Paper Group ANR 349
Synthetic to Real Adaptation with Generative Correlation Alignment Networks. Survey of reasoning using Neural networks. Automatic Generation of Natural Language Explanations. Practical Block-wise Neural Network Architecture Generation. An Automatic Diagnosis Method of Facial Acne Vulgaris Based on Convolutional Neural Network. Is this word borrowed …
Synthetic to Real Adaptation with Generative Correlation Alignment Networks
| Title | Synthetic to Real Adaptation with Generative Correlation Alignment Networks |
| Authors | Xingchao Peng, Kate Saenko |
| Abstract | Synthetic images rendered from 3D CAD models are useful for augmenting training data for object recognition algorithms. However, the generated images are non-photorealistic and do not match real image statistics. This leads to a large domain discrepancy, causing models trained on synthetic data to perform poorly on real domains. Recent work has shown the great potential of deep convolutional neural networks to generate realistic images, but has not utilized generative models to address synthetic-to-real domain adaptation. In this work, we propose a Deep Generative Correlation Alignment Network (DGCAN) to synthesize images using a novel domain adaption algorithm. DGCAN leverages a shape preserving loss and a low level statistic matching loss to minimize the domain discrepancy between synthetic and real images in deep feature space. Experimentally, we show training off-the-shelf classifiers on the newly generated data can significantly boost performance when testing on the real image domains (PASCAL VOC 2007 benchmark and Office dataset), improving upon several existing methods. |
| Tasks | Domain Adaptation, Object Recognition |
| Published | 2017-01-19 |
| URL | http://arxiv.org/abs/1701.05524v3 |
| http://arxiv.org/pdf/1701.05524v3.pdf | |
| PWC | https://paperswithcode.com/paper/synthetic-to-real-adaptation-with-generative |
| Repo | |
| Framework | |
Survey of reasoning using Neural networks
| Title | Survey of reasoning using Neural networks |
| Authors | Amit Sahu |
| Abstract | Reason and inference require process as well as memory skills by humans. Neural networks are able to process tasks like image recognition (better than humans) but in memory aspects are still limited (by attention mechanism, size). Recurrent Neural Network (RNN) and it’s modified version LSTM are able to solve small memory contexts, but as context becomes larger than a threshold, it is difficult to use them. The Solution is to use large external memory. Still, it poses many challenges like, how to train neural networks for discrete memory representation, how to describe long term dependencies in sequential data etc. Most prominent neural architectures for such tasks are Memory networks: inference components combined with long term memory and Neural Turing Machines: neural networks using external memory resources. Also, additional techniques like attention mechanism, end to end gradient descent on discrete memory representation are needed to support these solutions. Preliminary results of above neural architectures on simple algorithms (sorting, copying) and Question Answering (based on story, dialogs) application are comparable with the state of the art. In this paper, I explain these architectures (in general), the additional techniques used and the results of their application. |
| Tasks | Question Answering |
| Published | 2017-02-14 |
| URL | http://arxiv.org/abs/1702.06186v2 |
| http://arxiv.org/pdf/1702.06186v2.pdf | |
| PWC | https://paperswithcode.com/paper/survey-of-reasoning-using-neural-networks |
| Repo | |
| Framework | |
Automatic Generation of Natural Language Explanations
| Title | Automatic Generation of Natural Language Explanations |
| Authors | Felipe Costa, Sixun Ouyang, Peter Dolog, Aonghus Lawlor |
| Abstract | An important task for recommender system is to generate explanations according to a user’s preferences. Most of the current methods for explainable recommendations use structured sentences to provide descriptions along with the recommendations they produce. However, those methods have neglected the review-oriented way of writing a text, even though it is known that these reviews have a strong influence over user’s decision. In this paper, we propose a method for the automatic generation of natural language explanations, for predicting how a user would write about an item, based on user ratings from different items’ features. We design a character-level recurrent neural network (RNN) model, which generates an item’s review explanations using long-short term memories (LSTM). The model generates text reviews given a combination of the review and ratings score that express opinions about different factors or aspects of an item. Our network is trained on a sub-sample from the large real-world dataset BeerAdvocate. Our empirical evaluation using natural language processing metrics shows the generated text’s quality is close to a real user written review, identifying negation, misspellings, and domain specific vocabulary. |
