Paper Group ANR 780
Deep Video Color Propagation. A Precedent Approach to Assigning Access Rights. Transfer Learning using Representation Learning in Massive Open Online Courses. Greedy stochastic algorithms for entropy-regularized optimal transport problems. Model Selection for Generalized Zero-shot Learning. Bringing back simplicity and lightliness into neural image …
Deep Video Color Propagation
| Title | Deep Video Color Propagation |
| Authors | Simone Meyer, Victor Cornillère, Abdelaziz Djelouah, Christopher Schroers, Markus Gross |
| Abstract | Traditional approaches for color propagation in videos rely on some form of matching between consecutive video frames. Using appearance descriptors, colors are then propagated both spatially and temporally. These methods, however, are computationally expensive and do not take advantage of semantic information of the scene. In this work we propose a deep learning framework for color propagation that combines a local strategy, to propagate colors frame-by-frame ensuring temporal stability, and a global strategy, using semantics for color propagation within a longer range. Our evaluation shows the superiority of our strategy over existing video and image color propagation methods as well as neural photo-realistic style transfer approaches. |
| Tasks | Style Transfer |
| Published | 2018-08-09 |
| URL | http://arxiv.org/abs/1808.03232v1 |
| http://arxiv.org/pdf/1808.03232v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-video-color-propagation |
| Repo | |
| Framework | |
A Precedent Approach to Assigning Access Rights
| Title | A Precedent Approach to Assigning Access Rights |
| Authors | S. V. Belim, N. F. Bogachenko, A. N. Kabanov |
| Abstract | To design a discretionary access control policy, a technique is proposed that uses the principle of analogies and is based on both the properties of objects and the properties of subjects. As attributes characterizing these properties, the values of the security attributes of subjects and objects are chosen. The concept of precedent is defined as an access rule explicitly specified by the security administrator. The problem of interpolation of the access matrix is formulated: the security administrator defines a sequence of precedents, it is required to automate the process of filling the remaining cells of the access matrix. On the family of sets of security attributes, a linear order is introduced. The principles of filling the access matrix on the basis of analogy with the dominant precedent in accordance with a given order relation are developed. The analysis of the proposed methodology is performed and its main advantages are revealed. |
| Tasks | |
| Published | 2018-12-28 |
| URL | http://arxiv.org/abs/1812.10961v1 |
| http://arxiv.org/pdf/1812.10961v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-precedent-approach-to-assigning-access |
| Repo | |
| Framework | |
Transfer Learning using Representation Learning in Massive Open Online Courses
| Title | Transfer Learning using Representation Learning in Massive Open Online Courses |
| Authors | Mucong Ding, Yanbang Wang, Erik Hemberg, Una-May O’Reilly |
| Abstract | In a Massive Open Online Course (MOOC), predictive models of student behavior can support multiple aspects of learning, including instructor feedback and timely intervention. Ongoing courses, when the student outcomes are yet unknown, must rely on models trained from the historical data of previously offered courses. It is possible to transfer models, but they often have poor prediction performance. One reason is features that inadequately represent predictive attributes common to both courses. We present an automated transductive transfer learning approach that addresses this issue. It relies on problem-agnostic, temporal organization of the MOOC clickstream data, where, for each student, for multiple courses, a set of specific MOOC event types is expressed for each time unit. It consists of two alternative transfer methods based on representation learning with auto-encoders: a passive approach using transductive principal component analysis and an active approach that uses a correlation alignment loss term. With these methods, we investigate the transferability of dropout prediction across similar and dissimilar MOOCs and compare with known methods. Results show improved model transferability and suggest that the methods are capable of automatically learning a feature representation that expresses common predictive characteristics of MOOCs. |
| Tasks | Representation Learning, Transfer Learning |
| Published | 2018-12-12 |
| URL | http://arxiv.org/abs/1812.05043v2 |
| http://arxiv.org/pdf/1812.05043v2.pdf | |
| PWC | https://paperswithcode.com/paper/transfer-learning-using-representation |
