Paper Group ANR 244
Revisiting revisits in trajectory recommendation. Gaussian-Dirichlet Posterior Dominance in Sequential Learning. Visual aesthetic analysis using deep neural network: model and techniques to increase accuracy without transfer learning. Adaptive Relaxed ADMM: Convergence Theory and Practical Implementation. Artificial Intelligence and Economic Theori …
Revisiting revisits in trajectory recommendation
| Title | Revisiting revisits in trajectory recommendation |
| Authors | Aditya Krishna Menon, Dawei Chen, Lexing Xie, Cheng Soon Ong |
| Abstract | Trajectory recommendation is the problem of recommending a sequence of places in a city for a tourist to visit. It is strongly desirable for the recommended sequence to avoid loops, as tourists typically would not wish to revisit the same location. Given some learned model that scores sequences, how can we then find the highest-scoring sequence that is loop-free? This paper studies this problem, with three contributions. First, we detail three distinct approaches to the problem – graph-based heuristics, integer linear programming, and list extensions of the Viterbi algorithm – and qualitatively summarise their strengths and weaknesses. Second, we explicate how two ostensibly different approaches to the list Viterbi algorithm are in fact fundamentally identical. Third, we conduct experiments on real-world trajectory recommendation datasets to identify the tradeoffs imposed by each of the three approaches. Overall, our results indicate that a greedy graph-based heuristic offer excellent performance and runtime, leading us to recommend its use for removing loops at prediction time. |
| Tasks | |
| Published | 2017-08-17 |
| URL | http://arxiv.org/abs/1708.05165v1 |
| http://arxiv.org/pdf/1708.05165v1.pdf | |
| PWC | https://paperswithcode.com/paper/revisiting-revisits-in-trajectory |
| Repo | |
| Framework | |
Gaussian-Dirichlet Posterior Dominance in Sequential Learning
| Title | Gaussian-Dirichlet Posterior Dominance in Sequential Learning |
| Authors | Ian Osband, Benjamin Van Roy |
| Abstract | We consider the problem of sequential learning from categorical observations bounded in [0,1]. We establish an ordering between the Dirichlet posterior over categorical outcomes and a Gaussian posterior under observations with N(0,1) noise. We establish that, conditioned upon identical data with at least two observations, the posterior mean of the categorical distribution will always second-order stochastically dominate the posterior mean of the Gaussian distribution. These results provide a useful tool for the analysis of sequential learning under categorical outcomes. |
| Tasks | |
| Published | 2017-02-14 |
| URL | http://arxiv.org/abs/1702.04126v3 |
| http://arxiv.org/pdf/1702.04126v3.pdf | |
| PWC | https://paperswithcode.com/paper/gaussian-dirichlet-posterior-dominance-in |
| Repo | |
| Framework | |
Visual aesthetic analysis using deep neural network: model and techniques to increase accuracy without transfer learning
| Title | Visual aesthetic analysis using deep neural network: model and techniques to increase accuracy without transfer learning |
| Authors | Muktabh Mayank Srivastava, Sonaal Kant |
| Abstract | We train a deep Convolutional Neural Network (CNN) from scratch for visual aesthetic analysis in images and discuss techniques we adopt to improve the accuracy. We avoid the prevalent best transfer learning approaches of using pretrained weights to perform the task and train a model from scratch to get accuracy of 78.7% on AVA2 Dataset close to the best models available (85.6%). We further show that accuracy increases to 81.48% on increasing the training set by incremental 10 percentile of entire AVA dataset showing our algorithm gets better with more data. |
| Tasks | Transfer Learning |
| Published | 2017-12-09 |
| URL | http://arxiv.org/abs/1712.03382v4 |
| http://arxiv.org/pdf/1712.03382v4.pdf | |
| PWC | https://paperswithcode.com/paper/visual-aesthetic-analysis-using-deep-neural |
| Repo | |
| Framework | |
Adaptive Relaxed ADMM: Convergence Theory and Practical Implementation
| Title | Adaptive Relaxed ADMM: Convergence Theory and Practical Implementation |
| Authors | Zheng Xu, Mario A. T. Figueiredo, Xiaoming Yuan, Christoph Studer, Tom Goldstein |
