Paper Group ANR 577
Preference-based performance measures for Time-Domain Global Similarity method. Grounded Recurrent Neural Networks. C-WSL: Count-guided Weakly Supervised Localization. Hierarchical Modeling of Seed Variety Yields and Decision Making for Future Planting Plans. A New Point-set Registration Algorithm for Fingerprint Matching. Statistical Cost Sharing. …
Preference-based performance measures for Time-Domain Global Similarity method
| Title | Preference-based performance measures for Time-Domain Global Similarity method |
| Authors | Ting Lan, Jian Liu, Hong Qin |
| Abstract | For Time-Domain Global Similarity (TDGS) method, which transforms the data cleaning problem into a binary classification problem about the physical similarity between channels, directly adopting common performance measures could only guarantee the performance for physical similarity. Nevertheless, practical data cleaning tasks have preferences for the correctness of original data sequences. To obtain the general expressions of performance measures based on the preferences of tasks, the mapping relations between performance of TDGS method about physical similarity and correctness of data sequences are investigated by probability theory in this paper. Performance measures for TDGS method in several common data cleaning tasks are set. Cases when these preference-based performance measures could be simplified are introduced. |
| Tasks | |
| Published | 2017-06-30 |
| URL | http://arxiv.org/abs/1706.10020v2 |
| http://arxiv.org/pdf/1706.10020v2.pdf | |
| PWC | https://paperswithcode.com/paper/preference-based-performance-measures-for |
| Repo | |
| Framework | |
Grounded Recurrent Neural Networks
| Title | Grounded Recurrent Neural Networks |
| Authors | Ankit Vani, Yacine Jernite, David Sontag |
| Abstract | In this work, we present the Grounded Recurrent Neural Network (GRNN), a recurrent neural network architecture for multi-label prediction which explicitly ties labels to specific dimensions of the recurrent hidden state (we call this process “grounding”). The approach is particularly well-suited for extracting large numbers of concepts from text. We apply the new model to address an important problem in healthcare of understanding what medical concepts are discussed in clinical text. Using a publicly available dataset derived from Intensive Care Units, we learn to label a patient’s diagnoses and procedures from their discharge summary. Our evaluation shows a clear advantage to using our proposed architecture over a variety of strong baselines. |
| Tasks | |
| Published | 2017-05-23 |
| URL | http://arxiv.org/abs/1705.08557v1 |
| http://arxiv.org/pdf/1705.08557v1.pdf | |
| PWC | https://paperswithcode.com/paper/grounded-recurrent-neural-networks |
| Repo | |
| Framework | |
C-WSL: Count-guided Weakly Supervised Localization
| Title | C-WSL: Count-guided Weakly Supervised Localization |
| Authors | Mingfei Gao, Ang Li, Ruichi Yu, Vlad I. Morariu, Larry S. Davis |
| Abstract | We introduce count-guided weakly supervised localization (C-WSL), an approach that uses per-class object count as a new form of supervision to improve weakly supervised localization (WSL). C-WSL uses a simple count-based region selection algorithm to select high-quality regions, each of which covers a single object instance during training, and improves existing WSL methods by training with the selected regions. To demonstrate the effectiveness of C-WSL, we integrate it into two WSL architectures and conduct extensive experiments on VOC2007 and VOC2012. Experimental results show that C-WSL leads to large improvements in WSL and that the proposed approach significantly outperforms the state-of-the-art methods. The results of annotation experiments on VOC2007 suggest that a modest extra time is needed to obtain per-class object counts compared to labeling only object categories in an image. Furthermore, we reduce the annotation time by more than $2\times$ and $38\times$ compared to center-click and bounding-box annotations. |
| Tasks | |
| Published | 2017-11-14 |
| URL | http://arxiv.org/abs/1711.05282v2 |
| http://arxiv.org/pdf/1711.05282v2.pdf | |
| PWC | https://paperswithcode.com/paper/c-wsl-count-guided-weakly-supervised |
| Repo | |
| Framework | |
Hierarchical Modeling of Seed Variety Yields and Decision Making for Future Planting Plans
| Title | Hierarchical Modeling of Seed Variety Yields and Decision Making for Future Planting Plans |
| Authors | Huaiyang Zhong, Xiaocheng Li, David Lobell, Stefano Ermon, Margaret L. Brandeau |
