Paper Group ANR 350
Multi-Temporal Land Cover Classification with Sequential Recurrent Encoders. Simulated Autonomous Driving in a Realistic Driving Environment using Deep Reinforcement Learning and a Deterministic Finite State Machine. Deep Learning Model for Finding New Superconductors. A Method for Restoring the Training Set Distribution in an Image Classifier. Sec …
Multi-Temporal Land Cover Classification with Sequential Recurrent Encoders
Title | Multi-Temporal Land Cover Classification with Sequential Recurrent Encoders |
Authors | Marc Rußwurm, Marco Körner |
Abstract | Earth observation (EO) sensors deliver data with daily or weekly temporal resolution. Most land use and land cover (LULC) approaches, however, expect cloud-free and mono-temporal observations. The increasing temporal capabilities of today’s sensors enables the use of temporal, along with spectral and spatial features. Domains, such as speech recognition or neural machine translation, work with inherently temporal data and, today, achieve impressive results using sequential encoder-decoder structures. Inspired by these sequence-to-sequence models, we adapt an encoder structure with convolutional recurrent layers in order to approximate a phenological model for vegetation classes based on a temporal sequence of Sentinel 2 (S2) images. In our experiments, we visualize internal activations over a sequence of cloudy and non-cloudy images and find several recurrent cells, which reduce the input activity for cloudy observations. Hence, we assume that our network has learned cloud-filtering schemes solely from input data, which could alleviate the need for tedious cloud-filtering as a preprocessing step for many EO approaches. Moreover, using unfiltered temporal series of top-of-atmosphere (TOA) reflectance data, we achieved in our experiments state-of-the-art classification accuracies on a large number of crop classes with minimal preprocessing compared to other classification approaches. |
Tasks | Machine Translation, Speech Recognition |
Published | 2018-02-06 |
URL | http://arxiv.org/abs/1802.02080v4 |
http://arxiv.org/pdf/1802.02080v4.pdf | |
PWC | https://paperswithcode.com/paper/multi-temporal-land-cover-classification-with |
Repo | |
Framework | |
Simulated Autonomous Driving in a Realistic Driving Environment using Deep Reinforcement Learning and a Deterministic Finite State Machine
Title | Simulated Autonomous Driving in a Realistic Driving Environment using Deep Reinforcement Learning and a Deterministic Finite State Machine |
Authors | Patrick Klose, Rudolf Mester |
Abstract | In the field of Autonomous Driving, the system controlling the vehicle can be seen as an agent acting in a complex environment and thus naturally fits into the modern framework of Reinforcement Learning. However, learning to drive can be a challenging task and current results are often restricted to simplified driving environments. To advance the field, we present a method to adaptively restrict the action space of the agent according to its current driving situation and show that it can be used to swiftly learn to drive in a realistic environment based on the Deep Q-Network algorithm. |
Tasks | Autonomous Driving |
Published | 2018-11-19 |
URL | http://arxiv.org/abs/1811.07868v2 |
http://arxiv.org/pdf/1811.07868v2.pdf | |
PWC | https://paperswithcode.com/paper/simulated-autonomous-driving-in-a-realistic |
Repo | |
Framework | |
Deep Learning Model for Finding New Superconductors
Title | Deep Learning Model for Finding New Superconductors |
Authors | Tomohiko Konno, Hodaka Kurokawa, Fuyuki Nabeshima, Yuki Sakishita, Ryo Ogawa, Iwao Hosako, Atsutaka Maeda |
Abstract | Superconductivity has been extensively studied since its discovery in 1911. However, the feasibility of room-temperature superconductivity is unknown. It is very difficult for both theory and computational methods to predict the superconducting transition temperatures Tc of superconductors for strongly correlated systems, in which high-temperature superconductivity emerges. Exploration of new superconductors still relies on the experience and intuition of experts, and is largely a process of experimental trial and error. In one study, only 3% of the candidate materials showed superconductivity. Here we report the first deep learning model for finding new superconductors. We represented the periodic table in a way that allows a deep learning model to learn it. Although we used only the chemical composition of materials as information, we obtained an R2 value of 0.92 for predicting Tc for materials in a database of superconductors. We obtained three remarkable results. The deep learning method can predict superconductivity for a material with a precision of 62%, which shows the usefulness of the model; it found the recently discovered superconductor CaBi2, which is not in the superconductor database; and it found Fe-based high-temperature superconductors (discovered in 2008) from the training data before 2008. These results open the way for the discovery of new high-temperature superconductor families. |