| Abstract | Many modern computer vision and machine learning applications rely on solving difficult optimization problems that involve non-differentiable objective functions and constraints. The alternating direction method of multipliers (ADMM) is a widely used approach to solve such problems. Relaxed ADMM is a generalization of ADMM that often achieves better performance, but its efficiency depends strongly on algorithm parameters that must be chosen by an expert user. We propose an adaptive method that automatically tunes the key algorithm parameters to achieve optimal performance without user oversight. Inspired by recent work on adaptivity, the proposed adaptive relaxed ADMM (ARADMM) is derived by assuming a Barzilai-Borwein style linear gradient. A detailed convergence analysis of ARADMM is provided, and numerical results on several applications demonstrate fast practical convergence. |
| Tasks | |
| Published | 2017-04-10 |
| URL | http://arxiv.org/abs/1704.02712v1 |
| http://arxiv.org/pdf/1704.02712v1.pdf | |
| PWC | https://paperswithcode.com/paper/adaptive-relaxed-admm-convergence-theory-and |
| Repo | |
| Framework | |
Artificial Intelligence and Economic Theories
| Title | Artificial Intelligence and Economic Theories |
| Authors | Tshilidzi Marwala, Evan Hurwitz |
| Abstract | The advent of artificial intelligence has changed many disciplines such as engineering, social science and economics. Artificial intelligence is a computational technique which is inspired by natural intelligence such as the swarming of birds, the working of the brain and the pathfinding of the ants. These techniques have impact on economic theories. This book studies the impact of artificial intelligence on economic theories, a subject that has not been extensively studied. The theories that are considered are: demand and supply, asymmetrical information, pricing, rational choice, rational expectation, game theory, efficient market hypotheses, mechanism design, prospect, bounded rationality, portfolio theory, rational counterfactual and causality. The benefit of this book is that it evaluates existing theories of economics and update them based on the developments in artificial intelligence field. |
| Tasks | |
| Published | 2017-03-20 |
| URL | http://arxiv.org/abs/1703.06597v1 |
| http://arxiv.org/pdf/1703.06597v1.pdf | |
| PWC | https://paperswithcode.com/paper/artificial-intelligence-and-economic-theories |
| Repo | |
| Framework | |
Advanced Steel Microstructural Classification by Deep Learning Methods
| Title | Advanced Steel Microstructural Classification by Deep Learning Methods |
| Authors | Seyed Majid Azimi, Dominik Britz, Michael Engstler, Mario Fritz, Frank Mücklich |
| Abstract | The inner structure of a material is called microstructure. It stores the genesis of a material and determines all its physical and chemical properties. While microstructural characterization is widely spread and well known, the microstructural classification is mostly done manually by human experts, which gives rise to uncertainties due to subjectivity. Since the microstructure could be a combination of different phases or constituents with complex substructures its automatic classification is very challenging and only a few prior studies exist. Prior works focused on designed and engineered features by experts and classified microstructures separately from the feature extraction step. Recently, Deep Learning methods have shown strong performance in vision applications by learning the features from data together with the classification step. In this work, we propose a Deep Learning method for microstructural classification in the examples of certain microstructural constituents of low carbon steel. This novel method employs pixel-wise segmentation via Fully Convolutional Neural Networks (FCNN) accompanied by a max-voting scheme. Our system achieves 93.94% classification accuracy, drastically outperforming the state-of-the-art method of 48.89% accuracy. Beyond the strong performance of our method, this line of research offers a more robust and first of all objective way for the difficult task of steel quality appreciation. |
| Tasks | |
| Published | 2017-06-20 |
| URL | http://arxiv.org/abs/1706.06480v2 |
| http://arxiv.org/pdf/1706.06480v2.pdf | |
| PWC | https://paperswithcode.com/paper/advanced-steel-microstructural-classification |
| Repo | |
| Framework | |
FuCoLoT – A Fully-Correlational Long-Term Tracker
| Title | FuCoLoT – A Fully-Correlational Long-Term Tracker |
| Authors | Alan Lukežič, Luka Čehovin Zajc, Tomáš Vojíř, Jiří Matas, Matej Kristan |