| Abstract | Eradicating hunger and malnutrition is a key development goal of the 21st century. We address the problem of optimally identifying seed varieties to reliably increase crop yield within a risk-sensitive decision-making framework. Specifically, we introduce a novel hierarchical machine learning mechanism for predicting crop yield (the yield of different seed varieties of the same crop). We integrate this prediction mechanism with a weather forecasting model, and propose three different approaches for decision making under uncertainty to select seed varieties for planting so as to balance yield maximization and risk.We apply our model to the problem of soybean variety selection given in the 2016 Syngenta Crop Challenge. Our prediction model achieves a median absolute error of 3.74 bushels per acre and thus provides good estimates for input into the decision models.Our decision models identify the selection of soybean varieties that appropriately balance yield and risk as a function of the farmer’s risk aversion level. More generally, our models support farmers in decision making about which seed varieties to plant. |
| Tasks | Decision Making, Decision Making Under Uncertainty, Weather Forecasting |
| Published | 2017-11-15 |
| URL | http://arxiv.org/abs/1711.05809v1 |
| http://arxiv.org/pdf/1711.05809v1.pdf | |
| PWC | https://paperswithcode.com/paper/hierarchical-modeling-of-seed-variety-yields |
| Repo | |
| Framework | |
A New Point-set Registration Algorithm for Fingerprint Matching
| Title | A New Point-set Registration Algorithm for Fingerprint Matching |
| Authors | A. Pasha Hosseinbor, Renat Zhdanov, Alexander Ushveridze |
| Abstract | A novel minutia-based fingerprint matching algorithm is proposed that employs iterative global alignment on two minutia sets. The matcher considers all possible minutia pairings and iteratively aligns the two sets until the number of minutia pairs does not exceed the maximum number of allowable one-to-one pairings. The optimal alignment parameters are derived analytically via linear least squares. The first alignment establishes a region of overlap between the two minutia sets, which is then (iteratively) refined by each successive alignment. After each alignment, minutia pairs that exhibit weak correspondence are discarded. The process is repeated until the number of remaining pairs no longer exceeds the maximum number of allowable one-to-one pairings. The proposed algorithm is tested on both the FVC2000 and FVC2002 databases, and the results indicate that the proposed matcher is both effective and efficient for fingerprint authentication; it is fast and does not utilize any computationally expensive mathematical functions (e.g. trigonometric, exponential). In addition to the proposed matcher, another contribution of the paper is the analytical derivation of the least squares solution for the optimal alignment parameters for two point-sets lacking exact correspondence. |
| Tasks | |
| Published | 2017-02-07 |
| URL | http://arxiv.org/abs/1702.01870v1 |
| http://arxiv.org/pdf/1702.01870v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-new-point-set-registration-algorithm-for |
| Repo | |
| Framework | |
Statistical Cost Sharing
| Title | Statistical Cost Sharing |
| Authors | Eric Balkanski, Umar Syed, Sergei Vassilvitskii |
| Abstract | We study the cost sharing problem for cooperative games in situations where the cost function $C$ is not available via oracle queries, but must instead be derived from data, represented as tuples $(S, C(S))$, for different subsets $S$ of players. We formalize this approach, which we call statistical cost sharing, and consider the computation of the core and the Shapley value, when the tuples are drawn from some distribution $\mathcal{D}$. Previous work by Balcan et al. in this setting showed how to compute cost shares that satisfy the core property with high probability for limited classes of functions. We expand on their work and give an algorithm that computes such cost shares for any function with a non-empty core. We complement these results by proving an inapproximability lower bound for a weaker relaxation. We then turn our attention to the Shapley value. We first show that when cost functions come from the family of submodular functions with bounded curvature, $\kappa$, the Shapley value can be approximated from samples up to a $\sqrt{1 - \kappa}$ factor, and that the bound is tight. We then define statistical analogues of the Shapley axioms, and derive a notion of statistical Shapley value. We show that these can always be approximated arbitrarily well for general functions over any distribution $\mathcal{D}$. |
| Tasks | |
| Published | 2017-03-09 |
| URL | http://arxiv.org/abs/1703.03111v1 |
| http://arxiv.org/pdf/1703.03111v1.pdf | |
| PWC | https://paperswithcode.com/paper/statistical-cost-sharing |
| Repo | |
| Framework | |
A Semantic Loss Function for Deep Learning with Symbolic Knowledge