| Tasks | Recommendation Systems |
| Published | 2017-07-04 |
| URL | http://arxiv.org/abs/1707.01561v1 |
| http://arxiv.org/pdf/1707.01561v1.pdf | |
| PWC | https://paperswithcode.com/paper/automatic-generation-of-natural-language |
| Repo | |
| Framework | |
Practical Block-wise Neural Network Architecture Generation
| Title | Practical Block-wise Neural Network Architecture Generation |
| Authors | Zhao Zhong, Junjie Yan, Wei Wu, Jing Shao, Cheng-Lin Liu |
| Abstract | Convolutional neural networks have gained a remarkable success in computer vision. However, most usable network architectures are hand-crafted and usually require expertise and elaborate design. In this paper, we provide a block-wise network generation pipeline called BlockQNN which automatically builds high-performance networks using the Q-Learning paradigm with epsilon-greedy exploration strategy. The optimal network block is constructed by the learning agent which is trained sequentially to choose component layers. We stack the block to construct the whole auto-generated network. To accelerate the generation process, we also propose a distributed asynchronous framework and an early stop strategy. The block-wise generation brings unique advantages: (1) it performs competitive results in comparison to the hand-crafted state-of-the-art networks on image classification, additionally, the best network generated by BlockQNN achieves 3.54% top-1 error rate on CIFAR-10 which beats all existing auto-generate networks. (2) in the meanwhile, it offers tremendous reduction of the search space in designing networks which only spends 3 days with 32 GPUs, and (3) moreover, it has strong generalizability that the network built on CIFAR also performs well on a larger-scale ImageNet dataset. |
| Tasks | Image Classification, Q-Learning |
| Published | 2017-08-18 |
| URL | http://arxiv.org/abs/1708.05552v3 |
| http://arxiv.org/pdf/1708.05552v3.pdf | |
| PWC | https://paperswithcode.com/paper/practical-block-wise-neural-network |
| Repo | |
| Framework | |
An Automatic Diagnosis Method of Facial Acne Vulgaris Based on Convolutional Neural Network
| Title | An Automatic Diagnosis Method of Facial Acne Vulgaris Based on Convolutional Neural Network |
| Authors | Xiaolei Shen, Jiachi Zhang, Chenjun Yan, Hong Zhou |
| Abstract | In this paper, we present a new automatic diagnosis method of facial acne vulgaris based on convolutional neural network. This method is proposed to overcome the shortcoming of classification types in previous methods. The core of our method is to extract features of images based on convolutional neural network and achieve classification by classifier. We design a binary classifier of skin-and-non-skin to detect skin area and a seven-classifier to achieve the classification of facial acne vulgaris and healthy skin. In the experiment, we compared the effectiveness of our convolutional neural network and the pre-trained VGG16 neural network on the ImageNet dataset. And we use the ROC curve and normal confusion matrix to evaluate the performance of the binary classifier and the seven-classifier. The results of our experiment show that the pre-trained VGG16 neural network is more effective in extracting image features. The classifiers based on the pre-trained VGG16 neural network achieve the skin detection and acne classification and have good robustness. |
| Tasks | |
| Published | 2017-11-13 |
| URL | http://arxiv.org/abs/1711.04481v1 |
| http://arxiv.org/pdf/1711.04481v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-automatic-diagnosis-method-of-facial-acne |
| Repo | |
| Framework | |
Is this word borrowed? An automatic approach to quantify the likeliness of borrowing in social media
| Title | Is this word borrowed? An automatic approach to quantify the likeliness of borrowing in social media |
| Authors | Jasabanta Patro, Bidisha Samanta, Saurabh Singh, Prithwish Mukherjee, Monojit Choudhury, Animesh Mukherjee |
| Abstract | Code-mixing or code-switching are the effortless phenomena of natural switching between two or more languages in a single conversation. Use of a foreign word in a language; however, does not necessarily mean that the speaker is code-switching because often languages borrow lexical items from other languages. If a word is borrowed, it becomes a part of the lexicon of a language; whereas, during code-switching, the speaker is aware that the conversation involves foreign words or phrases. Identifying whether a foreign word used by a bilingual speaker is due to borrowing or code-switching is a fundamental importance to theories of multilingualism, and an essential prerequisite towards the development of language and speech technologies for multilingual communities. In this paper, we present a series of novel computational methods to identify the borrowed