Tasks | |
Published | 2018-12-03 |
URL | https://arxiv.org/abs/1812.01995v3 |
https://arxiv.org/pdf/1812.01995v3.pdf | |
PWC | https://paperswithcode.com/paper/deep-learning-of-superconductors-i-estimation |
Repo | |
Framework | |
A Method for Restoring the Training Set Distribution in an Image Classifier
Title | A Method for Restoring the Training Set Distribution in an Image Classifier |
Authors | Alexey Chaplygin, Joshua Chacksfield |
Abstract | Convolutional Neural Networks are a well-known staple of modern image classification. However, it can be difficult to assess the quality and robustness of such models. Deep models are known to perform well on a given training and estimation set, but can easily be fooled by data that is specifically generated for the purpose. It has been shown that one can produce an artificial example that does not represent the desired class, but activates the network in the desired way. This paper describes a new way of reconstructing a sample from the training set distribution of an image classifier without deep knowledge about the underlying distribution. This enables access to the elements of images that most influence the decision of a convolutional network and to extract meaningful information about the training distribution. |
Tasks | Image Classification |
Published | 2018-02-05 |
URL | http://arxiv.org/abs/1802.01435v1 |
http://arxiv.org/pdf/1802.01435v1.pdf | |
PWC | https://paperswithcode.com/paper/a-method-for-restoring-the-training-set |
Repo | |
Framework | |
Security for Machine Learning-based Systems: Attacks and Challenges during Training and Inference
Title | Security for Machine Learning-based Systems: Attacks and Challenges during Training and Inference |
Authors | Faiq Khalid, Muhammad Abdullah Hanif, Semeen Rehman, Muhammad Shafique |
Abstract | The exponential increase in dependencies between the cyber and physical world leads to an enormous amount of data which must be efficiently processed and stored. Therefore, computing paradigms are evolving towards machine learning (ML)-based systems because of their ability to efficiently and accurately process the enormous amount of data. Although ML-based solutions address the efficient computing requirements of big data, they introduce (new) security vulnerabilities into the systems, which cannot be addressed by traditional monitoring-based security measures. Therefore, this paper first presents a brief overview of various security threats in machine learning, their respective threat models and associated research challenges to develop robust security measures. To illustrate the security vulnerabilities of ML during training, inferencing and hardware implementation, we demonstrate some key security threats on ML using LeNet and VGGNet for MNIST and German Traffic Sign Recognition Benchmarks (GTSRB), respectively. Moreover, based on the security analysis of ML-training, we also propose an attack that has a very less impact on the inference accuracy. Towards the end, we highlight the associated research challenges in developing security measures and provide a brief overview of the techniques used to mitigate such security threats. |
Tasks | Traffic Sign Recognition |
Published | 2018-11-05 |
URL | http://arxiv.org/abs/1811.01463v1 |
http://arxiv.org/pdf/1811.01463v1.pdf | |
PWC | https://paperswithcode.com/paper/security-for-machine-learning-based-systems |
Repo | |
Framework | |
FairMod - Making Predictive Models Discrimination Aware
Title | FairMod - Making Predictive Models Discrimination Aware |
Authors | Jixue Liu, Jiuyong Li, Lin Liu, Thuc Duy Le, Feiyue Ye, Gefei Li |
