Paper Group ANR 1032
Dual Attention Matching Network for Context-Aware Feature Sequence based Person Re-Identification. Advancing System Performance with Redundancy: From Biological to Artificial Designs. A Robot to Shape your Natural Plant: The Machine Learning Approach to Model and Control Bio-Hybrid Systems. Phrase-Indexed Question Answering: A New Challenge for Sca …
Dual Attention Matching Network for Context-Aware Feature Sequence based Person Re-Identification
| Title | Dual Attention Matching Network for Context-Aware Feature Sequence based Person Re-Identification |
| Authors | Jianlou Si, Honggang Zhang, Chun-Guang Li, Jason Kuen, Xiangfei Kong, Alex C. Kot, Gang Wang |
| Abstract | Typical person re-identification (ReID) methods usually describe each pedestrian with a single feature vector and match them in a task-specific metric space. However, the methods based on a single feature vector are not sufficient enough to overcome visual ambiguity, which frequently occurs in real scenario. In this paper, we propose a novel end-to-end trainable framework, called Dual ATtention Matching network (DuATM), to learn context-aware feature sequences and perform attentive sequence comparison simultaneously. The core component of our DuATM framework is a dual attention mechanism, in which both intra-sequence and inter-sequence attention strategies are used for feature refinement and feature-pair alignment, respectively. Thus, detailed visual cues contained in the intermediate feature sequences can be automatically exploited and properly compared. We train the proposed DuATM network as a siamese network via a triplet loss assisted with a de-correlation loss and a cross-entropy loss. We conduct extensive experiments on both image and video based ReID benchmark datasets. Experimental results demonstrate the significant advantages of our approach compared to the state-of-the-art methods. |
| Tasks | Person Re-Identification |
| Published | 2018-03-27 |
| URL | http://arxiv.org/abs/1803.09937v1 |
| http://arxiv.org/pdf/1803.09937v1.pdf | |
| PWC | https://paperswithcode.com/paper/dual-attention-matching-network-for-context |
| Repo | |
| Framework | |
Advancing System Performance with Redundancy: From Biological to Artificial Designs
| Title | Advancing System Performance with Redundancy: From Biological to Artificial Designs |
| Authors | Anh Tuan Nguyen, Jian Xu, Diu Khue Luu, Qi Zhao, Zhi Yang |
| Abstract | Redundancy is a fundamental characteristic of many biological processes such as those in the genetic, visual, muscular and nervous system; yet its function has not been fully understood. The conventional interpretation of redundancy is that it serves as a fault-tolerance mechanism, which leads to redundancy’s de facto application in man-made systems for reliability enhancement. On the contrary, our previous works have demonstrated an example where redundancy can be engineered solely for enhancing other aspects of the system, namely accuracy and precision. This design was inspired by the binocular structure of the human vision which we believe may share a similar operation. In this paper, we present a unified theory describing how such utilization of redundancy is feasible through two complementary mechanisms: representational redundancy (RPR) and entangled redundancy (ETR). Besides the previous works, we point out two additional examples where our new understanding of redundancy can be applied to justify a system’s superior performance. One is the human musculoskeletal system (HMS) - a biological instance, and one is the deep residual neural network (ResNet) - an artificial counterpart. We envision that our theory would provide a framework for the future development of bio-inspired redundant artificial systems as well as assist the studies of the fundamental mechanisms governing various biological processes. |
| Tasks | |
| Published | 2018-02-14 |
| URL | http://arxiv.org/abs/1802.05324v1 |
| http://arxiv.org/pdf/1802.05324v1.pdf | |
| PWC | https://paperswithcode.com/paper/advancing-system-performance-with-redundancy |
| Repo | |
| Framework | |
A Robot to Shape your Natural Plant: The Machine Learning Approach to Model and Control Bio-Hybrid Systems
| Title | A Robot to Shape your Natural Plant: The Machine Learning Approach to Model and Control Bio-Hybrid Systems |
| Authors | Mostafa Wahby, Mary Katherine Heinrich, Daniel Nicolas Hofstadler, Payam Zahadat, Sebastian Risi, Phil Ayres, Thomas Schmickl, Heiko Hamann |
| Abstract | Bio-hybrid systems—close couplings of natural organisms with technology—are high potential and still underexplored. In existing work, robots have mostly influenced group behaviors of animals. We explore the possibilities of mixing robots with natural plants, merging useful attributes. Significant synergies arise by combining the plants’ ability to efficiently produce shaped material and the robots’ ability to extend sensing and decision-making behaviors. However, programming robots to control plant motion and shape requires good knowledge of complex plant behaviors. Therefore, we use machine learning to create a holistic plant model and evolve robot controllers. As a benchmark task we choose obstacle avoidance. We use computer vision to construct a model of plant stem stiffening and motion dynamics by training an LSTM network. The LSTM network acts as a forward model predicting change in the plant, driving the evolution of neural network robot controllers. The evolved controllers augment the plants’ natural light-finding and tissue-stiffening behaviors to avoid obstacles and grow desired shapes. We successfully verify the robot controllers and bio-hybrid behavior in reality, with a physical setup and actual plants. |
| Tasks | Decision Making |
| Published | 2018-04-18 |
| URL | http://arxiv.org/abs/1804.06682v2 |
| http://arxiv.org/pdf/1804.06682v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-robot-to-shape-your-natural-plant-the |
| Repo | |
| Framework | |
Phrase-Indexed Question Answering: A New Challenge for Scalable Document Comprehension
| Title | Phrase-Indexed Question Answering: A New Challenge for Scalable Document Comprehension |
| Authors | Minjoon Seo, Tom Kwiatkowski, Ankur P. Parikh, Ali Farhadi, Hannaneh Hajishirzi |
| Abstract | We formalize a new modular variant of current question answering tasks by enforcing complete independence of the document encoder from the question encoder. This formulation addresses a key challenge in machine comprehension by requiring a standalone representation of the document discourse. It additionally leads to a significant scalability advantage since the encoding of the answer candidate phrases in the document can be pre-computed and indexed offline for efficient retrieval. We experiment with baseline models for the new task, which achieve a reasonable accuracy but significantly underperform unconstrained QA models. We invite the QA research community to engage in Phrase-Indexed Question Answering (PIQA, pika) for closing the gap. The leaderboard is at: nlp.cs.washington.edu/piqa |
| Tasks | Question Answering, Reading Comprehension |
| Published | 2018-04-20 |
| URL | http://arxiv.org/abs/1804.07726v2 |
| http://arxiv.org/pdf/1804.07726v2.pdf | |
| PWC | https://paperswithcode.com/paper/phrase-indexed-question-answering-a-new |
| Repo | |
| Framework | |
Time-sensitive Customer Churn Prediction based on PU Learning
| Title | Time-sensitive Customer Churn Prediction based on PU Learning |
| Authors | Li Wang, Chaochao Chen, Jun Zhou, Xiaolong Li |
| Abstract | With the fast development of Internet companies throughout the world, customer churn has become a serious concern. To better help the companies retain their customers, it is important to build a customer churn prediction model to identify the customers who are most likely to churn ahead of time. In this paper, we propose a Time-sensitive Customer Churn Prediction (TCCP) framework based on Positive and Unlabeled (PU) learning technique. Specifically, we obtain the recent data by shortening the observation period, and start to train model as long as enough positive samples are collected, ignoring the absence of the negative examples. We conduct thoroughly experiments on real industry data from Alipay.com. The experimental results demonstrate that TCCP outperforms the rule-based models and the traditional supervised learning models. |
| Tasks | |
| Published | 2018-02-27 |
| URL | http://arxiv.org/abs/1802.09788v1 |
| http://arxiv.org/pdf/1802.09788v1.pdf | |
| PWC | https://paperswithcode.com/paper/time-sensitive-customer-churn-prediction |
| Repo | |
| Framework | |
A Successive-Elimination Approach to Adaptive Robotic Source Seeking
| Title | A Successive-Elimination Approach to Adaptive Robotic Source Seeking |
| Authors | Esther Rolf, David Fridovich-Keil, Max Simchowitz, Benjamin Recht, Claire Tomlin |
| Abstract | We study an adaptive source seeking problem, in which a mobile robot must identify the strongest emitter(s) of a signal in an environment with background emissions. Background signals may be highly heterogeneous and can mislead algorithms that are based on receding horizon control, greedy heuristics, or smooth background priors. We propose AdaSearch, a general algorithm for adaptive source seeking in the face of heterogeneous background noise. AdaSearch combines global trajectory planning with principled confidence intervals in order to concentrate measurements in promising regions while guaranteeing sufficient coverage of the entire area. Theoretical analysis shows that AdaSearch confers gains over a uniform sampling strategy when the distribution of background signals is highly variable. Simulation experiments demonstrate that when applied to the problem of radioactive source seeking, AdaSearch outperforms both uniform sampling and a receding time horizon information-maximization approach based on the current literature. We also demonstrate AdaSearch in hardware, providing further evidence of its potential for real-time implementation. |
| Tasks | Motion Capture |
| Published | 2018-09-27 |
| URL | https://arxiv.org/abs/1809.10611v2 |
| https://arxiv.org/pdf/1809.10611v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-successive-elimination-approach-to-adaptive |
| Repo | |
| Framework | |
ARCHER: Aggressive Rewards to Counter bias in Hindsight Experience Replay
| Title | ARCHER: Aggressive Rewards to Counter bias in Hindsight Experience Replay |
| Authors | Sameera Lanka, Tianfu Wu |
| Abstract | Experience replay is an important technique for addressing sample-inefficiency in deep reinforcement learning (RL), but faces difficulty in learning from binary and sparse rewards due to disproportionately few successful experiences in the replay buffer. Hindsight experience replay (HER) was recently proposed to tackle this difficulty by manipulating unsuccessful transitions, but in doing so, HER introduces a significant bias in the replay buffer experiences and therefore achieves a suboptimal improvement in sample-efficiency. In this paper, we present an analysis on the source of bias in HER, and propose a simple and effective method to counter the bias, to most effectively harness the sample-efficiency provided by HER. Our method, motivated by counter-factual reasoning and called ARCHER, extends HER with a trade-off to make rewards calculated for hindsight experiences numerically greater than real rewards. We validate our algorithm on two continuous control environments from DeepMind Control Suite - Reacher and Finger, which simulate manipulation tasks with a robotic arm - in combination with various reward functions, task complexities and goal sampling strategies. Our experiments consistently demonstrate that countering bias using more aggressive hindsight rewards increases sample efficiency, thus establishing the greater benefit of ARCHER in RL applications with limited computing budget. |
| Tasks | Continuous Control |
| Published | 2018-09-06 |
| URL | http://arxiv.org/abs/1809.02070v2 |
| http://arxiv.org/pdf/1809.02070v2.pdf | |
| PWC | https://paperswithcode.com/paper/archer-aggressive-rewards-to-counter-bias-in |
| Repo | |
| Framework | |
Towards More Efficient Stochastic Decentralized Learning: Faster Convergence and Sparse Communication
| Title | Towards More Efficient Stochastic Decentralized Learning: Faster Convergence and Sparse Communication |
| Authors | Zebang Shen, Aryan Mokhtari, Tengfei Zhou, Peilin Zhao, Hui Qian |
| Abstract | Recently, the decentralized optimization problem is attracting growing attention. Most existing methods are deterministic with high per-iteration cost and have a convergence rate quadratically depending on the problem condition number. Besides, the dense communication is necessary to ensure the convergence even if the dataset is sparse. In this paper, we generalize the decentralized optimization problem to a monotone operator root finding problem, and propose a stochastic algorithm named DSBA that (i) converges geometrically with a rate linearly depending on the problem condition number, and (ii) can be implemented using sparse communication only. Additionally, DSBA handles learning problems like AUC-maximization which cannot be tackled efficiently in the decentralized setting. Experiments on convex minimization and AUC-maximization validate the efficiency of our method. |
| Tasks | |
| Published | 2018-05-25 |
| URL | http://arxiv.org/abs/1805.09969v1 |
| http://arxiv.org/pdf/1805.09969v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-more-efficient-stochastic |
| Repo | |
| Framework | |
A Comparison of CNN-based Face and Head Detectors for Real-Time Video Surveillance Applications
| Title | A Comparison of CNN-based Face and Head Detectors for Real-Time Video Surveillance Applications |
| Authors | Le Thanh Nguyen-Meidine, Eric Granger, Madhu Kiran, Louis-Antoine Blais-Morin |
| Abstract | Detecting faces and heads appearing in video feeds are challenging tasks in real-world video surveillance applications due to variations in appearance, occlusions and complex backgrounds. Recently, several CNN architectures have been proposed to increase the accuracy of detectors, although their computational complexity can be an issue, especially for real-time applications, where faces and heads must be detected live using high-resolution cameras. This paper compares the accuracy and complexity of state-of-the-art CNN architectures that are suitable for face and head detection. Single pass and region-based architectures are reviewed and compared empirically to baseline techniques according to accuracy and to time and memory complexity on images from several challenging datasets. The viability of these architectures is analyzed with real-time video surveillance applications in mind. Results suggest that, although CNN architectures can achieve a very high level of accuracy compared to traditional detectors, their computational cost can represent a limitation for many practical real-time applications. |
