Paper Group ANR 7
Reducing over-clustering via the powered Chinese restaurant process. Deep Learning based Pedestrian Detection at Distance in Smart Cities. Overabundant Information and Learning Traps. An FPGA-Accelerated Design for Deep Learning Pedestrian Detection in Self-Driving Vehicles. On the Algebra in Boole’s Laws of Thought. Blazingly Fast Video Object Seg …
Reducing over-clustering via the powered Chinese restaurant process
Title | Reducing over-clustering via the powered Chinese restaurant process |
Authors | Jun Lu, Meng Li, David Dunson |
Abstract | Dirichlet process mixture (DPM) models tend to produce many small clusters regardless of whether they are needed to accurately characterize the data - this is particularly true for large data sets. However, interpretability, parsimony, data storage and communication costs all are hampered by having overly many clusters. We propose a powered Chinese restaurant process to limit this kind of problem and penalize over clustering. The method is illustrated using some simulation examples and data with large and small sample size including MNIST and the Old Faithful Geyser data. |
Tasks | |
Published | 2018-02-15 |
URL | http://arxiv.org/abs/1802.05392v1 |
http://arxiv.org/pdf/1802.05392v1.pdf | |
PWC | https://paperswithcode.com/paper/reducing-over-clustering-via-the-powered |
Repo | |
Framework | |
Deep Learning based Pedestrian Detection at Distance in Smart Cities
Title | Deep Learning based Pedestrian Detection at Distance in Smart Cities |
Authors | Ranjith K Dinakaran, Philip Easom, Ahmed Bouridane, Li Zhang, Richard Jiang, Fozia Mehboob, Abdul Rauf |
Abstract | Generative adversarial networks (GANs) have been promising for many computer vision problems due to their powerful capabilities to enhance the data for training and test. In this paper, we leveraged GANs and proposed a new architecture with a cascaded Single Shot Detector (SSD) for pedestrian detection at distance, which is yet a challenge due to the varied sizes of pedestrians in videos at distance. To overcome the low-resolution issues in pedestrian detection at distance, DCGAN is employed to improve the resolution first to reconstruct more discriminative features for a SSD to detect objects in images or videos. A crucial advantage of our method is that it learns a multi-scale metric to distinguish multiple objects at different distances under one image, while DCGAN serves as an encoder-decoder platform to generate parts of an image that contain better discriminative information. To measure the effectiveness of our proposed method, experiments were carried out on the Canadian Institute for Advanced Research (CIFAR) dataset, and it was demonstrated that the proposed new architecture achieved a much better detection rate, particularly on vehicles and pedestrians at distance, making it highly suitable for smart cities applications that need to discover key objects or pedestrians at distance. |
Tasks | Pedestrian Detection |
Published | 2018-11-18 |
URL | https://arxiv.org/abs/1812.00876v4 |
https://arxiv.org/pdf/1812.00876v4.pdf | |
PWC | https://paperswithcode.com/paper/deep-learning-based-pedestrian-detection-at |
Repo | |
Framework | |
Overabundant Information and Learning Traps
Title | Overabundant Information and Learning Traps |
Authors | Annie Liang, Xiaosheng Mu |
Abstract | We develop a model of social learning from overabundant information: Short-lived agents sequentially choose from a large set of (flexibly correlated) information sources for prediction of an unknown state. Signal realizations are public. We demonstrate two starkly different long-run outcomes: (1) efficient information aggregation, where the community eventually learns as fast as possible; (2) “learning traps,” where the community gets stuck observing suboptimal sources and learns inefficiently. Our main results identify a simple property of the signal correlation structure that separates these outcomes. In both regimes, we characterize which sources are observed in the long run and how often. |
Tasks | |
Published | 2018-05-21 |
URL | http://arxiv.org/abs/1805.08134v2 |
http://arxiv.org/pdf/1805.08134v2.pdf | |
PWC | https://paperswithcode.com/paper/overabundant-information-and-learning-traps |
Repo | |
Framework | |
An FPGA-Accelerated Design for Deep Learning Pedestrian Detection in Self-Driving Vehicles
Title | An FPGA-Accelerated Design for Deep Learning Pedestrian Detection in Self-Driving Vehicles |
Authors | Abdallah Moussawi, Kamal Haddad, Anthony Chahine |
Abstract | With the rise of self-driving vehicles comes the risk of accidents and the need for higher safety, and protection for pedestrian detection in the following scenarios: imminent crashes, thus the car should crash into an object and avoid the pedestrian, and in the case of road intersections, where it is important for the car to stop when pedestrians are crossing. Currently, a special topology of deep neural networks called Fused Deep Neural Network (F-DNN) is considered to be the state of the art in pedestrian detection, as it has the lowest miss rate, yet it is very slow. Therefore, acceleration is needed to speed up the performance. This project proposes two contributions to address this problem, by using a deep neural network used for object detection, called Single Shot Multi-Box Detector (SSD). The first contribution is training and tuning the hyperparameters of SSD to improve pedestrian detection. The second contribution is a new FPGA design for accelerating the model on the Altera Arria 10 platform. The final system will be used in self-driving vehicles in real-time. Preliminary results of the improved SSD shows 3% higher miss-rate than F-DNN on Caltech pedestrian detection benchmark, but 4x performance improvement. The acceleration design is expected to achieve an additional performance improvement significantly outweighing the minimal difference in accuracy. |