likeliness of a word, based on the social media signals. We first propose context based clustering method to sample a set of candidate words from the social media data.Next, we propose three novel and similar metrics based on the usage of these words by the users in different tweets; these metrics were used to score and rank the candidate words indicating their borrowed likeliness. We compare these rankings with a ground truth ranking constructed through a human judgment experiment. The Spearman’s rank correlation between the two rankings (nearly 0.62 for all the three metric variants) is more than double the value (0.26) of the most competitive existing baseline reported in the literature. Some other striking observations are, (i) the correlation is higher for the ground truth data elicited from the younger participants (age less than 30) than that from the older participants, and (ii )those participants who use mixed-language for tweeting the least, provide the best signals of borrowing. |
| Tasks | |
| Published | 2017-03-15 |
| URL | http://arxiv.org/abs/1703.05122v1 |
| http://arxiv.org/pdf/1703.05122v1.pdf | |
| PWC | https://paperswithcode.com/paper/is-this-word-borrowed-an-automatic-approach |
| Repo | |
| Framework | |
Deep Decentralized Multi-task Multi-Agent Reinforcement Learning under Partial Observability
| Title | Deep Decentralized Multi-task Multi-Agent Reinforcement Learning under Partial Observability |
| Authors | Shayegan Omidshafiei, Jason Pazis, Christopher Amato, Jonathan P. How, John Vian |
| Abstract | Many real-world tasks involve multiple agents with partial observability and limited communication. Learning is challenging in these settings due to local viewpoints of agents, which perceive the world as non-stationary due to concurrently-exploring teammates. Approaches that learn specialized policies for individual tasks face problems when applied to the real world: not only do agents have to learn and store distinct policies for each task, but in practice identities of tasks are often non-observable, making these approaches inapplicable. This paper formalizes and addresses the problem of multi-task multi-agent reinforcement learning under partial observability. We introduce a decentralized single-task learning approach that is robust to concurrent interactions of teammates, and present an approach for distilling single-task policies into a unified policy that performs well across multiple related tasks, without explicit provision of task identity. |
| Tasks | Multi-agent Reinforcement Learning |
| Published | 2017-03-17 |
| URL | http://arxiv.org/abs/1703.06182v4 |
| http://arxiv.org/pdf/1703.06182v4.pdf | |
| PWC | https://paperswithcode.com/paper/deep-decentralized-multi-task-multi-agent |
| Repo | |
| Framework | |
Learning from various labeling strategies for suicide-related messages on social media: An experimental study
| Title | Learning from various labeling strategies for suicide-related messages on social media: An experimental study |
| Authors | Tong Liu, Qijin Cheng, Christopher M. Homan, Vincent M. B. Silenzio |
| Abstract | Suicide is an important but often misunderstood problem, one that researchers are now seeking to better understand through social media. Due in large part to the fuzzy nature of what constitutes suicidal risks, most supervised approaches for learning to automatically detect suicide-related activity in social media require a great deal of human labor to train. However, humans themselves have diverse or conflicting views on what constitutes suicidal thoughts. So how to obtain reliable gold standard labels is fundamentally challenging and, we hypothesize, depends largely on what is asked of the annotators and what slice of the data they label. We conducted multiple rounds of data labeling and collected annotations from crowdsourcing workers and domain experts. We aggregated the resulting labels in various ways to train a series of supervised models. Our preliminary evaluations show that using unanimously agreed labels from multiple annotators is helpful to achieve robust machine models. |
| Tasks | |
| Published | 2017-01-30 |
| URL | http://arxiv.org/abs/1701.08796v1 |
| http://arxiv.org/pdf/1701.08796v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-from-various-labeling-strategies-for |
| Repo | |
| Framework | |
Accuracy First: Selecting a Differential Privacy Level for Accuracy-Constrained ERM
| Title | Accuracy First: Selecting a Differential Privacy Level for Accuracy-Constrained ERM |
| Authors | Katrina Ligett, Seth Neel, Aaron Roth, Bo Waggoner, Z. Steven Wu |
| Abstract | Traditional approaches to differential privacy assume a fixed privacy requirement $\epsilon$ for a computation, and attempt to maximize the accuracy of the computation subject to the privacy constraint. As differential privacy is increasingly deployed in practical settings, it may often be that there is instead a fixed accuracy requirement for a given computation and the data analyst would like to maximize the privacy of the computation subject to the accuracy constraint. This raises the question of how to find and run a maximally private empirical risk minimizer subject to a given accuracy requirement. We propose a general “noise reduction” framework that can apply to a variety of private empirical risk minimization (ERM) algorithms, using them to “search” the space of privacy levels to find the empirically strongest one that meets the accuracy constraint, incurring only logarithmic overhead in the number of privacy levels searched. The privacy analysis of our algorithm leads naturally to a version of differential privacy where the privacy parameters are dependent on the data, which we term ex-post privacy, and which is related to the recently introduced notion of privacy odometers. We also give an ex-post privacy analysis of the classical AboveThreshold privacy tool, modifying it to allow for queries chosen depending on the database. Finally, we apply our approach to two common objectives, regularized linear and logistic regression, and empirically compare our noise reduction methods to (i) inverting the theoretical utility guarantees of standard private ERM algorithms and (ii) a stronger, empirical baseline based on binary search. |
| Tasks | |
| Published | 2017-05-30 |
| URL | http://arxiv.org/abs/1705.10829v1 |
| http://arxiv.org/pdf/1705.10829v1.pdf | |
| PWC | https://paperswithcode.com/paper/accuracy-first-selecting-a-differential-1 |
| Repo | |
| Framework | |
Towards lightweight convolutional neural networks for object detection
| Title | Towards lightweight convolutional neural networks for object detection |
| Authors | Dmitriy Anisimov, Tatiana Khanova |
| Abstract | We propose model with larger spatial size of feature maps and evaluate it on object detection task. With the goal to choose the best feature extraction network for our model we compare several popular lightweight networks. After that we conduct a set of experiments with channels reduction algorithms in order to accelerate execution. Our vehicle detection models are accurate, fast and therefore suit for embedded visual applications. With only 1.5 GFLOPs our best model gives 93.39 AP on validation subset of challenging DETRAC dataset. The smallest of our models is the first to achieve real-time inference speed on CPU with reasonable accuracy drop to 91.43 AP. |
| Tasks | Object Detection |
| Published | 2017-07-05 |
| URL | http://arxiv.org/abs/1707.01395v3 |
| http://arxiv.org/pdf/1707.01395v3.pdf | |
| PWC | https://paperswithcode.com/paper/towards-lightweight-convolutional-neural |
| Repo | |
| Framework | |
The Shape of an Image: A Study of Mapper on Images
| Title | The Shape of an Image: A Study of Mapper on Images |
| Authors | Alejandro Robles, Mustafa Hajij, Paul Rosen |
| Abstract | We study the topological construction called Mapper in the context of simply connected domains, in particular on images. The Mapper construction can be considered as a generalization for contour, split, and joint trees on simply connected domains. A contour tree on an image domain assumes the height function to be a piecewise linear Morse function. This is a rather restrictive class of functions and does not allow us to explore the topology for most real world images. The Mapper construction avoids this limitation by assuming only continuity on the height function allowing this construction to robustly deal with a significant larger set of images. We provide a customized construction for Mapper on images, give a fast algorithm to compute it, and show how to simplify the Mapper structure in this case. Finally, we provide a simple procedure that guarantees the equivalence of Mapper to contour, join, and split trees on a simply connected domain. |
| Tasks | |
| Published | 2017-10-24 |
| URL | http://arxiv.org/abs/1710.09008v2 |
| http://arxiv.org/pdf/1710.09008v2.pdf | |
| PWC | https://paperswithcode.com/paper/the-shape-of-an-image-a-study-of-mapper-on |
| Repo | |
| Framework | |
Max K-armed bandit: On the ExtremeHunter algorithm and beyond
| Title | Max K-armed bandit: On the ExtremeHunter algorithm and beyond |
| Authors | Mastane Achab, Stephan Clémençon, Aurélien Garivier, Anne Sabourin, Claire Vernade |
| Abstract | This paper is devoted to the study of the max K-armed bandit problem, which consists in sequentially allocating resources in order to detect extreme values. Our contribution is twofold. We first significantly refine the analysis of the ExtremeHunter algorithm carried out in Carpentier and Valko (2014), and next propose an alternative approach, showing that, remarkably, Extreme Bandits can be reduced to a classical version of the bandit problem to a certain extent. Beyond the formal analysis, these two approaches are compared through numerical experiments. |
| Tasks | |
| Published | 2017-07-27 |
| URL | http://arxiv.org/abs/1707.08820v1 |