| Repo | |
| Framework | |
Greedy stochastic algorithms for entropy-regularized optimal transport problems
| Title | Greedy stochastic algorithms for entropy-regularized optimal transport problems |
| Authors | Brahim Khalil Abid, Robert M. Gower |
| Abstract | Optimal transport (OT) distances are finding evermore applications in machine learning and computer vision, but their wide spread use in larger-scale problems is impeded by their high computational cost. In this work we develop a family of fast and practical stochastic algorithms for solving the optimal transport problem with an entropic penalization. This work extends the recently developed Greenkhorn algorithm, in the sense that, the Greenkhorn algorithm is a limiting case of this family. We also provide a simple and general convergence theorem for all algorithms in the class, with rates that match the best known rates of Greenkorn and the Sinkhorn algorithm, and conclude with numerical experiments that show under what regime of penalization the new stochastic methods are faster than the aforementioned methods. |
| Tasks | |
| Published | 2018-03-04 |
| URL | http://arxiv.org/abs/1803.01347v1 |
| http://arxiv.org/pdf/1803.01347v1.pdf | |
| PWC | https://paperswithcode.com/paper/greedy-stochastic-algorithms-for-entropy |
| Repo | |
| Framework | |
Model Selection for Generalized Zero-shot Learning
| Title | Model Selection for Generalized Zero-shot Learning |
| Authors | Hongguang Zhang, Piotr Koniusz |
| Abstract | In the problem of generalized zero-shot learning, the datapoints from unknown classes are not available during training. The main challenge for generalized zero-shot learning is the unbalanced data distribution which makes it hard for the classifier to distinguish if a given testing sample comes from a seen or unseen class. However, using Generative Adversarial Network (GAN) to generate auxiliary datapoints by the semantic embeddings of unseen classes alleviates the above problem. Current approaches combine the auxiliary datapoints and original training data to train the generalized zero-shot learning model and obtain state-of-the-art results. Inspired by such models, we propose to feed the generated data via a model selection mechanism. Specifically, we leverage two sources of datapoints (observed and auxiliary) to train some classifier to recognize which test datapoints come from seen and which from unseen classes. This way, generalized zero-shot learning can be divided into two disjoint classification tasks, thus reducing the negative influence of the unbalanced data distribution. Our evaluations on four publicly available datasets for generalized zero-shot learning show that our model obtains state-of-the-art results. |
| Tasks | Model Selection, Zero-Shot Learning |
| Published | 2018-11-08 |
| URL | http://arxiv.org/abs/1811.03252v1 |
| http://arxiv.org/pdf/1811.03252v1.pdf | |
| PWC | https://paperswithcode.com/paper/model-selection-for-generalized-zero-shot |
| Repo | |
| Framework | |
Bringing back simplicity and lightliness into neural image captioning
| Title | Bringing back simplicity and lightliness into neural image captioning |
| Authors | Jean-Benoit Delbrouck, Stéphane Dupont |
| Abstract | Neural Image Captioning (NIC) or neural caption generation has attracted a lot of attention over the last few years. Describing an image with a natural language has been an emerging challenge in both fields of computer vision and language processing. Therefore a lot of research has focused on driving this task forward with new creative ideas. So far, the goal has been to maximize scores on automated metric and to do so, one has to come up with a plurality of new modules and techniques. Once these add up, the models become complex and resource-hungry. In this paper, we take a small step backwards in order to study an architecture with interesting trade-off between performance and computational complexity. To do so, we tackle every component of a neural captioning model and propose one or more solution that lightens the model overall. Our ideas are inspired by two related tasks: Multimodal and Monomodal Neural Machine Translation. |
| Tasks | Image Captioning, Machine Translation |
| Published | 2018-10-15 |
| URL | http://arxiv.org/abs/1810.06245v1 |
| http://arxiv.org/pdf/1810.06245v1.pdf | |
| PWC | https://paperswithcode.com/paper/bringing-back-simplicity-and-lightliness-into |
| Repo | |
| Framework | |
Informed Democracy: Voting-based Novelty Detection for Action Recognition
| Title | Informed Democracy: Voting-based Novelty Detection for Action Recognition |
| Authors | Alina Roitberg, Ziad Al-Halah, Rainer Stiefelhagen |