| Title | A Semantic Loss Function for Deep Learning with Symbolic Knowledge |
| Authors | Jingyi Xu, Zilu Zhang, Tal Friedman, Yitao Liang, Guy Van den Broeck |
| Abstract | This paper develops a novel methodology for using symbolic knowledge in deep learning. From first principles, we derive a semantic loss function that bridges between neural output vectors and logical constraints. This loss function captures how close the neural network is to satisfying the constraints on its output. An experimental evaluation shows that it effectively guides the learner to achieve (near-)state-of-the-art results on semi-supervised multi-class classification. Moreover, it significantly increases the ability of the neural network to predict structured objects, such as rankings and paths. These discrete concepts are tremendously difficult to learn, and benefit from a tight integration of deep learning and symbolic reasoning methods. |
| Tasks | |
| Published | 2017-11-29 |
| URL | http://arxiv.org/abs/1711.11157v2 |
| http://arxiv.org/pdf/1711.11157v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-semantic-loss-function-for-deep-learning |
| Repo | |
| Framework | |
Deep Multitask Architecture for Integrated 2D and 3D Human Sensing
| Title | Deep Multitask Architecture for Integrated 2D and 3D Human Sensing |
| Authors | Alin-Ionut Popa, Mihai Zanfir, Cristian Sminchisescu |
| Abstract | We propose a deep multitask architecture for \emph{fully automatic 2d and 3d human sensing} (DMHS), including \emph{recognition and reconstruction}, in \emph{monocular images}. The system computes the figure-ground segmentation, semantically identifies the human body parts at pixel level, and estimates the 2d and 3d pose of the person. The model supports the joint training of all components by means of multi-task losses where early processing stages recursively feed into advanced ones for increasingly complex calculations, accuracy and robustness. The design allows us to tie a complete training protocol, by taking advantage of multiple datasets that would otherwise restrictively cover only some of the model components: complex 2d image data with no body part labeling and without associated 3d ground truth, or complex 3d data with limited 2d background variability. In detailed experiments based on several challenging 2d and 3d datasets (LSP, HumanEva, Human3.6M), we evaluate the sub-structures of the model, the effect of various types of training data in the multitask loss, and demonstrate that state-of-the-art results can be achieved at all processing levels. We also show that in the wild our monocular RGB architecture is perceptually competitive to a state-of-the art (commercial) Kinect system based on RGB-D data. |
| Tasks | |
| Published | 2017-01-31 |
| URL | http://arxiv.org/abs/1701.08985v1 |
| http://arxiv.org/pdf/1701.08985v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-multitask-architecture-for-integrated-2d |
| Repo | |
| Framework | |
End-to-end Active Object Tracking via Reinforcement Learning
| Title | End-to-end Active Object Tracking via Reinforcement Learning |
| Authors | Wenhan Luo, Peng Sun, Fangwei Zhong, Wei Liu, Tong Zhang, Yizhou Wang |
| Abstract | We study active object tracking, where a tracker takes as input the visual observation (i.e., frame sequence) and produces the camera control signal (e.g., move forward, turn left, etc.). Conventional methods tackle the tracking and the camera control separately, which is challenging to tune jointly. It also incurs many human efforts for labeling and many expensive trial-and-errors in realworld. To address these issues, we propose, in this paper, an end-to-end solution via deep reinforcement learning, where a ConvNet-LSTM function approximator is adopted for the direct frame-toaction prediction. We further propose an environment augmentation technique and a customized reward function, which are crucial for a successful training. The tracker trained in simulators (ViZDoom, Unreal Engine) shows good generalization in the case of unseen object moving path, unseen object appearance, unseen background, and distracting object. It can restore tracking when occasionally losing the target. With the experiments over the VOT dataset, we also find that the tracking ability, obtained solely from simulators, can potentially transfer to real-world scenarios. |
| Tasks | Object Tracking |
| Published | 2017-05-30 |
| URL | http://arxiv.org/abs/1705.10561v3 |
| http://arxiv.org/pdf/1705.10561v3.pdf | |
| PWC | https://paperswithcode.com/paper/end-to-end-active-object-tracking-via |
| Repo | |
| Framework | |
Active Tolerant Testing
| Title | Active Tolerant Testing |
| Authors | Avrim Blum, Lunjia Hu |