| http://arxiv.org/pdf/1707.08820v1.pdf | |
| PWC | https://paperswithcode.com/paper/max-k-armed-bandit-on-the-extremehunter |
| Repo | |
| Framework | |
Unifying Local and Global Change Detection in Dynamic Networks
| Title | Unifying Local and Global Change Detection in Dynamic Networks |
| Authors | Wenzhe Li, Dong Guo, Greg Ver Steeg, Aram Galstyan |
| Abstract | Many real-world networks are complex dynamical systems, where both local (e.g., changing node attributes) and global (e.g., changing network topology) processes unfold over time. Local dynamics may provoke global changes in the network, and the ability to detect such effects could have profound implications for a number of real-world problems. Most existing techniques focus individually on either local or global aspects of the problem or treat the two in isolation from each other. In this paper we propose a novel network model that simultaneously accounts for both local and global dynamics. To the best of our knowledge, this is the first attempt at modeling and detecting local and global change points on dynamic networks via a unified generative framework. Our model is built upon the popular mixed membership stochastic blockmodels (MMSB) with sparse co-evolving patterns. We derive an efficient stochastic gradient Langevin dynamics (SGLD) sampler for our proposed model, which allows it to scale to potentially very large networks. Finally, we validate our model on both synthetic and real-world data and demonstrate its superiority over several baselines. |
| Tasks | |
| Published | 2017-10-09 |
| URL | http://arxiv.org/abs/1710.03035v1 |
| http://arxiv.org/pdf/1710.03035v1.pdf | |
| PWC | https://paperswithcode.com/paper/unifying-local-and-global-change-detection-in |
| Repo | |
| Framework | |
Conceptual Spaces for Cognitive Architectures: A Lingua Franca for Different Levels of Representation
| Title | Conceptual Spaces for Cognitive Architectures: A Lingua Franca for Different Levels of Representation |
| Authors | Antonio Lieto, Antonio Chella, Marcello Frixione |
| Abstract | During the last decades, many cognitive architectures (CAs) have been realized adopting different assumptions about the organization and the representation of their knowledge level. Some of them (e.g. SOAR [Laird (2012)]) adopt a classical symbolic approach, some (e.g. LEABRA [O’Reilly and Munakata (2000)]) are based on a purely connectionist model, while others (e.g. CLARION [Sun (2006)] adopt a hybrid approach combining connectionist and symbolic representational levels. Additionally, some attempts (e.g. biSOAR) trying to extend the representational capacities of CAs by integrating diagrammatical representations and reasoning are also available [Kurup and Chandrasekaran (2007)]. In this paper we propose a reflection on the role that Conceptual Spaces, a framework developed by Peter G"ardenfors [G"ardenfors (2000)] more than fifteen years ago, can play in the current development of the Knowledge Level in Cognitive Systems and Architectures. In particular, we claim that Conceptual Spaces offer a lingua franca that allows to unify and generalize many aspects of the symbolic, sub-symbolic and diagrammatic approaches (by overcoming some of their typical problems) and to integrate them on a common ground. In doing so we extend and detail some of the arguments explored by G"ardenfors [G"ardenfors (1997)] for defending the need of a conceptual, intermediate, representation level between the symbolic and the sub-symbolic one. |
| Tasks | |
| Published | 2017-01-02 |
| URL | http://arxiv.org/abs/1701.00464v1 |
| http://arxiv.org/pdf/1701.00464v1.pdf | |
| PWC | https://paperswithcode.com/paper/conceptual-spaces-for-cognitive-architectures |
| Repo | |
| Framework | |
On Relaxing Determinism in Arithmetic Circuits
| Title | On Relaxing Determinism in Arithmetic Circuits |
| Authors | Arthur Choi, Adnan Darwiche |
| Abstract | The past decade has seen a significant interest in learning tractable probabilistic representations. Arithmetic circuits (ACs) were among the first proposed tractable representations, with some subsequent representations being instances of ACs with weaker or stronger properties. In this paper, we provide a formal basis under which variants on ACs can be compared, and where the precise roles and semantics of their various properties can be made more transparent. This allows us to place some recent developments on ACs in a clearer perspective and to also derive new results for ACs. This includes an exponential separation between ACs with and without determinism; completeness and incompleteness results; and tractability results (or lack thereof) when computing most probable explanations (MPEs). |
| Tasks | |
| Published | 2017-08-22 |
| URL | http://arxiv.org/abs/1708.06846v1 |
| http://arxiv.org/pdf/1708.06846v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-relaxing-determinism-in-arithmetic |
| Repo | |
| Framework | |