| Abstract | Novelty detection is crucial for real-life applications. While it is common in activity recognition to assume a closed-set setting, i.e. test samples are always of training categories, this assumption is impractical in a real-world scenario. Test samples can be of various categories including those never seen before during training. Thus, being able to know what we know and what we do not know is decisive for the model to avoid what can be catastrophic consequences. We present in this work a novel approach for identifying samples of activity classes that are not previously seen by the classifier. Our model employs a voting-based scheme that leverages the estimated uncertainty of the individual classifiers in their predictions to measure the novelty of a new input sample. Furthermore, the voting is privileged to a subset of informed classifiers that can best estimate whether a sample is novel or not when it is classified to a certain known category. In a thorough evaluation on UCF-101 and HMDB-51, we show that our model consistently outperforms state-of-the-art in novelty detection. Additionally, by combining our model with off-the-shelf zero-shot learning (ZSL) approaches, our model leads to a significant improvement in action classification accuracy for the generalized ZSL setting. |
| Tasks | Action Classification, Activity Recognition, Temporal Action Localization, Zero-Shot Learning |
| Published | 2018-10-30 |
| URL | http://arxiv.org/abs/1810.12819v1 |
| http://arxiv.org/pdf/1810.12819v1.pdf | |
| PWC | https://paperswithcode.com/paper/informed-democracy-voting-based-novelty |
| Repo | |
| Framework | |
Hybrid Forecasting of Chaotic Processes: Using Machine Learning in Conjunction with a Knowledge-Based Model
| Title | Hybrid Forecasting of Chaotic Processes: Using Machine Learning in Conjunction with a Knowledge-Based Model |
| Authors | Jaideep Pathak, Alexander Wikner, Rebeckah Fussell, Sarthak Chandra, Brian Hunt, Michelle Girvan, Edward Ott |
| Abstract | A model-based approach to forecasting chaotic dynamical systems utilizes knowledge of the physical processes governing the dynamics to build an approximate mathematical model of the system. In contrast, machine learning techniques have demonstrated promising results for forecasting chaotic systems purely from past time series measurements of system state variables (training data), without prior knowledge of the system dynamics. The motivation for this paper is the potential of machine learning for filling in the gaps in our underlying mechanistic knowledge that cause widely-used knowledge-based models to be inaccurate. Thus we here propose a general method that leverages the advantages of these two approaches by combining a knowledge-based model and a machine learning technique to build a hybrid forecasting scheme. Potential applications for such an approach are numerous (e.g., improving weather forecasting). We demonstrate and test the utility of this approach using a particular illustrative version of a machine learning known as reservoir computing, and we apply the resulting hybrid forecaster to a low-dimensional chaotic system, as well as to a high-dimensional spatiotemporal chaotic system. These tests yield extremely promising results in that our hybrid technique is able to accurately predict for a much longer period of time than either its machine-learning component or its model-based component alone. |
| Tasks | Time Series, Weather Forecasting |
| Published | 2018-03-09 |
| URL | http://arxiv.org/abs/1803.04779v1 |
| http://arxiv.org/pdf/1803.04779v1.pdf | |
| PWC | https://paperswithcode.com/paper/hybrid-forecasting-of-chaotic-processes-using |
| Repo | |
| Framework | |
Classification of Building Information Model (BIM) Structures with Deep Learning
| Title | Classification of Building Information Model (BIM) Structures with Deep Learning |
| Authors | Francesco Lomio, Ricardo Farinha, Mauri Laasonen, Heikki Huttunen |
| Abstract | In this work we study an application of machine learning to the construction industry and we use classical and modern machine learning methods to categorize images of building designs into three classes: Apartment building, Industrial building or Other. No real images are used, but only images extracted from Building Information Model (BIM) software, as these are used by the construction industry to store building designs. For this task, we compared four different methods: the first is based on classical machine learning, where Histogram of Oriented Gradients (HOG) was used for feature extraction and a Support Vector Machine (SVM) for classification; the other three methods are based on deep learning, covering common pre-trained networks as well as ones designed from scratch. To validate the accuracy of the models, a database of 240 images was used. The accuracy achieved is 57% for the HOG + SVM model, and above 89% for the neural networks. |