| Abstract | We propose FuCoLoT – a Fully Correlational Long-term Tracker. It exploits the novel DCF constrained filter learning method to design a detector that is able to re-detect the target in the whole image efficiently. FuCoLoT maintains several correlation filters trained on different time scales that act as the detector components. A novel mechanism based on the correlation response is used for tracking failure estimation. FuCoLoT achieves state-of-the-art results on standard short-term benchmarks and it outperforms the current best-performing tracker on the long-term UAV20L benchmark by over 19%. It has an order of magnitude smaller memory footprint than its best-performing competitors and runs at 15fps in a single CPU thread. |
| Tasks | |
| Published | 2017-11-27 |
| URL | http://arxiv.org/abs/1711.09594v2 |
| http://arxiv.org/pdf/1711.09594v2.pdf | |
| PWC | https://paperswithcode.com/paper/fucolot-a-fully-correlational-long-term |
| Repo | |
| Framework | |
Video Denoising and Enhancement via Dynamic Video Layering
| Title | Video Denoising and Enhancement via Dynamic Video Layering |
| Authors | Han Guo, Namrata Vaswani |
| Abstract | Video denoising refers to the problem of removing “noise” from a video sequence. Here the term “noise” is used in a broad sense to refer to any corruption or outlier or interference that is not the quantity of interest. In this work, we develop a novel approach to video denoising that is based on the idea that many noisy or corrupted videos can be split into three parts - the “low-rank layer”, the “sparse layer”, and a small residual (which is small and bounded). We show, using extensive experiments, that our denoising approach outperforms the state-of-the-art denoising algorithms. |
| Tasks | Denoising, Video Denoising |
| Published | 2017-10-05 |
| URL | http://arxiv.org/abs/1710.02213v1 |
| http://arxiv.org/pdf/1710.02213v1.pdf | |
| PWC | https://paperswithcode.com/paper/video-denoising-and-enhancement-via-dynamic |
| Repo | |
| Framework | |
Recent Advances in Transfer Learning for Cross-Dataset Visual Recognition: A Problem-Oriented Perspective
| Title | Recent Advances in Transfer Learning for Cross-Dataset Visual Recognition: A Problem-Oriented Perspective |
| Authors | Jing Zhang, Wanqing Li, Philip Ogunbona, Dong Xu |
| Abstract | This paper takes a problem-oriented perspective and presents a comprehensive review of transfer learning methods, both shallow and deep, for cross-dataset visual recognition. Specifically, it categorises the cross-dataset recognition into seventeen problems based on a set of carefully chosen data and label attributes. Such a problem-oriented taxonomy has allowed us to examine how different transfer learning approaches tackle each problem and how well each problem has been researched to date. The comprehensive problem-oriented review of the advances in transfer learning with respect to the problem has not only revealed the challenges in transfer learning for visual recognition, but also the problems (e.g. eight of the seventeen problems) that have been scarcely studied. This survey not only presents an up-to-date technical review for researchers, but also a systematic approach and a reference for a machine learning practitioner to categorise a real problem and to look up for a possible solution accordingly. |
| Tasks | Transfer Learning |
| Published | 2017-05-11 |
| URL | https://arxiv.org/abs/1705.04396v3 |
| https://arxiv.org/pdf/1705.04396v3.pdf | |
| PWC | https://paperswithcode.com/paper/transfer-learning-for-cross-dataset |
| Repo | |
| Framework | |
Scene-Specific Pedestrian Detection Based on Parallel Vision
| Title | Scene-Specific Pedestrian Detection Based on Parallel Vision |
| Authors | Wenwen Zhang, Kunfeng Wang, Hua Qu, Jihong Zhao, Fei-Yue Wang |