Tasks | Object Detection, Pedestrian Detection |
Published | 2018-09-16 |
URL | http://arxiv.org/abs/1809.05879v1 |
http://arxiv.org/pdf/1809.05879v1.pdf | |
PWC | https://paperswithcode.com/paper/an-fpga-accelerated-design-for-deep-learning |
Repo | |
Framework | |
On the Algebra in Boole’s Laws of Thought
Title | On the Algebra in Boole’s Laws of Thought |
Authors | Subhash Kak |
Abstract | This article explores the ideas that went into George Boole’s development of an algebra for logical inference in his book The Laws of Thought. We explore in particular his wife Mary Boole’s claim that he was deeply influenced by Indian logic and argue that his work was more than a framework for processing propositions. By exploring parallels between his work and Indian logic, we are able to explain several peculiarities of this work. |
Tasks | |
Published | 2018-03-13 |
URL | http://arxiv.org/abs/1803.04994v1 |
http://arxiv.org/pdf/1803.04994v1.pdf | |
PWC | https://paperswithcode.com/paper/on-the-algebra-in-booles-laws-of-thought |
Repo | |
Framework | |
Blazingly Fast Video Object Segmentation with Pixel-Wise Metric Learning
Title | Blazingly Fast Video Object Segmentation with Pixel-Wise Metric Learning |
Authors | Yuhua Chen, Jordi Pont-Tuset, Alberto Montes, Luc Van Gool |
Abstract | This paper tackles the problem of video object segmentation, given some user annotation which indicates the object of interest. The problem is formulated as pixel-wise retrieval in a learned embedding space: we embed pixels of the same object instance into the vicinity of each other, using a fully convolutional network trained by a modified triplet loss as the embedding model. Then the annotated pixels are set as reference and the rest of the pixels are classified using a nearest-neighbor approach. The proposed method supports different kinds of user input such as segmentation mask in the first frame (semi-supervised scenario), or a sparse set of clicked points (interactive scenario). In the semi-supervised scenario, we achieve results competitive with the state of the art but at a fraction of computation cost (275 milliseconds per frame). In the interactive scenario where the user is able to refine their input iteratively, the proposed method provides instant response to each input, and reaches comparable quality to competing methods with much less interaction. |
Tasks | Metric Learning, Semantic Segmentation, Video Object Segmentation, Video Semantic Segmentation, Visual Object Tracking |
Published | 2018-04-09 |
URL | http://arxiv.org/abs/1804.03131v1 |
http://arxiv.org/pdf/1804.03131v1.pdf | |
PWC | https://paperswithcode.com/paper/blazingly-fast-video-object-segmentation-with |
Repo | |
Framework | |
Effectiveness of Scaled Exponentially-Regularized Linear Units (SERLUs)
Title | Effectiveness of Scaled Exponentially-Regularized Linear Units (SERLUs) |
Authors | G. Zhang, H. Li |
Abstract | Recently, self-normalizing neural networks (SNNs) have been proposed with the intention to avoid batch or weight normalization. The key step in SNNs is to properly scale the exponential linear unit (referred to as SELU) to inherently incorporate normalization based on central limit theory. SELU is a monotonically increasing function, where it has an approximately constant negative output for large negative input. In this work, we propose a new activation function to break the monotonicity property of SELU while still preserving the self-normalizing property. Differently from SELU, the new function introduces a bump-shaped function in the region of negative input by regularizing a linear function with a scaled exponential function, which is referred to as a scaled exponentially-regularized linear unit (SERLU). The bump-shaped function has approximately zero response to large negative input while being able to push the output of SERLU towards zero mean statistically. To effectively combat over-fitting, we develop a so-called shift-dropout for SERLU, which includes standard dropout as a special case. Experimental results on MNIST, CIFAR10 and CIFAR100 show that SERLU-based neural networks provide consistently promising results in comparison to other 5 activation functions including ELU, SELU, Swish, Leakly ReLU and ReLU. |
Tasks | |
Published | 2018-07-26 |
URL | http://arxiv.org/abs/1807.10117v2 |
http://arxiv.org/pdf/1807.10117v2.pdf | |
PWC | https://paperswithcode.com/paper/effectiveness-of-scaled-exponentially |
Repo | |
Framework | |
Sample-Efficient Reinforcement Learning through Transfer and Architectural Priors
Title | Sample-Efficient Reinforcement Learning through Transfer and Architectural Priors |
Authors | Benjamin Spector, Serge Belongie |
Abstract | Recent work in deep reinforcement learning has allowed algorithms to learn complex tasks such as Atari 2600 games just from the reward provided by the game, but these algorithms presently require millions of training steps in order to learn, making them approximately five orders of magnitude slower than humans. One reason for this is that humans build robust shared representations that are applicable to collections of problems, making it much easier to assimilate new variants. This paper first introduces the idea of automatically-generated game sets to aid in transfer learning research, and then demonstrates the utility of shared representations by showing that models can substantially benefit from the incorporation of relevant architectural priors. This technique affords a remarkable 50x positive transfer on a toy problem-set. |
Tasks | Atari Games, