Paper Group ANR 310
SCNet: Learning Semantic Correspondence. Deep Reinforcement Learning for Conversational AI. Grammatical Inference as a Satisfiability Modulo Theories Problem. General Phase Regularized Reconstruction using Phase Cycling. Semi-Supervised Hierarchical Semantic Object Parsing. Restricting Greed in Training of Generative Adversarial Network. Point of I …
SCNet: Learning Semantic Correspondence
| Title | SCNet: Learning Semantic Correspondence |
| Authors | Kai Han, Rafael S. Rezende, Bumsub Ham, Kwan-Yee K. Wong, Minsu Cho, Cordelia Schmid, Jean Ponce |
| Abstract | This paper addresses the problem of establishing semantic correspondences between images depicting different instances of the same object or scene category. Previous approaches focus on either combining a spatial regularizer with hand-crafted features, or learning a correspondence model for appearance only. We propose instead a convolutional neural network architecture, called SCNet, for learning a geometrically plausible model for semantic correspondence. SCNet uses region proposals as matching primitives, and explicitly incorporates geometric consistency in its loss function. It is trained on image pairs obtained from the PASCAL VOC 2007 keypoint dataset, and a comparative evaluation on several standard benchmarks demonstrates that the proposed approach substantially outperforms both recent deep learning architectures and previous methods based on hand-crafted features. |
| Tasks | |
| Published | 2017-05-11 |
| URL | http://arxiv.org/abs/1705.04043v3 |
| http://arxiv.org/pdf/1705.04043v3.pdf | |
| PWC | https://paperswithcode.com/paper/scnet-learning-semantic-correspondence |
| Repo | |
| Framework | |
Deep Reinforcement Learning for Conversational AI
| Title | Deep Reinforcement Learning for Conversational AI |
| Authors | Mahipal Jadeja, Neelanshi Varia, Agam Shah |
| Abstract | Deep reinforcement learning is revolutionizing the artificial intelligence field. Currently, it serves as a good starting point for constructing intelligent autonomous systems which offer a better knowledge of the visual world. It is possible to scale deep reinforcement learning with the use of deep learning and do amazing tasks such as use of pixels in playing video games. In this paper, key concepts of deep reinforcement learning including reward function, differences between reinforcement learning and supervised learning and models for implementation of reinforcement are discussed. Key challenges related to the implementation of reinforcement learning in conversational AI domain are identified as well as discussed in detail. Various conversational models which are based on deep reinforcement learning (as well as deep learning) are also discussed. In summary, this paper discusses key aspects of deep reinforcement learning which are crucial for designing an efficient conversational AI. |
| Tasks | |
| Published | 2017-09-15 |
| URL | http://arxiv.org/abs/1709.05067v1 |
| http://arxiv.org/pdf/1709.05067v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-reinforcement-learning-for |
| Repo | |
| Framework | |
Grammatical Inference as a Satisfiability Modulo Theories Problem
| Title | Grammatical Inference as a Satisfiability Modulo Theories Problem |
| Authors | Rick Smetsers |
| Abstract | The problem of learning a minimal consistent model from a set of labeled sequences of symbols is addressed from a satisfiability modulo theories perspective. We present two encodings for deterministic finite automata and extend one of these for Moore and Mealy machines. Our experimental results show that these encodings improve upon the state-of-the-art, and are useful in practice for learning small models. |
| Tasks | |
| Published | 2017-05-30 |
| URL | http://arxiv.org/abs/1705.10639v1 |
| http://arxiv.org/pdf/1705.10639v1.pdf | |
| PWC | https://paperswithcode.com/paper/grammatical-inference-as-a-satisfiability |
| Repo | |
| Framework | |
General Phase Regularized Reconstruction using Phase Cycling
| Title | General Phase Regularized Reconstruction using Phase Cycling |
| Authors | Frank Ong, Joseph Cheng, Michael Lustig |
| Abstract | Purpose: To develop a general phase regularized image reconstruction method, with applications to partial Fourier imaging, water-fat imaging and flow imaging. Theory and Methods: The problem of enforcing phase constraints in reconstruction was studied under a regularized inverse problem framework. A general phase regularized reconstruction algorithm was proposed to enable various joint reconstruction of partial Fourier imaging, water-fat imaging and flow imaging, along with parallel imaging (PI) and compressed sensing (CS). Since phase regularized reconstruction is inherently non-convex and sensitive to phase wraps in the initial solution, a reconstruction technique, named phase cycling, was proposed to render the overall algorithm invariant to phase wraps. The proposed method was applied to retrospectively under-sampled in vivo datasets and compared with state of the art reconstruction methods. Results: Phase cycling reconstructions showed reduction of artifacts compared to reconstructions with- out phase cycling and achieved similar performances as state of the art results in partial Fourier, water-fat and divergence-free regularized flow reconstruction. Joint reconstruction of partial Fourier + water-fat imaging + PI + CS, and partial Fourier + divergence-free regularized flow imaging + PI + CS were demonstrated. Conclusion: The proposed phase cycling reconstruction provides an alternative way to perform phase regularized reconstruction, without the need to perform phase unwrapping. It is robust to the choice of initial solutions and encourages the joint reconstruction of phase imaging applications. |
| Tasks | Image Reconstruction |
| Published | 2017-09-15 |
| URL | http://arxiv.org/abs/1709.05374v1 |
| http://arxiv.org/pdf/1709.05374v1.pdf | |
| PWC | https://paperswithcode.com/paper/general-phase-regularized-reconstruction |
| Repo | |
| Framework | |
Semi-Supervised Hierarchical Semantic Object Parsing
| Title | Semi-Supervised Hierarchical Semantic Object Parsing |
| Authors | Jalal Mirakhorli, Hamidreza Amindavar |
| Abstract | Models based on Convolutional Neural Networks (CNNs) have been proven very successful for semantic segmentation and object parsing that yield hierarchies of features. Our key insight is to build convolutional networks that take input of arbitrary size and produce object parsing output with efficient inference and learning. In this work, we focus on the task of instance segmentation and parsing which recognizes and localizes objects down to a pixel level base on deep CNN. Therefore, unlike some related work, a pixel cannot belong to multiple instances and parsing. Our model is based on a deep neural network trained for object masking that supervised with input image and follow incorporates a Conditional Random Field (CRF) with end-to-end trainable piecewise order potentials based on object parsing outputs. In each CRF unit we designed terms to capture the short range and long range dependencies from various neighbors. The accurate instance-level segmentation that our network produce is reflected by the considerable improvements obtained over previous work at high APr thresholds. We demonstrate the effectiveness of our model with extensive experiments on challenging dataset subset of PASCAL VOC2012. |
| Tasks | Instance Segmentation, Semantic Segmentation |
| Published | 2017-09-23 |
| URL | http://arxiv.org/abs/1709.08019v3 |
| http://arxiv.org/pdf/1709.08019v3.pdf | |
| PWC | https://paperswithcode.com/paper/semi-supervised-hierarchical-semantic-object |
| Repo | |
| Framework | |
Restricting Greed in Training of Generative Adversarial Network
| Title | Restricting Greed in Training of Generative Adversarial Network |
| Authors | Haoxuan You, Zhicheng Jiao, Haojun Xu, Jie Li, Ying Wang, Xinbo Gao |
| Abstract | Generative adversarial network (GAN) has gotten wide re-search interest in the field of deep learning. Variations of GAN have achieved competitive results on specific tasks. However, the stability of training and diversity of generated instances are still worth studying further. Training of GAN can be thought of as a greedy procedure, in which the generative net tries to make the locally optimal choice (minimizing loss function of discriminator) in each iteration. Unfortunately, this often makes generated data resemble only a few modes of real data and rotate between modes. To alleviate these problems, we propose a novel training strategy to restrict greed in training of GAN. With help of our method, the generated samples can cover more instance modes with more stable training process. Evaluating our method on several representative datasets, we demonstrate superiority of improved training strategy on typical GAN models with different distance metrics. |
| Tasks | |
| Published | 2017-11-28 |
| URL | http://arxiv.org/abs/1711.10152v2 |
| http://arxiv.org/pdf/1711.10152v2.pdf | |
| PWC | https://paperswithcode.com/paper/restricting-greed-in-training-of-generative |
| Repo | |
| Framework | |
Point of Interest Recommendation Methods in Location Based Social Networks: Traveling to a new geographical region
| Title | Point of Interest Recommendation Methods in Location Based Social Networks: Traveling to a new geographical region |
| Authors | Billy Zimba, Samson Chibuta, David Chisanga, Fredah Banda, Jackson Phiri |