| Tasks | Head Detection |
| Published | 2018-09-10 |
| URL | http://arxiv.org/abs/1809.03336v1 |
| http://arxiv.org/pdf/1809.03336v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-comparison-of-cnn-based-face-and-head |
| Repo | |
| Framework | |
Learning Stabilizable Dynamical Systems via Control Contraction Metrics
| Title | Learning Stabilizable Dynamical Systems via Control Contraction Metrics |
| Authors | Sumeet Singh, Vikas Sindhwani, Jean-Jacques E. Slotine, Marco Pavone |
| Abstract | We propose a novel framework for learning stabilizable nonlinear dynamical systems for continuous control tasks in robotics. The key idea is to develop a new control-theoretic regularizer for dynamics fitting rooted in the notion of stabilizability, which guarantees that the learned system can be accompanied by a robust controller capable of stabilizing any open-loop trajectory that the system may generate. By leveraging tools from contraction theory, statistical learning, and convex optimization, we provide a general and tractable semi-supervised algorithm to learn stabilizable dynamics, which can be applied to complex underactuated systems. We validated the proposed algorithm on a simulated planar quadrotor system and observed notably improved trajectory generation and tracking performance with the control-theoretic regularized model over models learned using traditional regression techniques, especially when using a small number of demonstration examples. The results presented illustrate the need to infuse standard model-based reinforcement learning algorithms with concepts drawn from nonlinear control theory for improved reliability. |
| Tasks | Continuous Control |
| Published | 2018-07-31 |
| URL | http://arxiv.org/abs/1808.00113v2 |
| http://arxiv.org/pdf/1808.00113v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-stabilizable-dynamical-systems-via |
| Repo | |
| Framework | |
microNER: A Micro-Service for German Named Entity Recognition based on BiLSTM-CRF
| Title | microNER: A Micro-Service for German Named Entity Recognition based on BiLSTM-CRF |
| Authors | Gregor Wiedemann, Raghav Jindal, Chris Biemann |
| Abstract | For named entity recognition (NER), bidirectional recurrent neural networks became the state-of-the-art technology in recent years. Competing approaches vary with respect to pre-trained word embeddings as well as models for character embeddings to represent sequence information most effectively. For NER in German language texts, these model variations have not been studied extensively. We evaluate the performance of different word and character embeddings on two standard German datasets and with a special focus on out-of-vocabulary words. With F-Scores above 82% for the GermEval’14 dataset and above 85% for the CoNLL’03 dataset, we achieve (near) state-of-the-art performance for this task. We publish several pre-trained models wrapped into a micro-service based on Docker to allow for easy integration of German NER into other applications via a JSON API. |
| Tasks | Named Entity Recognition, Word Embeddings |
| Published | 2018-11-07 |
| URL | http://arxiv.org/abs/1811.02902v1 |
| http://arxiv.org/pdf/1811.02902v1.pdf | |
| PWC | https://paperswithcode.com/paper/microner-a-micro-service-for-german-named |
| Repo | |
| Framework | |
Detecting Heads using Feature Refine Net and Cascaded Multi-Scale Architecture
| Title | Detecting Heads using Feature Refine Net and Cascaded Multi-Scale Architecture |
| Authors | Dezhi Peng, Zikai Sun, Zirong Chen, Zirui Cai, Lele Xie, Lianwen Jin |
| Abstract | This paper presents a method that can accurately detect heads especially small heads under the indoor scene. To achieve this, we propose a novel method, Feature Refine Net (FRN), and a cascaded multi-scale architecture. FRN exploits the multi-scale hierarchical features created by deep convolutional neural networks. The proposed channel weighting method enables FRN to make use of features alternatively and effectively. To improve the performance of small head detection, we propose a cascaded multi-scale architecture which has two detectors. One called global detector is responsible for detecting large objects and acquiring the global distribution information. The other called local detector is designed for small objects detection and makes use of the information provided by global detector. Due to the lack of head detection datasets, we have collected and labeled a new large dataset named SCUT-HEAD which includes 4405 images with 111251 heads annotated. Experiments show that our method has achieved state-of-the-art performance on SCUT-HEAD. |
| Tasks | Head Detection |
| Published | 2018-03-25 |
| URL | http://arxiv.org/abs/1803.09256v4 |
| http://arxiv.org/pdf/1803.09256v4.pdf | |
| PWC | https://paperswithcode.com/paper/detecting-heads-using-feature-refine-net-and |
| Repo | |
| Framework | |
Jointly Discovering Visual Objects and Spoken Words from Raw Sensory Input
| Title | Jointly Discovering Visual Objects and Spoken Words from Raw Sensory Input |
| Authors | David Harwath, Adrià Recasens, Dídac Surís, Galen Chuang, Antonio Torralba, James Glass |
| Abstract | In this paper, we explore neural network models that learn to associate segments of spoken audio captions with the semantically relevant portions of natural images that they refer to. We demonstrate that these audio-visual associative localizations emerge from network-internal representations learned as a by-product of training to perform an image-audio retrieval task. Our models operate directly on the image pixels and speech waveform, and do not rely on any conventional supervision in the form of labels, segmentations, or alignments between the modalities during training. We perform analysis using the Places 205 and ADE20k datasets demonstrating that our models implicitly learn semantically-coupled object and word detectors. |
| Tasks | |
| Published | 2018-04-04 |
| URL | http://arxiv.org/abs/1804.01452v1 |
| http://arxiv.org/pdf/1804.01452v1.pdf | |
| PWC | https://paperswithcode.com/paper/jointly-discovering-visual-objects-and-spoken |
| Repo | |
| Framework | |
A Study on Passage Re-ranking in Embedding based Unsupervised Semantic Search
| Title | A Study on Passage Re-ranking in Embedding based Unsupervised Semantic Search |
| Authors | Md Faisal Mahbub Chowdhury, Vijil Chenthamarakshan, Rishav Chakravarti, Alfio M. Gliozzo |
| Abstract | State of the art approaches for (embedding based) unsupervised semantic search exploits either compositional similarity (of a query and a passage) or pair-wise word (or term) similarity (from the query and the passage). By design, word based approaches do not incorporate similarity in the larger context (query/passage), while compositional similarity based approaches are usually unable to take advantage of the most important cues in the context. In this paper we propose a new compositional similarity based approach, called variable centroid vector (VCVB), that tries to address both of these limitations. We also presents results using a different type of compositional similarity based approach by exploiting universal sentence embedding. We provide empirical evaluation on two different benchmarks. |
| Tasks | Passage Re-Ranking, Sentence Embedding |
| Published | 2018-04-22 |
| URL | http://arxiv.org/abs/1804.08057v4 |
| http://arxiv.org/pdf/1804.08057v4.pdf | |
| PWC | https://paperswithcode.com/paper/a-study-on-passage-re-ranking-in-embedding |
| Repo | |
| Framework | |
Blind Over-the-Air Computation and Data Fusion via Provable Wirtinger Flow
| Title | Blind Over-the-Air Computation and Data Fusion via Provable Wirtinger Flow |
| Authors | Jialin Dong, Yuanming Shi, Zhi Ding |
| Abstract | Over-the-air computation (AirComp) shows great promise to support fast data fusion in Internet-of-Things (IoT) networks. AirComp typically computes desired functions of distributed sensing data by exploiting superposed data transmission in multiple access channels. To overcome its reliance on channel station information (CSI), this work proposes a novel blind over-the-air computation (BlairComp) without requiring CSI access, particularly for low complexity and low latency IoT networks. To solve the resulting non-convex optimization problem without the initialization dependency exhibited by the solutions of a number of recently proposed efficient algorithms, we develop a Wirtinger flow solution to the BlairComp problem based on random initialization. To analyze the resulting efficiency, we prove its statistical optimality and global convergence guarantee. Specifically, in the first stage of the algorithm, the iteration of randomly initialized Wirtinger flow given sufficient data samples can enter a local region that enjoys strong convexity and strong smoothness within a few iterations. We also prove the estimation error of BlairComp in the local region to be sufficiently small. We show that, at the second stage of the algorithm, its estimation error decays exponentially at a linear convergence rate. |
| Tasks | |
| Published | 2018-11-12 |
| URL | http://arxiv.org/abs/1811.04644v1 |
| http://arxiv.org/pdf/1811.04644v1.pdf | |
| PWC | https://paperswithcode.com/paper/blind-over-the-air-computation-and-data |
| Repo | |
| Framework | |