| Tasks | |
| Published | 2018-08-01 |
| URL | http://arxiv.org/abs/1808.00601v1 |
| http://arxiv.org/pdf/1808.00601v1.pdf | |
| PWC | https://paperswithcode.com/paper/classification-of-building-information-model |
| Repo | |
| Framework | |
Incremental Learning for Semantic Segmentation of Large-Scale Remote Sensing Data
| Title | Incremental Learning for Semantic Segmentation of Large-Scale Remote Sensing Data |
| Authors | Onur Tasar, Yuliya Tarabalka, Pierre Alliez |
| Abstract | In spite of remarkable success of the convolutional neural networks on semantic segmentation, they suffer from catastrophic forgetting: a significant performance drop for the already learned classes when new classes are added on the data, having no annotations for the old classes. We propose an incremental learning methodology, enabling to learn segmenting new classes without hindering dense labeling abilities for the previous classes, although the entire previous data are not accessible. The key points of the proposed approach are adapting the network to learn new as well as old classes on the new training data, and allowing it to remember the previously learned information for the old classes. For adaptation, we keep a frozen copy of the previously trained network, which is used as a memory for the updated network in absence of annotations for the former classes. The updated network minimizes a loss function, which balances the discrepancy between outputs for the previous classes from the memory and updated networks, and the mis-classification rate between outputs for the new classes from the updated network and the new ground-truth. For remembering, we either regularly feed samples from the stored, little fraction of the previous data or use the memory network, depending on whether the new data are collected from completely different geographic areas or from the same city. Our experimental results prove that it is possible to add new classes to the network, while maintaining its performance for the previous classes, despite the whole previous training data are not available. |
| Tasks | Semantic Segmentation |
| Published | 2018-10-29 |
| URL | http://arxiv.org/abs/1810.12448v1 |
| http://arxiv.org/pdf/1810.12448v1.pdf | |
| PWC | https://paperswithcode.com/paper/incremental-learning-for-semantic |
| Repo | |
| Framework | |
Factors Influencing the Surprising Instability of Word Embeddings
| Title | Factors Influencing the Surprising Instability of Word Embeddings |
| Authors | Laura Wendlandt, Jonathan K. Kummerfeld, Rada Mihalcea |
| Abstract | Despite the recent popularity of word embedding methods, there is only a small body of work exploring the limitations of these representations. In this paper, we consider one aspect of embedding spaces, namely their stability. We show that even relatively high frequency words (100-200 occurrences) are often unstable. We provide empirical evidence for how various factors contribute to the stability of word embeddings, and we analyze the effects of stability on downstream tasks. |
| Tasks | Word Embeddings |
| Published | 2018-04-25 |
| URL | http://arxiv.org/abs/1804.09692v1 |
| http://arxiv.org/pdf/1804.09692v1.pdf | |
| PWC | https://paperswithcode.com/paper/factors-influencing-the-surprising |
| Repo | |
| Framework | |
Semi-supervised Rare Disease Detection Using Generative Adversarial Network
| Title | Semi-supervised Rare Disease Detection Using Generative Adversarial Network |
| Authors | Wenyuan Li, Yunlong Wang, Yong Cai, Corey Arnold, Emily Zhao, Yilian Yuan |
| Abstract | Rare diseases affect a relatively small number of people, which limits investment in research for treatments and cures. Developing an efficient method for rare disease detection is a crucial first step towards subsequent clinical research. In this paper, we present a semi-supervised learning framework for rare disease detection using generative adversarial networks. Our method takes advantage of the large amount of unlabeled data for disease detection and achieves the best results in terms of precision-recall score compared to baseline techniques. |
| Tasks | |
| Published | 2018-12-03 |
| URL | http://arxiv.org/abs/1812.00547v1 |
| http://arxiv.org/pdf/1812.00547v1.pdf | |
| PWC | https://paperswithcode.com/paper/semi-supervised-rare-disease-detection-using |
| Repo | |
| Framework | |
Challenge AI Mind: A Crowd System for Proactive AI Testing
| Title | Challenge AI Mind: A Crowd System for Proactive AI Testing |
| Authors | Siwei Fu, Anbang Xu, Xiaotong Liu, Huimin Zhou, Rama Akkiraju |