| Abstract | In this work, we give the first algorithms for tolerant testing of nontrivial classes in the active model: estimating the distance of a target function to a hypothesis class C with respect to some arbitrary distribution D, using only a small number of label queries to a polynomial-sized pool of unlabeled examples drawn from D. Specifically, we show that for the class D of unions of d intervals on the line, we can estimate the error rate of the best hypothesis in the class to an additive error epsilon from only $O(\frac{1}{\epsilon^6}\log \frac{1}{\epsilon})$ label queries to an unlabeled pool of size $O(\frac{d}{\epsilon^2}\log \frac{1}{\epsilon})$. The key point here is the number of labels needed is independent of the VC-dimension of the class. This extends the work of Balcan et al. [2012] who solved the non-tolerant testing problem for this class (distinguishing the zero-error case from the case that the best hypothesis in the class has error greater than epsilon). We also consider the related problem of estimating the performance of a given learning algorithm A in this setting. That is, given a large pool of unlabeled examples drawn from distribution D, can we, from only a few label queries, estimate how well A would perform if the entire dataset were labeled? We focus on k-Nearest Neighbor style algorithms, and also show how our results can be applied to the problem of hyperparameter tuning (selecting the best value of k for the given learning problem). |
| Tasks | |
| Published | 2017-11-01 |
| URL | http://arxiv.org/abs/1711.00388v1 |
| http://arxiv.org/pdf/1711.00388v1.pdf | |
| PWC | https://paperswithcode.com/paper/active-tolerant-testing |
| Repo | |
| Framework | |
Distance-based Confidence Score for Neural Network Classifiers
| Title | Distance-based Confidence Score for Neural Network Classifiers |
| Authors | Amit Mandelbaum, Daphna Weinshall |
| Abstract | The reliable measurement of confidence in classifiers’ predictions is very important for many applications and is, therefore, an important part of classifier design. Yet, although deep learning has received tremendous attention in recent years, not much progress has been made in quantifying the prediction confidence of neural network classifiers. Bayesian models offer a mathematically grounded framework to reason about model uncertainty, but usually come with prohibitive computational costs. In this paper we propose a simple, scalable method to achieve a reliable confidence score, based on the data embedding derived from the penultimate layer of the network. We investigate two ways to achieve desirable embeddings, by using either a distance-based loss or Adversarial Training. We then test the benefits of our method when used for classification error prediction, weighting an ensemble of classifiers, and novelty detection. In all tasks we show significant improvement over traditional, commonly used confidence scores. |
| Tasks | |
| Published | 2017-09-28 |
| URL | http://arxiv.org/abs/1709.09844v1 |
| http://arxiv.org/pdf/1709.09844v1.pdf | |
| PWC | https://paperswithcode.com/paper/distance-based-confidence-score-for-neural |
| Repo | |
| Framework | |
Image Registration of Very Large Images via Genetic Programming
| Title | Image Registration of Very Large Images via Genetic Programming |
| Authors | Sarit Chicotay, Eli David, Nathan S. Netanyahu |
| Abstract | Image registration (IR) is a fundamental task in image processing for matching two or more images of the same scene taken at different times, from different viewpoints and/or by different sensors. Due to the enormous diversity of IR applications, automatic IR remains a challenging problem to this day. A wide range of techniques has been developed for various data types and problems. However, they might not handle effectively very large images, which give rise usually to more complex transformations, e.g., deformations and various other distortions. In this paper we present a genetic programming (GP)-based approach for IR, which could offer a significant advantage in dealing with very large images, as it does not make any prior assumptions about the transformation model. Thus, by incorporating certain generic building blocks into the proposed GP framework, we hope to realize a large set of specialized transformations that should yield accurate registration of very large images. |
| Tasks | Image Registration |
| Published | 2017-11-17 |
| URL | http://arxiv.org/abs/1711.06764v2 |
| http://arxiv.org/pdf/1711.06764v2.pdf | |
| PWC | https://paperswithcode.com/paper/image-registration-of-very-large-images-via |
| Repo | |
| Framework | |
PRM-RL: Long-range Robotic Navigation Tasks by Combining Reinforcement Learning and Sampling-based Planning
| Title | PRM-RL: Long-range Robotic Navigation Tasks by Combining Reinforcement Learning and Sampling-based Planning |