| Abstract | As a special type of object detection, pedestrian detection in generic scenes has made a significant progress trained with large amounts of labeled training data manually. While the models trained with generic dataset work bad when they are directly used in specific scenes. With special viewpoints, flow light and backgrounds, datasets from specific scenes are much different from the datasets from generic scenes. In order to make the generic scene pedestrian detectors work well in specific scenes, the labeled data from specific scenes are needed to adapt the models to the specific scenes. While labeling the data manually spends much time and money, especially for specific scenes, each time with a new specific scene, large amounts of images must be labeled. What’s more, the labeling information is not so accurate in the pixels manually and different people make different labeling information. In this paper, we propose an ACP-based method, with augmented reality’s help, we build the virtual world of specific scenes, and make people walking in the virtual scenes where it is possible for them to appear to solve this problem of lacking labeled data and the results show that data from virtual world is helpful to adapt generic pedestrian detectors to specific scenes. |
| Tasks | Object Detection, Pedestrian Detection |
| Published | 2017-12-23 |
| URL | http://arxiv.org/abs/1712.08745v1 |
| http://arxiv.org/pdf/1712.08745v1.pdf | |
| PWC | https://paperswithcode.com/paper/scene-specific-pedestrian-detection-based-on |
| Repo | |
| Framework | |
Sea Level Anomaly Prediction using Recurrent Neural Networks
| Title | Sea Level Anomaly Prediction using Recurrent Neural Networks |
| Authors | Anne Braakmann-Folgmann, Ribana Roscher, Susanne Wenzel, Bernd Uebbing, Jürgen Kusche |
| Abstract | Sea level change, one of the most dire impacts of anthropogenic global warming, will affect a large amount of the world’s population. However, sea level change is not uniform in time and space, and the skill of conventional prediction methods is limited due to the ocean’s internal variabi-lity on timescales from weeks to decades. Here we study the potential of neural network methods which have been used successfully in other applications, but rarely been applied for this task. We develop a combination of a convolutional neural network (CNN) and a recurrent neural network (RNN) to ana-lyse both the spatial and the temporal evolution of sea level and to suggest an independent, accurate method to predict interannual sea level anomalies (SLA). We test our method for the northern and equatorial Pacific Ocean, using gridded altimeter-derived SLA data. We show that the used network designs outperform a simple regression and that adding a CNN improves the skill significantly. The predictions are stable over several years. |
| Tasks | |
| Published | 2017-10-19 |
| URL | http://arxiv.org/abs/1710.07099v1 |
| http://arxiv.org/pdf/1710.07099v1.pdf | |
| PWC | https://paperswithcode.com/paper/sea-level-anomaly-prediction-using-recurrent |
| Repo | |
| Framework | |
Identifying Most Walkable Direction for Navigation in an Outdoor Environment
| Title | Identifying Most Walkable Direction for Navigation in an Outdoor Environment |
| Authors | Sachin Mehta, Hannaneh Hajishirzi, Linda Shapiro |
| Abstract | We present an approach for identifying the most walkable direction for navigation using a hand-held camera. Our approach extracts semantically rich contextual information from the scene using a custom encoder-decoder architecture for semantic segmentation and models the spatial and temporal behavior of objects in the scene using a spatio-temporal graph. The system learns to minimize a cost function over the spatial and temporal object attributes to identify the most walkable direction. We construct a new annotated navigation dataset collected using a hand-held mobile camera in an unconstrained outdoor environment, which includes challenging settings such as highly dynamic scenes, occlusion between objects, and distortions. Our system achieves an accuracy of 84% on predicting a safe direction. We also show that our custom segmentation network is both fast and accurate, achieving mIOU (mean intersection over union) scores of 81 and 44.7 on the PASCAL VOC and the PASCAL Context datasets, respectively, while running at about 21 frames per second. |
| Tasks | Semantic Segmentation |
| Published | 2017-11-21 |
| URL | http://arxiv.org/abs/1711.08040v2 |
| http://arxiv.org/pdf/1711.08040v2.pdf | |
| PWC | https://paperswithcode.com/paper/identifying-most-walkable-direction-for |
| Repo | |
| Framework | |
Looking Beyond Appearances: Synthetic Training Data for Deep CNNs in Re-identification
| Title | Looking Beyond Appearances: Synthetic Training Data for Deep CNNs in Re-identification |
| Authors | Igor Barros Barbosa, Marco Cristani, Barbara Caputo, Aleksander Rognhaugen, Theoharis Theoharis |