Abstract | Predictive models such as decision trees and neural networks may produce discrimination in their predictions. This paper proposes a method to post-process the predictions of a predictive model to make the processed predictions non-discriminatory. The method considers multiple protected variables together. Multiple protected variables make the problem more challenging than a simple protected variable. The method uses a well-cited discrimination metric and adapts it to allow the specification of explanatory variables, such as position, profession, education, that describe the contexts of the applications. It models the post-processing of predictions problem as a nonlinear optimization problem to find best adjustments to the predictions so that the discrimination constraints of all protected variables are all met at the same time. The proposed method is independent of classification methods. It can handle the cases that existing methods cannot handle: satisfying multiple protected attributes at the same time, allowing multiple explanatory attributes, and being independent of classification model types. An evaluation using four real world data sets shows that the proposed method is as effectively as existing methods, in addition to its extra power. |
Tasks | |
Published | 2018-11-05 |
URL | http://arxiv.org/abs/1811.01480v1 |
http://arxiv.org/pdf/1811.01480v1.pdf | |
PWC | https://paperswithcode.com/paper/fairmod-making-predictive-models |
Repo | |
Framework | |
A Simple but Effective Classification Model for Grammatical Error Correction
Title | A Simple but Effective Classification Model for Grammatical Error Correction |
Authors | Zhu Kaili, Chuan Wang, Ruobing Li, Yang Liu, Tianlei Hu, Hui Lin |
Abstract | We treat grammatical error correction (GEC) as a classification problem in this study, where for different types of errors, a target word is identified, and the classifier predicts the correct word form from a set of possible choices. We propose a novel neural network based feature representation and classification model, trained using large text corpora without human annotations. Specifically we use RNNs with attention to represent both the left and right context of a target word. All feature embeddings are learned jointly in an end-to-end fashion. Experimental results show that our novel approach outperforms other classifier methods on the CoNLL-2014 test set (F0.5 45.05%). Our model is simple but effective, and is suitable for industrial production. |
Tasks | Grammatical Error Correction |
Published | 2018-07-02 |
URL | http://arxiv.org/abs/1807.00488v1 |
http://arxiv.org/pdf/1807.00488v1.pdf | |
PWC | https://paperswithcode.com/paper/a-simple-but-effective-classification-model |
Repo | |
Framework | |
Localized Traffic Sign Detection with Multi-scale Deconvolution Networks
Title | Localized Traffic Sign Detection with Multi-scale Deconvolution Networks |
Authors | Songwen Pei, Fuwu Tang, Yanfei Ji, Jing Fan, Zhong Ning |
Abstract | Autonomous driving is becoming a future practical lifestyle greatly driven by deep learning. Specifically, an effective traffic sign detection by deep learning plays a critical role for it. However, different countries have different sets of traffic signs, making localized traffic sign recognition model training a tedious and daunting task. To address the issues of taking amount of time to compute complicate algorithm and low ratio of detecting blurred and sub-pixel images of localized traffic signs, we propose Multi-Scale Deconvolution Networks (MDN), which flexibly combines multi-scale convolutional neural network with deconvolution sub-network, leading to efficient and reliable localized traffic sign recognition model training. It is demonstrated that the proposed MDN is effective compared with classical algorithms on the benchmarks of the localized traffic sign, such as Chinese Traffic Sign Dataset (CTSD), and the German Traffic Sign Benchmarks (GTSRB). |
Tasks | Autonomous Driving, Traffic Sign Recognition |
Published | 2018-04-27 |
URL | http://arxiv.org/abs/1804.10428v2 |
http://arxiv.org/pdf/1804.10428v2.pdf | |
PWC | https://paperswithcode.com/paper/localized-traffic-sign-detection-with-multi |
Repo | |
Framework | |
Seq2Seq Mimic Games: A Signaling Perspective
Title | Seq2Seq Mimic Games: A Signaling Perspective |
Authors | Juan Leni, John Levine, John Quigley |
Abstract | We study the emergence of communication in multiagent adversarial settings inspired by the classic Imitation game. A class of three player games is used to explore how agents based on sequence to sequence (Seq2Seq) models can learn to communicate information in adversarial settings. We propose a modeling approach, an initial set of experiments and use signaling theory to support our analysis. In addition, we describe how we operationalize the learning process of actor-critic Seq2Seq based agents in these communicational games. |
