract	This paper proposes a novel technique for single image dehazing. Most of the state-of-the-art methods for single image dehazing relies either on Dark Channel Prior (DCP) or on Color line. The proposed method combines the two different approaches. We initially compute the dark channel prior and then apply a Nearest-Neighbor (NN) based regularization technique to obtain a smooth transmission map of the hazy image. We consider the effect of airlight on the image by using the color line model to assess the commitment of airlight in each patch of the image and interpolate at the local neighborhood where the estimate is unreliable. The NN based regularization of the DCP can remove the haze, whereas, the color line based interpolation of airlight effect makes the proposed system robust against the variation of haze within an image due to multiple light sources. The proposed method is tested on benchmark datasets and shows promising results compared to the state-of-the-art, including the deep learning based methods, which require a huge computational setup. Moreover, the proposed method outperforms the recent deep learning based methods when applied on images with sky regions.
Tasks	Image Dehazing, Single Image Dehazing
Published	2018-08-26
URL	http://arxiv.org/abs/1808.08610v1
PDF	http://arxiv.org/pdf/1808.08610v1.pdf
PWC	https://paperswithcode.com/paper/single-image-dehazing-based-on-generic
Repo
Framework

Learning a Latent Space of Multitrack Measures


Title	Learning a Latent Space of Multitrack Measures
Authors	Ian Simon, Adam Roberts, Colin Raffel, Jesse Engel, Curtis Hawthorne, Douglas Eck
Abstract	Discovering and exploring the underlying structure of multi-instrumental music using learning-based approaches remains an open problem. We extend the recent MusicVAE model to represent multitrack polyphonic measures as vectors in a latent space. Our approach enables several useful operations such as generating plausible measures from scratch, interpolating between measures in a musically meaningful way, and manipulating specific musical attributes. We also introduce chord conditioning, which allows all of these operations to be performed while keeping harmony fixed, and allows chords to be changed while maintaining musical “style”. By generating a sequence of measures over a predefined chord progression, our model can produce music with convincing long-term structure. We demonstrate that our latent space model makes it possible to intuitively control and generate musical sequences with rich instrumentation (see https://goo.gl/s2N7dV for generated audio).
Tasks
Published	2018-06-01
URL	http://arxiv.org/abs/1806.00195v1
PDF	http://arxiv.org/pdf/1806.00195v1.pdf
PWC	https://paperswithcode.com/paper/learning-a-latent-space-of-multitrack
Repo
Framework

Strategies for Language Identification in Code-Mixed Low Resource Languages


Title	Strategies for Language Identification in Code-Mixed Low Resource Languages
Authors	Soumil Mandal, Sankalp Sanand
Abstract	In recent years, substantial work has been done on language tagging of code-mixed data, but most of them use large amounts of data to build their models. In this article, we present three strategies to build a word level language tagger for code-mixed data using very low resources. Each of them secured an accuracy higher than our baseline model, and the best performing system got an accuracy around 91%. Combining all, the ensemble system achieved an accuracy of around 92.6%.
Tasks	Language Identification
Published	2018-10-16
URL	http://arxiv.org/abs/1810.07156v2
PDF	http://arxiv.org/pdf/1810.07156v2.pdf
PWC	https://paperswithcode.com/paper/strategies-for-language-identification-in
Repo
Framework

Generalized Inverse Optimization through Online Learning


Title	Generalized Inverse Optimization through Online Learning
Authors	Chaosheng Dong, Yiran Chen, Bo Zeng
Abstract	Inverse optimization is a powerful paradigm for learning preferences and restrictions that explain the behavior of a decision maker, based on a set of external signal and the corresponding decision pairs. However, most inverse optimization algorithms are designed specifically in batch setting, where all the data is available in advance. As a consequence, there has been rare use of these methods in an online setting suitable for real-time applications. In this paper, we propose a general framework for inverse optimization through online learning. Specifically, we develop an online learning algorithm that uses an implicit update rule which can handle noisy data. Moreover, under additional regularity assumptions in terms of the data and the model, we prove that our algorithm converges at a rate of $\mathcal{O}(1/\sqrt{T})$ and is statistically consistent. In our experiments, we show the online learning approach can learn the parameters with great accuracy and is very robust to noises, and achieves a dramatic improvement in computational efficacy over the batch learning approach.
Tasks
Published	2018-10-03
URL	http://arxiv.org/abs/1810.01920v2
PDF	http://arxiv.org/pdf/1810.01920v2.pdf
PWC	https://paperswithcode.com/paper/generalized-inverse-optimization-through
Repo
Framework

Recent advances and opportunities in scene classification of aerial images with deep models