| Authors | Aleksandra Faust, Oscar Ramirez, Marek Fiser, Kenneth Oslund, Anthony Francis, James Davidson, Lydia Tapia |
| Abstract | We present PRM-RL, a hierarchical method for long-range navigation task completion that combines sampling based path planning with reinforcement learning (RL). The RL agents learn short-range, point-to-point navigation policies that capture robot dynamics and task constraints without knowledge of the large-scale topology. Next, the sampling-based planners provide roadmaps which connect robot configurations that can be successfully navigated by the RL agent. The same RL agents are used to control the robot under the direction of the planning, enabling long-range navigation. We use the Probabilistic Roadmaps (PRMs) for the sampling-based planner. The RL agents are constructed using feature-based and deep neural net policies in continuous state and action spaces. We evaluate PRM-RL, both in simulation and on-robot, on two navigation tasks with non-trivial robot dynamics: end-to-end differential drive indoor navigation in office environments, and aerial cargo delivery in urban environments with load displacement constraints. Our results show improvement in task completion over both RL agents on their own and traditional sampling-based planners. In the indoor navigation task, PRM-RL successfully completes up to 215 m long trajectories under noisy sensor conditions, and the aerial cargo delivery completes flights over 1000 m without violating the task constraints in an environment 63 million times larger than used in training. |
| Tasks | |
| Published | 2017-10-11 |
| URL | http://arxiv.org/abs/1710.03937v2 |
| http://arxiv.org/pdf/1710.03937v2.pdf | |
| PWC | https://paperswithcode.com/paper/prm-rl-long-range-robotic-navigation-tasks-by |
| Repo | |
| Framework | |
Lithium NLP: A System for Rich Information Extraction from Noisy User Generated Text on Social Media
| Title | Lithium NLP: A System for Rich Information Extraction from Noisy User Generated Text on Social Media |
| Authors | Preeti Bhargava, Nemanja Spasojevic, Guoning Hu |
| Abstract | In this paper, we describe the Lithium Natural Language Processing (NLP) system - a resource-constrained, high- throughput and language-agnostic system for information extraction from noisy user generated text on social media. Lithium NLP extracts a rich set of information including entities, topics, hashtags and sentiment from text. We discuss several real world applications of the system currently incorporated in Lithium products. We also compare our system with existing commercial and academic NLP systems in terms of performance, information extracted and languages supported. We show that Lithium NLP is at par with and in some cases, outperforms state- of-the-art commercial NLP systems. |
| Tasks | |
| Published | 2017-07-13 |
| URL | http://arxiv.org/abs/1707.04244v1 |
| http://arxiv.org/pdf/1707.04244v1.pdf | |
| PWC | https://paperswithcode.com/paper/lithium-nlp-a-system-for-rich-information |
| Repo | |
| Framework | |
Time Limits in Reinforcement Learning
| Title | Time Limits in Reinforcement Learning |
| Authors | Fabio Pardo, Arash Tavakoli, Vitaly Levdik, Petar Kormushev |
| Abstract | In reinforcement learning, it is common to let an agent interact for a fixed amount of time with its environment before resetting it and repeating the process in a series of episodes. The task that the agent has to learn can either be to maximize its performance over (i) that fixed period, or (ii) an indefinite period where time limits are only used during training to diversify experience. In this paper, we provide a formal account for how time limits could effectively be handled in each of the two cases and explain why not doing so can cause state-aliasing and invalidation of experience replay, leading to suboptimal policies and training instability. In case (i), we argue that the terminations due to time limits are in fact part of the environment, and thus a notion of the remaining time should be included as part of the agent’s input to avoid violation of the Markov property. In case (ii), the time limits are not part of the environment and are only used to facilitate learning. We argue that this insight should be incorporated by bootstrapping from the value of the state at the end of each partial episode. For both cases, we illustrate empirically the significance of our considerations in improving the performance and stability of existing reinforcement learning algorithms, showing state-of-the-art results on several control tasks. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://arxiv.org/abs/1712.00378v3 |
| http://arxiv.org/pdf/1712.00378v3.pdf | |
| PWC | https://paperswithcode.com/paper/time-limits-in-reinforcement-learning |
| Repo | |
| Framework | |
