Paper Group ANR 675
Judging a Book by its Description : Analyzing Gender Stereotypes in the Man Bookers Prize Winning Fiction. High Dimensional Estimation, Basis Assets, and Adaptive Multi-Factor Models. BinarEye: An Always-On Energy-Accuracy-Scalable Binary CNN Processor With All Memory On Chip in 28nm CMOS. DeepIR: A Deep Semantics Driven Framework for Image Retarge …
Judging a Book by its Description : Analyzing Gender Stereotypes in the Man Bookers Prize Winning Fiction
Title | Judging a Book by its Description : Analyzing Gender Stereotypes in the Man Bookers Prize Winning Fiction |
Authors | Nishtha Madaan, Sameep Mehta, Shravika Mittal, Ashima Suvarna |
Abstract | The presence of gender stereotypes in many aspects of society is a well-known phenomenon. In this paper, we focus on studying and quantifying such stereotypes and bias in the Man Bookers Prize winning fiction. We consider 275 books shortlisted for Man Bookers Prize between 1969 and 2017. The gender bias is analyzed by semantic modeling of book descriptions on Goodreads. This reveals the pervasiveness of gender bias and stereotype in the books on different features like occupation, introductions and actions associated to the characters in the book. |
Tasks | |
Published | 2018-07-25 |
URL | http://arxiv.org/abs/1807.10615v1 |
http://arxiv.org/pdf/1807.10615v1.pdf | |
PWC | https://paperswithcode.com/paper/judging-a-book-by-its-description-analyzing |
Repo | |
Framework | |
High Dimensional Estimation, Basis Assets, and Adaptive Multi-Factor Models
Title | High Dimensional Estimation, Basis Assets, and Adaptive Multi-Factor Models |
Authors | Liao Zhu, Sumanta Basu, Robert A. Jarrow, Martin T. Wells |
Abstract | The paper proposes a new algorithm for the high-dimensional financial data – the Groupwise Interpretable Basis Selection (GIBS) algorithm, to estimate a new Adaptive Multi-Factor (AMF) asset pricing model, implied by the recently developed Generalized Arbitrage Pricing Theory, which relaxes the convention that the number of risk-factors is small. We first obtain an adaptive collection of basis assets and then simultaneously test which basis assets correspond to which securities, using high-dimensional methods. The AMF model, along with the GIBS algorithm, is shown to have a significantly better fitting and prediction power than the Fama-French 5-factor model. |
Tasks | |
Published | 2018-04-23 |
URL | https://arxiv.org/abs/1804.08472v5 |
https://arxiv.org/pdf/1804.08472v5.pdf | |
PWC | https://paperswithcode.com/paper/high-dimensional-estimation-and-multi-factor |
Repo | |
Framework | |
BinarEye: An Always-On Energy-Accuracy-Scalable Binary CNN Processor With All Memory On Chip in 28nm CMOS
Title | BinarEye: An Always-On Energy-Accuracy-Scalable Binary CNN Processor With All Memory On Chip in 28nm CMOS |
Authors | Bert Moons, Daniel Bankman, Lita Yang, Boris Murmann, Marian Verhelst |
Abstract | This paper introduces BinarEye: a digital processor for always-on Binary Convolutional Neural Networks. The chip maximizes data reuse through a Neuron Array exploiting local weight Flip-Flops. It stores full network models and feature maps and hence requires no off-chip bandwidth, which leads to a 230 1b-TOPS/W peak efficiency. Its 3 levels of flexibility - (a) weight reconfiguration, (b) a programmable network depth and (c) a programmable network width - allow trading energy for accuracy depending on the task’s requirements. BinarEye’s full system input-to-label energy consumption ranges from 14.4uJ/f for 86% CIFAR-10 and 98% owner recognition down to 0.92uJ/f for 94% face detection at up to 1700 frames per second. This is 3-12-70x more efficient than the state-of-the-art at on-par accuracy. |
Tasks | Face Detection |
Published | 2018-04-16 |
URL | http://arxiv.org/abs/1804.05554v1 |
http://arxiv.org/pdf/1804.05554v1.pdf | |
PWC | https://paperswithcode.com/paper/binareye-an-always-on-energy-accuracy |
Repo | |
Framework | |
DeepIR: A Deep Semantics Driven Framework for Image Retargeting
Title | DeepIR: A Deep Semantics Driven Framework for Image Retargeting |
Authors | Jianxin Lin, Tiankuang Zhou, Zhibo Chen |
Abstract | We present \emph{Deep Image Retargeting} (\emph{DeepIR}), a coarse-to-fine framework for content-aware image retargeting. Our framework first constructs the semantic structure of input image with a deep convolutional neural network. Then a uniform re-sampling that suits for semantic structure preserving is devised to resize feature maps to target aspect ratio at each feature layer. The final retargeting result is generated by coarse-to-fine nearest neighbor field search and step-by-step nearest neighbor field fusion. We empirically demonstrate the effectiveness of our model with both qualitative and quantitative results on widely used RetargetMe dataset. |
Tasks | |
Published | 2018-11-19 |
URL | https://arxiv.org/abs/1811.07793v3 |
https://arxiv.org/pdf/1811.07793v3.pdf | |
PWC | https://paperswithcode.com/paper/deepir-a-deep-semantics-driven-framework-for |
Repo | |
Framework | |
Beyond Trade-off: Accelerate FCN-based Face Detector with Higher Accuracy
Title | Beyond Trade-off: Accelerate FCN-based Face Detector with Higher Accuracy |
Authors | Guanglu Song, Yu Liu, Ming Jiang, Yujie Wang, Junjie Yan, Biao Leng |
Abstract | Fully convolutional neural network (FCN) has been dominating the game of face detection task for a few years with its congenital capability of sliding-window-searching with shared kernels, which boiled down all the redundant calculation, and most recent state-of-the-art methods such as Faster-RCNN, SSD, YOLO and FPN use FCN as their backbone. So here comes one question: Can we find a universal strategy to further accelerate FCN with higher accuracy, so could accelerate all the recent FCN-based methods? To analyze this, we decompose the face searching space into two orthogonal directions, scale' and spatial’. Only a few coordinates in the space expanded by the two base vectors indicate foreground. So if FCN could ignore most of the other points, the searching space and false alarm should be significantly boiled down. Based on this philosophy, a novel method named scale estimation and spatial attention proposal ($S^2AP$) is proposed to pay attention to some specific scales and valid locations in the image pyramid. Furthermore, we adopt a masked-convolution operation based on the attention result to accelerate FCN calculation. Experiments show that FCN-based method RPN can be accelerated by about $4\times$ with the help of $S^2AP$ and masked-FCN and at the same time it can also achieve the state-of-the-art on FDDB, AFW and MALF face detection benchmarks as well. |
Tasks | Face Detection |
Published | 2018-04-14 |
URL | http://arxiv.org/abs/1804.05197v2 |
http://arxiv.org/pdf/1804.05197v2.pdf | |
PWC | https://paperswithcode.com/paper/beyond-trade-off-accelerate-fcn-based-face |
Repo | |
Framework | |
Contextual Neural Model for Translating Bilingual Multi-Speaker Conversations
Title | Contextual Neural Model for Translating Bilingual Multi-Speaker Conversations |
Authors | Sameen Maruf, André F. T. Martins, Gholamreza Haffari |
Abstract | Recent works in neural machine translation have begun to explore document translation. However, translating online multi-speaker conversations is still an open problem. In this work, we propose the task of translating Bilingual Multi-Speaker Conversations, and explore neural architectures which exploit both source and target-side conversation histories for this task. To initiate an evaluation for this task, we introduce datasets extracted from Europarl v7 and OpenSubtitles2016. Our experiments on four language-pairs confirm the significance of leveraging conversation history, both in terms of BLEU and manual evaluation. |
Tasks | Machine Translation |
Published | 2018-09-02 |
URL | http://arxiv.org/abs/1809.00344v1 |
http://arxiv.org/pdf/1809.00344v1.pdf | |
PWC | https://paperswithcode.com/paper/contextual-neural-model-for-translating |
Repo | |
Framework | |
Probabilistic Prediction of Interactive Driving Behavior via Hierarchical Inverse Reinforcement Learning
Title | Probabilistic Prediction of Interactive Driving Behavior via Hierarchical Inverse Reinforcement Learning |
Authors | Liting Sun, Wei Zhan, Masayoshi Tomizuka |
Abstract | Autonomous vehicles (AVs) are on the road. To safely and efficiently interact with other road participants, AVs have to accurately predict the behavior of surrounding vehicles and plan accordingly. Such prediction should be probabilistic, to address the uncertainties in human behavior. Such prediction should also be interactive, since the distribution over all possible trajectories of the predicted vehicle depends not only on historical information, but also on future plans of other vehicles that interact with it. To achieve such interaction-aware predictions, we propose a probabilistic prediction approach based on hierarchical inverse reinforcement learning (IRL). First, we explicitly consider the hierarchical trajectory-generation process of human drivers involving both discrete and continuous driving decisions. Based on this, the distribution over all future trajectories of the predicted vehicle is formulated as a mixture of distributions partitioned by the discrete decisions. Then we apply IRL hierarchically to learn the distributions from real human demonstrations. A case study for the ramp-merging driving scenario is provided. The quantitative results show that the proposed approach can accurately predict both the discrete driving decisions such as yield or pass as well as the continuous trajectories. |
Tasks | Autonomous Vehicles |
Published | 2018-09-09 |
URL | http://arxiv.org/abs/1809.02926v1 |
http://arxiv.org/pdf/1809.02926v1.pdf | |
PWC | https://paperswithcode.com/paper/probabilistic-prediction-of-interactive |
Repo | |
Framework | |
A Fingerprint Indexing Method Based on Minutia Descriptor and Clustering
Title | A Fingerprint Indexing Method Based on Minutia Descriptor and Clustering |
Authors | Gwang-Il Ri, Chol-Gyun Ri, Su-Rim Ji |
Abstract | In this paper we propose a novel fingerprint indexing approach for speeding up in the fingerprint recognition system. What kind of features are used for indexing and how to employ the extracted features for searching are crucial for the fingerprint indexing. In this paper, we select a minutia descriptor, which has been used to improve the accuracy of the fingerprint matching, as a local feature for indexing and construct a fixed-length feature vector which will be used for searching from the minutia descriptors of the fingerprint image using a clustering. And we propose a fingerprint searching approach that uses the Euclidean distance between two feature vectors as the similarity between two indexing features. Our indexing approach has several benefits. It reduces searching time significantly and is irrespective of the existence of singular points and robust even though the size of the fingerprint image is small or the quality is low. And the constructed indexing vector by this approach is independent of the features which are used for indexing based on the geometrical relations between the minutiae, like one based on the minutiae triplets. Thus, the proposed approach could be combined with other indexing approaches to gain a better indexing performance. |
Tasks | |
Published | 2018-11-21 |
URL | http://arxiv.org/abs/1811.08645v1 |
http://arxiv.org/pdf/1811.08645v1.pdf | |
PWC | https://paperswithcode.com/paper/a-fingerprint-indexing-method-based-on |
Repo | |
Framework | |
Learning Conceptual Space Representations of Interrelated Concepts
Title | Learning Conceptual Space Representations of Interrelated Concepts |
Authors | Zied Bouraoui, Steven Schockaert |
Abstract | Several recently proposed methods aim to learn conceptual space representations from large text collections. These learned representations asso- ciate each object from a given domain of interest with a point in a high-dimensional Euclidean space, but they do not model the concepts from this do- main, and can thus not directly be used for catego- rization and related cognitive tasks. A natural solu- tion is to represent concepts as Gaussians, learned from the representations of their instances, but this can only be reliably done if sufficiently many in- stances are given, which is often not the case. In this paper, we introduce a Bayesian model which addresses this problem by constructing informative priors from background knowledge about how the concepts of interest are interrelated with each other. We show that this leads to substantially better pre- dictions in a knowledge base completion task. |
Tasks | Knowledge Base Completion |
Published | 2018-05-03 |
URL | http://arxiv.org/abs/1805.01276v2 |
http://arxiv.org/pdf/1805.01276v2.pdf | |
PWC | https://paperswithcode.com/paper/learning-conceptual-space-representations-of |
Repo | |
Framework | |
DOP: Deep Optimistic Planning with Approximate Value Function Evaluation
Title | DOP: Deep Optimistic Planning with Approximate Value Function Evaluation |
Authors | Francesco Riccio, Roberto Capobianco, Daniele Nardi |
Abstract | Research on reinforcement learning has demonstrated promising results in manifold applications and domains. Still, efficiently learning effective robot behaviors is very difficult, due to unstructured scenarios, high uncertainties, and large state dimensionality (e.g. multi-agent systems or hyper-redundant robots). To alleviate this problem, we present DOP, a deep model-based reinforcement learning algorithm, which exploits action values to both (1) guide the exploration of the state space and (2) plan effective policies. Specifically, we exploit deep neural networks to learn Q-functions that are used to attack the curse of dimensionality during a Monte-Carlo tree search. Our algorithm, in fact, constructs upper confidence bounds on the learned value function to select actions optimistically. We implement and evaluate DOP on different scenarios: (1) a cooperative navigation problem, (2) a fetching task for a 7-DOF KUKA robot, and (3) a human-robot handover with a humanoid robot (both in simulation and real). The obtained results show the effectiveness of DOP in the chosen applications, where action values drive the exploration and reduce the computational demand of the planning process while achieving good performance. |
Tasks | |
Published | 2018-03-22 |
URL | http://arxiv.org/abs/1803.08501v1 |
http://arxiv.org/pdf/1803.08501v1.pdf | |
PWC | https://paperswithcode.com/paper/dop-deep-optimistic-planning-with-approximate |
Repo | |
Framework | |
Ambient Hidden Space of Generative Adversarial Networks
Title | Ambient Hidden Space of Generative Adversarial Networks |
Authors | Xinhan Di, Pengqian Yu, Meng Tian |
Abstract | Generative adversarial models are powerful tools to model structure in complex distributions for a variety of tasks. Current techniques for learning generative models require an access to samples which have high quality, and advanced generative models are applied to generate samples from noisy training data through ambient modules. However, the modules are only practical for the output space of the generator, and their application in the hidden space is not well studied. In this paper, we extend the ambient module to the hidden space of the generator, and provide the uniqueness condition and the corresponding strategy for the ambient hidden generator in the adversarial training process. We report the practicality of the proposed method on the benchmark dataset. |
Tasks | |
Published | 2018-07-02 |
URL | http://arxiv.org/abs/1807.00780v1 |
http://arxiv.org/pdf/1807.00780v1.pdf | |
PWC | https://paperswithcode.com/paper/ambient-hidden-space-of-generative |
Repo | |
Framework | |
Weakly Supervised Deep Learning for Thoracic Disease Classification and Localization on Chest X-rays
Title | Weakly Supervised Deep Learning for Thoracic Disease Classification and Localization on Chest X-rays |
Authors | Chaochao Yan, Jiawen Yao, Ruoyu Li, Zheng Xu, Junzhou Huang |
Abstract | Chest X-rays is one of the most commonly available and affordable radiological examinations in clinical practice. While detecting thoracic diseases on chest X-rays is still a challenging task for machine intelligence, due to 1) the highly varied appearance of lesion areas on X-rays from patients of different thoracic disease and 2) the shortage of accurate pixel-level annotations by radiologists for model training. Existing machine learning methods are unable to deal with the challenge that thoracic diseases usually happen in localized disease-specific areas. In this article, we propose a weakly supervised deep learning framework equipped with squeeze-and-excitation blocks, multi-map transfer, and max-min pooling for classifying thoracic diseases as well as localizing suspicious lesion regions. The comprehensive experiments and discussions are performed on the ChestX-ray14 dataset. Both numerical and visual results have demonstrated the effectiveness of the proposed model and its better performance against the state-of-the-art pipelines. |
Tasks | Thoracic Disease Classification |
Published | 2018-07-16 |
URL | http://arxiv.org/abs/1807.06067v1 |
http://arxiv.org/pdf/1807.06067v1.pdf | |
PWC | https://paperswithcode.com/paper/weakly-supervised-deep-learning-for-thoracic |
Repo | |
Framework | |
End-to-End Deep Kronecker-Product Matching for Person Re-identification
Title | End-to-End Deep Kronecker-Product Matching for Person Re-identification |
Authors | Yantao Shen, Tong Xiao, Hongsheng Li, Shuai Yi, Xiaogang Wang |
Abstract | Person re-identification aims to robustly measure similarities between person images. The significant variation of person poses and viewing angles challenges for accurate person re-identification. The spatial layout and correspondences between query person images are vital information for tackling this problem but are ignored by most state-of-the-art methods. In this paper, we propose a novel Kronecker Product Matching module to match feature maps of different persons in an end-to-end trainable deep neural network. A novel feature soft warping scheme is designed for aligning the feature maps based on matching results, which is shown to be crucial for achieving superior accuracy. The multi-scale features based on hourglass-like networks and self-residual attention are also exploited to further boost the re-identification performance. The proposed approach outperforms state-of-the-art methods on the Market-1501, CUHK03, and DukeMTMC datasets, which demonstrates the effectiveness and generalization ability of our proposed approach. |
Tasks | Person Re-Identification |
Published | 2018-07-30 |
URL | http://arxiv.org/abs/1807.11182v1 |
http://arxiv.org/pdf/1807.11182v1.pdf | |
PWC | https://paperswithcode.com/paper/end-to-end-deep-kronecker-product-matching |
Repo | |
Framework | |
Mean-field theory of graph neural networks in graph partitioning
Title | Mean-field theory of graph neural networks in graph partitioning |
Authors | Tatsuro Kawamoto, Masashi Tsubaki, Tomoyuki Obuchi |
Abstract | A theoretical performance analysis of the graph neural network (GNN) is presented. For classification tasks, the neural network approach has the advantage in terms of flexibility that it can be employed in a data-driven manner, whereas Bayesian inference requires the assumption of a specific model. A fundamental question is then whether GNN has a high accuracy in addition to this flexibility. Moreover, whether the achieved performance is predominately a result of the backpropagation or the architecture itself is a matter of considerable interest. To gain a better insight into these questions, a mean-field theory of a minimal GNN architecture is developed for the graph partitioning problem. This demonstrates a good agreement with numerical experiments. |
Tasks | Bayesian Inference, graph partitioning |
Published | 2018-10-29 |
URL | http://arxiv.org/abs/1810.11908v1 |
http://arxiv.org/pdf/1810.11908v1.pdf | |
PWC | https://paperswithcode.com/paper/mean-field-theory-of-graph-neural-networks-in |
Repo | |
Framework | |
A Memristor based Unsupervised Neuromorphic System Towards Fast and Energy-Efficient GAN
Title | A Memristor based Unsupervised Neuromorphic System Towards Fast and Energy-Efficient GAN |
Authors | F. Liu, C. Liu, F. Bi |
Abstract | Deep Learning has gained immense success in pushing today’s artificial intelligence forward. To solve the challenge of limited labeled data in the supervised learning world, unsupervised learning has been proposed years ago while low accuracy hinters its realistic applications. Generative adversarial network (GAN) emerges as an unsupervised learning approach with promising accuracy and are under extensively study. However, the execution of GAN is extremely memory and computation intensive and results in ultra-low speed and high-power consumption. In this work, we proposed a holistic solution for fast and energy-efficient GAN computation through a memristor-based neuromorphic system. First, we exploited a hardware and software co-design approach to map the computation blocks in GAN efficiently. We also proposed an efficient data flow for optimal parallelism training and testing, depending on the computation correlations between different computing blocks. To compute the unique and complex loss of GAN, we developed a diff-block with optimized accuracy and performance. The experiment results on big data show that our design achieves 2.8x speedup and 6.1x energy-saving compared with the traditional GPU accelerator, as well as 5.5x speedup and 1.4x energy-saving compared with the previous FPGA-based accelerator. |
Tasks | |
Published | 2018-05-09 |
URL | https://arxiv.org/abs/1806.01775v4 |
https://arxiv.org/pdf/1806.01775v4.pdf | |
PWC | https://paperswithcode.com/paper/a-memristor-based-unsupervised-neuromorphic |
Repo | |
Framework | |