| Abstract | Artificial Intelligence (AI) has burrowed into our lives in various aspects; however, without appropriate testing, deployed AI systems are often being criticized to fail in critical and embarrassing cases. Existing testing approaches mainly depend on fixed and pre-defined datasets, providing a limited testing coverage. In this paper, we propose the concept of proactive testing to dynamically generate testing data and evaluate the performance of AI systems. We further introduce Challenge.AI, a new crowd system that features the integration of crowdsourcing and machine learning techniques in the process of error generation, error validation, error categorization, and error analysis. We present experiences and insights into a participatory design with AI developers. The evaluation shows that the crowd workflow is more effective with the help of machine learning techniques. AI developers found that our system can help them discover unknown errors made by the AI models, and engage in the process of proactive testing. |
| Tasks | |
| Published | 2018-10-21 |
| URL | http://arxiv.org/abs/1810.09030v1 |
| http://arxiv.org/pdf/1810.09030v1.pdf | |
| PWC | https://paperswithcode.com/paper/challenge-ai-mind-a-crowd-system-for |
| Repo | |
| Framework | |
A Logic of Agent Organizations
| Title | A Logic of Agent Organizations |
| Authors | Virginia Dignum, Frank Dignum |
| Abstract | Organization concepts and models are increasingly being adopted for the design and specification of multi-agent systems. Agent organizations can be seen as mechanisms of social order, created to achieve global (or organizational) objectives by more or less autonomous agents. In order to develop a theory on the relation between organizational structures, organizational objectives and the actions of agents fulfilling roles in the organization a theoretical framework is needed to describe organizational structures and actions of (groups of) agents. Current logical formalisms focus on specific aspects of organizations (e.g. power, delegation, agent actions, or normative issues) but a framework that integrates and relates different aspects is missing. Given the amount of aspects involved and the subsequent complexity of a formalism encompassing them all, it is difficult to realize. In this paper, a first step is taken to solve this problem. We present a generic formal model that enables to specify and relate the main concepts of an organization (including, activity, structure, environment and others) so that organizations can be analyzed at a high level of abstraction. However, for some aspects we use a simplified model in order to avoid the complexity of combining many different types of (modal) operators. |
| Tasks | |
| Published | 2018-04-28 |
| URL | http://arxiv.org/abs/1804.10817v1 |
| http://arxiv.org/pdf/1804.10817v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-logic-of-agent-organizations |
| Repo | |
| Framework | |
Decentralized Task Allocation in Multi-Robot Systems via Bipartite Graph Matching Augmented with Fuzzy Clustering
| Title | Decentralized Task Allocation in Multi-Robot Systems via Bipartite Graph Matching Augmented with Fuzzy Clustering |
| Authors | Payam Ghassemi, Souma Chowdhury |
| Abstract | Robotic systems, working together as a team, are becoming valuable players in different real-world applications, from disaster response to warehouse fulfillment services. Centralized solutions for coordinating multi-robot teams often suffer from poor scalability and vulnerability to communication disruptions. This paper develops a decentralized multi-agent task allocation (Dec-MATA) algorithm for multi-robot applications. The task planning problem is posed as a maximum-weighted matching of a bipartite graph, the solution of which using the blossom algorithm allows each robot to autonomously identify the optimal sequence of tasks it should undertake. The graph weights are determined based on a soft clustering process, which also plays a problem decomposition role seeking to reduce the complexity of the individual-agents’ task assignment problems. To evaluate the new Dec-MATA algorithm, a series of case studies (of varying complexity) are performed, with tasks being distributed randomly over an observable 2D environment. A centralized approach, based on a state-of-the-art MILP formulation of the multi-Traveling Salesman problem is used for comparative analysis. While getting within 7-28% of the optimal cost obtained by the centralized algorithm, the Dec-MATA algorithm is found to be 1-3 orders of magnitude faster and minimally sensitive to task-to-robot ratios, unlike the centralized algorithm. |
| Tasks | Graph Matching, Problem Decomposition |
| Published | 2018-07-20 |
| URL | http://arxiv.org/abs/1807.07957v1 |
| http://arxiv.org/pdf/1807.07957v1.pdf | |
| PWC | https://paperswithcode.com/paper/decentralized-task-allocation-in-multi-robot |
| Repo | |
| Framework | |