| Abstract | Re-identification is generally carried out by encoding the appearance of a subject in terms of outfit, suggesting scenarios where people do not change their attire. In this paper we overcome this restriction, by proposing a framework based on a deep convolutional neural network, SOMAnet, that additionally models other discriminative aspects, namely, structural attributes of the human figure (e.g. height, obesity, gender). Our method is unique in many respects. First, SOMAnet is based on the Inception architecture, departing from the usual siamese framework. This spares expensive data preparation (pairing images across cameras) and allows the understanding of what the network learned. Second, and most notably, the training data consists of a synthetic 100K instance dataset, SOMAset, created by photorealistic human body generation software. Synthetic data represents a good compromise between realistic imagery, usually not required in re-identification since surveillance cameras capture low-resolution silhouettes, and complete control of the samples, which is useful in order to customize the data w.r.t. the surveillance scenario at-hand, e.g. ethnicity. SOMAnet, trained on SOMAset and fine-tuned on recent re-identification benchmarks, outperforms all competitors, matching subjects even with different apparel. The combination of synthetic data with Inception architectures opens up new research avenues in re-identification. |
| Tasks | |
| Published | 2017-01-11 |
| URL | http://arxiv.org/abs/1701.03153v2 |
| http://arxiv.org/pdf/1701.03153v2.pdf | |
| PWC | https://paperswithcode.com/paper/looking-beyond-appearances-synthetic-training |
| Repo | |
| Framework | |
When is a Convolutional Filter Easy To Learn?
| Title | When is a Convolutional Filter Easy To Learn? |
| Authors | Simon S. Du, Jason D. Lee, Yuandong Tian |
| Abstract | We analyze the convergence of (stochastic) gradient descent algorithm for learning a convolutional filter with Rectified Linear Unit (ReLU) activation function. Our analysis does not rely on any specific form of the input distribution and our proofs only use the definition of ReLU, in contrast with previous works that are restricted to standard Gaussian input. We show that (stochastic) gradient descent with random initialization can learn the convolutional filter in polynomial time and the convergence rate depends on the smoothness of the input distribution and the closeness of patches. To the best of our knowledge, this is the first recovery guarantee of gradient-based algorithms for convolutional filter on non-Gaussian input distributions. Our theory also justifies the two-stage learning rate strategy in deep neural networks. While our focus is theoretical, we also present experiments that illustrate our theoretical findings. |
| Tasks | |
| Published | 2017-09-18 |
| URL | http://arxiv.org/abs/1709.06129v2 |
| http://arxiv.org/pdf/1709.06129v2.pdf | |
| PWC | https://paperswithcode.com/paper/when-is-a-convolutional-filter-easy-to-learn |
| Repo | |
| Framework | |
Perceptually Optimized Image Rendering
| Title | Perceptually Optimized Image Rendering |
| Authors | Valero Laparra, Alex Berardino, Johannes Ballé, Eero P. Simoncelli |
| Abstract | We develop a framework for rendering photographic images, taking into account display limitations, so as to optimize perceptual similarity between the rendered image and the original scene. We formulate this as a constrained optimization problem, in which we minimize a measure of perceptual dissimilarity, the Normalized Laplacian Pyramid Distance (NLPD), which mimics the early stage transformations of the human visual system. When rendering images acquired with higher dynamic range than that of the display, we find that the optimized solution boosts the contrast of low-contrast features without introducing significant artifacts, yielding results of comparable visual quality to current state-of-the art methods with no manual intervention or parameter settings. We also examine a variety of other display constraints, including limitations on minimum luminance (black point), mean luminance (as a proxy for energy consumption), and quantized luminance levels (halftoning). Finally, we show that the method may be used to enhance details and contrast of images degraded by optical scattering (e.g. fog). |
| Tasks | |
| Published | 2017-01-23 |
| URL | http://arxiv.org/abs/1701.06641v1 |
| http://arxiv.org/pdf/1701.06641v1.pdf | |
| PWC | https://paperswithcode.com/paper/perceptually-optimized-image-rendering |
| Repo | |
| Framework | |