Tasks | |
Published | 2018-11-15 |
URL | http://arxiv.org/abs/1811.06564v1 |
http://arxiv.org/pdf/1811.06564v1.pdf | |
PWC | https://paperswithcode.com/paper/seq2seq-mimic-games-a-signaling-perspective |
Repo | |
Framework | |
BRDF Estimation of Complex Materials with Nested Learning
Title | BRDF Estimation of Complex Materials with Nested Learning |
Authors | Raquel Vidaurre, Dan Casas, Elena Garces, Jorge Lopez-Moreno |
Abstract | The estimation of the optical properties of a material from RGB-images is an important but extremely ill-posed problem in Computer Graphics. While recent works have successfully approached this problem even from just a single photograph, significant simplifications of the material model are assumed, limiting the usability of such methods. The detection of complex material properties such as anisotropy or Fresnel effect remains an unsolved challenge. We propose a novel method that predicts the model parameters of an artist-friendly, physically-based BRDF, from only two low-resolution shots of the material. Thanks to a novel combination of deep neural networks in a nested architecture, we are able to handle the ambiguities given by the non-orthogonality and non-convexity of the parameter space. To train the network, we generate a novel dataset of physically-based synthetic images. We prove that our model can recover new properties like anisotropy, index of refraction and a second reflectance color, for materials that have tinted specular reflections or whose albedo changes at glancing angles. |
Tasks | |
Published | 2018-11-22 |
URL | http://arxiv.org/abs/1811.09131v1 |
http://arxiv.org/pdf/1811.09131v1.pdf | |
PWC | https://paperswithcode.com/paper/brdf-estimation-of-complex-materials-with |
Repo | |
Framework | |
Ineffectiveness of Dictionary Coding to Infer Predictability Limits of Human Mobility
Title | Ineffectiveness of Dictionary Coding to Infer Predictability Limits of Human Mobility |
Authors | Yunheng Han, Weiwei Sun, Baihua Zheng |
Abstract | Recently, a series of models have been proposed to predict future movements of people. Meanwhile, dictionary coding algorithms are used to estimate the predictability limit of human mobility. Although dictionary coding is optimal, it takes long time to converge. Consequently, it is ineffective to infer predictability through dictionary coding algorithms. In this report, we illustrate this ineffectiveness on the basis of human movements in urban space. |
Tasks | |
Published | 2018-10-08 |
URL | http://arxiv.org/abs/1810.06405v2 |
http://arxiv.org/pdf/1810.06405v2.pdf | |
PWC | https://paperswithcode.com/paper/ineffectiveness-of-dictionary-coding-to-infer |
Repo | |
Framework | |
Benchmarking and Optimization of Gradient Boosting Decision Tree Algorithms
Title | Benchmarking and Optimization of Gradient Boosting Decision Tree Algorithms |
Authors | Andreea Anghel, Nikolaos Papandreou, Thomas Parnell, Alessandro De Palma, Haralampos Pozidis |
Abstract | Gradient boosting decision trees (GBDTs) have seen widespread adoption in academia, industry and competitive data science due to their state-of-the-art performance in many machine learning tasks. One relative downside to these models is the large number of hyper-parameters that they expose to the end-user. To maximize the predictive power of GBDT models, one must either manually tune the hyper-parameters, or utilize automated techniques such as those based on Bayesian optimization. Both of these approaches are time-consuming since they involve repeatably training the model for different sets of hyper-parameters. A number of software GBDT packages have started to offer GPU acceleration which can help to alleviate this problem. In this paper, we consider three such packages: XGBoost, LightGBM and Catboost. Firstly, we evaluate the performance of the GPU acceleration provided by these packages using large-scale datasets with varying shapes, sparsities and learning tasks. Then, we compare the packages in the context of hyper-parameter optimization, both in terms of how quickly each package converges to a good validation score, and in terms of generalization performance. |
Tasks | |
Published | 2018-09-12 |
URL | http://arxiv.org/abs/1809.04559v3 |
http://arxiv.org/pdf/1809.04559v3.pdf | |
PWC | https://paperswithcode.com/paper/benchmarking-and-optimization-of-gradient |
Repo | |