Title	Recent advances and opportunities in scene classification of aerial images with deep models
Authors	Fan Hu, Gui-Song Xia, Wen Yang, Liangpei Zhang
Abstract	Scene classification is a fundamental task in interpretation of remote sensing images, and has become an active research topic in remote sensing community due to its important role in a wide range of applications. Over the past years, tremendous efforts have been made for developing powerful approaches for scene classification of remote sensing images, evolving from the traditional bag-of-visual-words model to the new generation deep convolutional neural networks (CNNs). The deep CNN based methods have exhibited remarkable breakthrough on performance, dramatically outperforming previous methods which strongly rely on hand-crafted features. However, performance with deep CNNs has gradually plateaued on existing public scene datasets, due to the notable drawbacks of these datasets, such as the small scale and low-diversity of training samples. Therefore, to promote the development of new methods and move the scene classification task a step further, we deeply discuss the existing problems in scene classification task, and accordingly present three open directions. We believe these potential directions will be instructive for the researchers in this field.
Tasks	Scene Classification
Published	2018-06-04
URL	http://arxiv.org/abs/1806.00899v1
PDF	http://arxiv.org/pdf/1806.00899v1.pdf
PWC	https://paperswithcode.com/paper/recent-advances-and-opportunities-in-scene
Repo
Framework

The Neural Painter: Multi-Turn Image Generation


Title	The Neural Painter: Multi-Turn Image Generation
Authors	Ryan Y. Benmalek, Claire Cardie, Serge Belongie, Xiadong He, Jianfeng Gao
Abstract	In this work we combine two research threads from Vision/ Graphics and Natural Language Processing to formulate an image generation task conditioned on attributes in a multi-turn setting. By multiturn, we mean the image is generated in a series of steps of user-specified conditioning information. Our proposed approach is practically useful and offers insights into neural interpretability. We introduce a framework that includes a novel training algorithm as well as model improvements built for the multi-turn setting. We demonstrate that this framework generates a sequence of images that match the given conditioning information and that this task is useful for more detailed benchmarking and analysis of conditional image generation methods.
Tasks	Conditional Image Generation, Image Generation
Published	2018-06-16
URL	http://arxiv.org/abs/1806.06183v1
PDF	http://arxiv.org/pdf/1806.06183v1.pdf
PWC	https://paperswithcode.com/paper/the-neural-painter-multi-turn-image
Repo
Framework

Investigating Label Noise Sensitivity of Convolutional Neural Networks for Fine Grained Audio Signal Labelling


Title	Investigating Label Noise Sensitivity of Convolutional Neural Networks for Fine Grained Audio Signal Labelling
Authors	Rainer Kelz, Gerhard Widmer
Abstract	We measure the effect of small amounts of systematic and random label noise caused by slightly misaligned ground truth labels in a fine grained audio signal labeling task. The task we choose to demonstrate these effects on is also known as framewise polyphonic transcription or note quantized multi-f0 estimation, and transforms a monaural audio signal into a sequence of note indicator labels. It will be shown that even slight misalignments have clearly apparent effects, demonstrating a great sensitivity of convolutional neural networks to label noise. The implications are clear: when using convolutional neural networks for fine grained audio signal labeling tasks, great care has to be taken to ensure that the annotations have precise timing, and are free from systematic or random error as much as possible - even small misalignments will have a noticeable impact.
Tasks
Published	2018-05-28
URL	http://arxiv.org/abs/1805.10880v1
PDF	http://arxiv.org/pdf/1805.10880v1.pdf
PWC	https://paperswithcode.com/paper/investigating-label-noise-sensitivity-of
Repo
Framework

Automatic Detection of Node-Replication Attack in Vehicular Ad-hoc Networks


Title	Automatic Detection of Node-Replication Attack in Vehicular Ad-hoc Networks
Authors	Mohammed GH. I. AL Zamil
Abstract	Recent advances in smart cities applications enforce security threads such as node replication attacks. Such attack is take place when the attacker plants a replicated network node within the network. Vehicular Ad hoc networks are connecting sensors that have limited resources and required the response time to be as low as possible. In this type networks, traditional detection algorithms of node replication attacks are not efficient. In this paper, we propose an initial idea to apply a newly adapted statistical methodology that can detect node replication attacks with high performance as compared to state-of-the-art techniques. We provide a sufficient description of this methodology and a road-map for testing and experiment its performance.
Tasks
Published	2018-07-26
URL	http://arxiv.org/abs/1807.10079v3
PDF	http://arxiv.org/pdf/1807.10079v3.pdf
PWC	https://paperswithcode.com/paper/automatic-detection-of-node-replication
Repo
Framework

RADMPC: A Fast Decentralized Approach for Chance-Constrained Multi-Vehicle Path-Planning