| Abstract | Recommender systems in location based social networks mainly take advantage of social and geographical influence in making personalized Points-of-interest (POI) recommendations. The social influence is obtained from social network friends or similar users based on matching visit history whilst the geographical influence is obtained from the geographical footprints users’ leave when they check-in at different POIs. However, this approach may fall short when a user moves to a new region where they have little or no activity history. We propose a location aware POI recommendation system that models user preferences mainly based on; user reviews and categories of POIs. We evaluate our algorithm on the Yelp dataset and the experimental results show that our algorithm achieves a better accuracy. |
| Tasks | Recommendation Systems |
| Published | 2017-11-26 |
| URL | https://arxiv.org/abs/1711.09471v4 |
| https://arxiv.org/pdf/1711.09471v4.pdf | |
| PWC | https://paperswithcode.com/paper/point-of-interest-recommendation-methods-in |
| Repo | |
| Framework | |
Learning from Ambiguously Labeled Face Images
| Title | Learning from Ambiguously Labeled Face Images |
| Authors | Ching-Hui Chen, Vishal M. Patel, Rama Chellappa |
| Abstract | Learning a classifier from ambiguously labeled face images is challenging since training images are not always explicitly-labeled. For instance, face images of two persons in a news photo are not explicitly labeled by their names in the caption. We propose a Matrix Completion for Ambiguity Resolution (MCar) method for predicting the actual labels from ambiguously labeled images. This step is followed by learning a standard supervised classifier from the disambiguated labels to classify new images. To prevent the majority labels from dominating the result of MCar, we generalize MCar to a weighted MCar (WMCar) that handles label imbalance. Since WMCar outputs a soft labeling vector of reduced ambiguity for each instance, we can iteratively refine it by feeding it as the input to WMCar. Nevertheless, such an iterative implementation can be affected by the noisy soft labeling vectors, and thus the performance may degrade. Our proposed Iterative Candidate Elimination (ICE) procedure makes the iterative ambiguity resolution possible by gradually eliminating a portion of least likely candidates in ambiguously labeled face. We further extend MCar to incorporate the labeling constraints between instances when such prior knowledge is available. Compared to existing methods, our approach demonstrates improvement on several ambiguously labeled datasets. |
| Tasks | Matrix Completion |
| Published | 2017-02-15 |
| URL | http://arxiv.org/abs/1702.04455v2 |
| http://arxiv.org/pdf/1702.04455v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-from-ambiguously-labeled-face-images |
| Repo | |
| Framework | |
Sample Efficient Policy Search for Optimal Stopping Domains
| Title | Sample Efficient Policy Search for Optimal Stopping Domains |
| Authors | Karan Goel, Christoph Dann, Emma Brunskill |
| Abstract | Optimal stopping problems consider the question of deciding when to stop an observation-generating process in order to maximize a return. We examine the problem of simultaneously learning and planning in such domains, when data is collected directly from the environment. We propose GFSE, a simple and flexible model-free policy search method that reuses data for sample efficiency by leveraging problem structure. We bound the sample complexity of our approach to guarantee uniform convergence of policy value estimates, tightening existing PAC bounds to achieve logarithmic dependence on horizon length for our setting. We also examine the benefit of our method against prevalent model-based and model-free approaches on 3 domains taken from diverse fields. |
| Tasks | |
| Published | 2017-02-21 |
| URL | http://arxiv.org/abs/1702.06238v2 |
| http://arxiv.org/pdf/1702.06238v2.pdf | |
| PWC | https://paperswithcode.com/paper/sample-efficient-policy-search-for-optimal |
| Repo | |
| Framework | |
Ensembles of phalanxes across assessment metrics for robust ranking of homologous proteins
| Title | Ensembles of phalanxes across assessment metrics for robust ranking of homologous proteins |
| Authors | Jabed H Tomal, William J Welch, Ruben H Zamar |
| Abstract | Two proteins are homologous if they have a common evolutionary origin, and the binary classification problem is to identify proteins in a candidate set that are homologous to a particular native protein. The feature (explanatory) variables available for classification are various measures of similarity of proteins. There are multiple classification problems of this type for different native proteins and their respective candidate sets. Homologous proteins are rare in a single candidate set, giving a highly unbalanced two-class problem. The goal is to rank proteins in a candidate set according to the probability of being homologous to the set’s native protein. An ideal classifier will place all the homologous proteins at the head of such a list. Our approach uses an ensemble of models in a classifier and an ensemble of assessment metrics. For a given metric a classifier combines models, each based on a subset of the available feature variables which we call phalanxes. The proposed ensemble of phalanxes identifies strong and diverse subsets of feature variables. A second phase of ensembling aggregates classifiers based on diverse evaluation metrics. The overall result is called an ensemble of phalanxes and metrics. It provide robustness against both close and distant homologues. |
| Tasks | |
| Published | 2017-06-21 |
| URL | https://arxiv.org/abs/1706.06971v2 |
| https://arxiv.org/pdf/1706.06971v2.pdf | |
| PWC | https://paperswithcode.com/paper/ensembles-of-models-and-metrics-for-robust |
| Repo | |
| Framework | |
Deep Collaborative Learning for Visual Recognition
| Title | Deep Collaborative Learning for Visual Recognition |
| Authors | Yan Wang, Lingxi Xie, Ya Zhang, Wenjun Zhang, Alan Yuille |
| Abstract | Deep neural networks are playing an important role in state-of-the-art visual recognition. To represent high-level visual concepts, modern networks are equipped with large convolutional layers, which use a large number of filters and contribute significantly to model complexity. For example, more than half of the weights of AlexNet are stored in the first fully-connected layer (4,096 filters). We formulate the function of a convolutional layer as learning a large visual vocabulary, and propose an alternative way, namely Deep Collaborative Learning (DCL), to reduce the computational complexity. We replace a convolutional layer with a two-stage DCL module, in which we first construct a couple of smaller convolutional layers individually, and then fuse them at each spatial position to consider feature co-occurrence. In mathematics, DCL can be explained as an efficient way of learning compositional visual concepts, in which the vocabulary size increases exponentially while the model complexity only increases linearly. We evaluate DCL on a wide range of visual recognition tasks, including a series of multi-digit number classification datasets, and some generic image classification datasets such as SVHN, CIFAR and ILSVRC2012. We apply DCL to several state-of-the-art network structures, improving the recognition accuracy meanwhile reducing the number of parameters (16.82% fewer in AlexNet). |
| Tasks | Image Classification |
| Published | 2017-03-03 |
| URL | http://arxiv.org/abs/1703.01229v1 |
| http://arxiv.org/pdf/1703.01229v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-collaborative-learning-for-visual |
| Repo | |
| Framework | |
The Theory is Predictive, but is it Complete? An Application to Human Perception of Randomness
| Title | The Theory is Predictive, but is it Complete? An Application to Human Perception of Randomness |
| Authors | Jon Kleinberg, Annie Liang, Sendhil Mullainathan |
| Abstract | When we test a theory using data, it is common to focus on correctness: do the predictions of the theory match what we see in the data? But we also care about completeness: how much of the predictable variation in the data is captured by the theory? This question is difficult to answer, because in general we do not know how much “predictable variation” there is in the problem. In this paper, we consider approaches motivated by machine learning algorithms as a means of constructing a benchmark for the best attainable level of prediction. We illustrate our methods on the task of predicting human-generated random sequences. Relative to an atheoretical machine learning algorithm benchmark, we find that existing behavioral models explain roughly 15 percent of the predictable variation in this problem. This fraction is robust across several variations on the problem. We also consider a version of this approach for analyzing field data from domains in which human perception and generation of randomness has been used as a conceptual framework; these include sequential decision-making and repeated zero-sum games. In these domains, our framework for testing the completeness of theories provides a way of assessing their effectiveness over different contexts; we find that despite some differences, the existing theories are fairly stable across our field domains in their performance relative to the benchmark. Overall, our results indicate that (i) there is a significant amount of structure in this problem that existing models have yet to capture and (ii) there are rich domains in which machine learning may provide a viable approach to testing completeness. |
| Tasks | Decision Making |
| Published | 2017-06-21 |
| URL | http://arxiv.org/abs/1706.06974v1 |
| http://arxiv.org/pdf/1706.06974v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-theory-is-predictive-but-is-it-complete |
| Repo | |
| Framework | |
In folly ripe. In reason rotten. Putting machine theology to rest
| Title | In folly ripe. In reason rotten. Putting machine theology to rest |
| Authors | Mihai Nadin |
| Abstract | Computation has changed the world more than any previous expressions of knowledge. In its particular algorithmic embodiment, it offers a perspective, within which the digital computer (one of many possible) exercises a role reminiscent of theology. Since it is closed to meaning, algorithmic digital computation can at most mimic the creative aspects of life. AI, in the perspective of time, proved to be less an acronym for artificial intelligence and more of automating tasks associated with intelligence. The entire development led to the hypostatized role of the machine: outputting nothing else but reality, including that of the humanity that made the machine happen. The convergence machine called deep learning is only the latest form through which the deterministic theology of the machine claims more than what extremely effective data processing actually is. A new understanding of complexity, as well as the need to distinguish between the reactive nature of the artificial and the anticipatory nature of the living are suggested as practical responses to the challenges posed by machine theology. |
| Tasks | |
| Published | 2017-12-03 |
| URL | http://arxiv.org/abs/1712.04306v1 |
| http://arxiv.org/pdf/1712.04306v1.pdf | |
| PWC | https://paperswithcode.com/paper/in-folly-ripe-in-reason-rotten-putting |
| Repo | |
| Framework | |
Discovery Radiomics with CLEAR-DR: Interpretable Computer Aided Diagnosis of Diabetic Retinopathy
| Title | Discovery Radiomics with CLEAR-DR: Interpretable Computer Aided Diagnosis of Diabetic Retinopathy |
| Authors | Devinder Kumar, Graham W. Taylor, Alexander Wong |
| Abstract | Objective: Radiomics-driven Computer Aided Diagnosis (CAD) has shown considerable promise in recent years as a potential tool for improving clinical decision support in medical oncology, particularly those based around the concept of Discovery Radiomics, where radiomic sequencers are discovered through the analysis of medical imaging data. One of the main limitations with current CAD approaches is that it is very difficult to gain insight or rationale as to how decisions are made, thus limiting their utility to clinicians. Methods: In this study, we propose CLEAR-DR, a novel interpretable CAD system based on the notion of CLass-Enhanced Attentive Response Discovery Radiomics for the purpose of clinical decision support for diabetic retinopathy. Results: In addition to disease grading via the discovered deep radiomic sequencer, the CLEAR-DR system also produces a visual interpretation of the decision-making process to provide better insight and understanding into the decision-making process of the system. Conclusion: We demonstrate the effectiveness and utility of the proposed CLEAR-DR system of enhancing the interpretability of diagnostic grading results for the application of diabetic retinopathy grading. Significance: CLEAR-DR can act as a potential powerful tool to address the uninterpretability issue of current CAD systems, thus improving their utility to clinicians. |
| Tasks | Decision Making |
| Published | 2017-10-29 |
| URL | http://arxiv.org/abs/1710.10675v1 |
| http://arxiv.org/pdf/1710.10675v1.pdf | |
| PWC | https://paperswithcode.com/paper/discovery-radiomics-with-clear-dr |
| Repo | |
| Framework | |
SLAM based Quasi Dense Reconstruction For Minimally Invasive Surgery Scenes
| Title | SLAM based Quasi Dense Reconstruction For Minimally Invasive Surgery Scenes |
| Authors | Nader Mahmoud, Alexandre Hostettler, Toby Collins, Luc Soler, Christophe Doignon, J. M. M. Montiel |
| Abstract | Recovering surgical scene structure in laparoscope surgery is crucial step for surgical guidance and augmented reality applications. In this paper, a quasi dense reconstruction algorithm of surgical scene is proposed. This is based on a state-of-the-art SLAM system, and is exploiting the initial exploration phase that is typically performed by the surgeon at the beginning of the surgery. We show how to convert the sparse SLAM map to a quasi dense scene reconstruction, using pairs of keyframe images and correlation-based featureless patch matching. We have validated the approach with a live porcine experiment using Computed Tomography as ground truth, yielding a Root Mean Squared Error of 4.9mm. |
| Tasks | |
| Published | 2017-05-25 |
| URL | http://arxiv.org/abs/1705.09107v1 |
| http://arxiv.org/pdf/1705.09107v1.pdf | |
| PWC | https://paperswithcode.com/paper/slam-based-quasi-dense-reconstruction-for |
| Repo | |
| Framework | |