Framework | |
Modelling Langford’s Problem: A Viewpoint for Search
Title | Modelling Langford’s Problem: A Viewpoint for Search |
Authors | Özgür Akgün, Ian Miguel |
Abstract | The performance of enumerating all solutions to an instance of Langford’s Problem is sensitive to the model and the search strategy. In this paper we compare the performance of a large variety of models, all derived from two base viewpoints. We empirically show that a channelled model with a static branching order on one of the viewpoints offers the best performance out of all the options we consider. Surprisingly, one of the base models proves very effective for propagation, while the other provides an effective means of stating a static search order. |
Tasks | |
Published | 2018-08-29 |
URL | http://arxiv.org/abs/1808.09847v1 |
http://arxiv.org/pdf/1808.09847v1.pdf | |
PWC | https://paperswithcode.com/paper/modelling-langfords-problem-a-viewpoint-for |
Repo | |
Framework | |
Neural Stain Normalization and Unsupervised Classification of Cell Nuclei in Histopathological Breast Cancer Images
Title | Neural Stain Normalization and Unsupervised Classification of Cell Nuclei in Histopathological Breast Cancer Images |
Authors | Edwin Yuan, Junkyo Suh |
Abstract | In this paper, we develop a complete pipeline for stain normalization, segmentation, and classification of nuclei in hematoxylin and eosin (H&E) stained breast cancer histopathology images. In the first step, we use a CNN-based stain transfer technique to normalize the staining characteristics of (H&E) images. We then train a neural network to segment images of nuclei from the H&E images. Finally, we train an Information Maximizing Generative Adversarial Network (InfoGAN) to learn visual representations of different types of nuclei and classify them in an entirely unsupervised manner. The results show that our proposed CNN stain normalization yields improved visual similarity and cell segmentation performance compared to the conventional SVD-based stain normalization method. In the final step of our pipeline, we demonstrate the ability to perform fully unsupervised clustering of various breast histopathology cell types based on morphological and color attributes. In addition, we quantitatively evaluate our neural network - based techniques against various quantitative metrics to validate the effectiveness of our pipeline. |
Tasks | Cell Segmentation |
Published | 2018-11-09 |
URL | http://arxiv.org/abs/1811.03815v1 |
http://arxiv.org/pdf/1811.03815v1.pdf | |
PWC | https://paperswithcode.com/paper/neural-stain-normalization-and-unsupervised |
Repo | |
Framework | |
Enhancing the Accuracy and Fairness of Human Decision Making
Title | Enhancing the Accuracy and Fairness of Human Decision Making |
Authors | Isabel Valera, Adish Singla, Manuel Gomez Rodriguez |
Abstract | Societies often rely on human experts to take a wide variety of decisions affecting their members, from jail-or-release decisions taken by judges and stop-and-frisk decisions taken by police officers to accept-or-reject decisions taken by academics. In this context, each decision is taken by an expert who is typically chosen uniformly at random from a pool of experts. However, these decisions may be imperfect due to limited experience, implicit biases, or faulty probabilistic reasoning. Can we improve the accuracy and fairness of the overall decision making process by optimizing the assignment between experts and decisions? In this paper, we address the above problem from the perspective of sequential decision making and show that, for different fairness notions from the literature, it reduces to a sequence of (constrained) weighted bipartite matchings, which can be solved efficiently using algorithms with approximation guarantees. Moreover, these algorithms also benefit from posterior sampling to actively trade off exploitation—selecting expert assignments which lead to accurate and fair decisions—and exploration—selecting expert assignments to learn about the experts’ preferences and biases. We demonstrate the effectiveness of our algorithms on both synthetic and real-world data and show that they can significantly improve both the accuracy and fairness of the decisions taken by pools of experts. |
Tasks | Decision Making |
Published | 2018-05-25 |
URL | http://arxiv.org/abs/1805.10318v1 |
http://arxiv.org/pdf/1805.10318v1.pdf | |
PWC | https://paperswithcode.com/paper/enhancing-the-accuracy-and-fairness-of-human |
Repo | |
Framework | |