Title	RADMPC: A Fast Decentralized Approach for Chance-Constrained Multi-Vehicle Path-Planning
Authors	Aaron Huang, Benjamin J. Ayton, Brian C. Williams
Abstract	Robust multi-vehicle path-planning is important for ensuring the safety of multi-vehicle systems in applications like transportation, search and rescue, and robotic exploration. Chance-constrained methods like Iterative Risk Allocation (IRA)\cite{IRA} have been developed for situations where environmental disturbances are unbounded. However, chance-constrained methods for the multi-vehicle case generally use centralized strategies where the vehicle set is planned with couplings between all vehicle pairs. This approach is intractable as fleet size increases because computation time is exponential with respect to the number of vehicles being planned over due to a polynomial increase in coupling constraints between vehicle pairs. We present a faster approach for chance-constrained multi-vehicle path-planning that relies upon a decentralized path-planning method called Risk-Aware Decentralized Model Predictive Control (RADMPC) to rapidly approximate a centralized IRA approach. The RADMPC approximation is evaluated for vehicle interactions to determine the vehicle sets that should be planned in a coupled manner. Applying IRA to the smaller vehicle sets determined from the RADMPC approximation rapidly plans safe paths for the entire fleet. A Monte Carlo simulation analysis demonstrates the correctness of our approach and a significant improvement in computation time compared to a centralized IRA approach.
Tasks
Published	2018-11-25
URL	http://arxiv.org/abs/1811.09914v1
PDF	http://arxiv.org/pdf/1811.09914v1.pdf
PWC	https://paperswithcode.com/paper/radmpc-a-fast-decentralized-approach-for
Repo
Framework

Classifying neuromorphic data using a deep learning framework for image classification


Title	Classifying neuromorphic data using a deep learning framework for image classification
Authors	Roshan Gopalakrishnan, Yansong Chua, Laxmi R Iyer
Abstract	In the field of artificial intelligence, neuromorphic computing has been around for several decades. Deep learning has however made much recent progress such that it consistently outperforms neuromorphic learning algorithms in classification tasks in terms of accuracy. Specifically in the field of image classification, neuromorphic computing has been traditionally using either the temporal or rate code for encoding static images in datasets into spike trains. It is only till recently, that neuromorphic vision sensors are widely used by the neuromorphic research community, and provides an alternative to such encoding methods. Since then, several neuromorphic datasets as obtained by applying such sensors on image datasets (e.g. the neuromorphic CALTECH 101) have been introduced. These data are encoded in spike trains and hence seem ideal for benchmarking of neuromorphic learning algorithms. Specifically, we train a deep learning framework used for image classification on the CALTECH 101 and a collapsed version of the neuromorphic CALTECH 101 datasets. We obtained an accuracy of 91.66% and 78.01% for the CALTECH 101 and neuromorphic CALTECH 101 datasets respectively. For CALTECH 101, our accuracy is close to the best reported accuracy, while for neuromorphic CALTECH 101, it outperforms the last best reported accuracy by over 10%. This raises the question of the suitability of such datasets as benchmarks for neuromorphic learning algorithms.
Tasks	Image Classification
Published	2018-07-02
URL	http://arxiv.org/abs/1807.00578v1
PDF	http://arxiv.org/pdf/1807.00578v1.pdf
PWC	https://paperswithcode.com/paper/classifying-neuromorphic-data-using-a-deep
Repo
Framework

Regret Bounds for Stochastic Combinatorial Multi-Armed Bandits with Linear Space Complexity


Title	Regret Bounds for Stochastic Combinatorial Multi-Armed Bandits with Linear Space Complexity
Authors	Mridul Agarwal, Vaneet Aggarwal
Abstract	Many real-world problems face the dilemma of choosing best $K$ out of $N$ options at a given time instant. This setup can be modelled as combinatorial bandit which chooses $K$ out of $N$ arms at each time, with an aim to achieve an efficient tradeoff between exploration and exploitation. This is the first work for combinatorial bandit where the reward received can be a non-linear function of the chosen $K$ arms. The direct use of multi-armed bandit requires choosing among $N$-choose-$K$ options making the state space large. In this paper, we present a novel algorithm which is computationally efficient and the storage is linear in $N$. The proposed algorithm is a divide-and-conquer based strategy, that we call CMAB-SM. Further, the proposed algorithm achieves a regret bound of $\tilde O(K^\frac{1}{2}N^\frac{1}{3}T^\frac{2}{3})$ for a time horizon $T$, which is sub-linear in all parameters $T$, $N$, and $K$. The evaluation results on different reward functions and arm distribution functions show significantly improved performance as compared to standard multi-armed bandit approach with $\binom{N}{K}$ choices.
Tasks	Multi-Armed Bandits
Published	2018-11-29
URL	http://arxiv.org/abs/1811.11925v1
PDF	http://arxiv.org/pdf/1811.11925v1.pdf
PWC	https://paperswithcode.com/paper/regret-bounds-for-stochastic-combinatorial
Repo
Framework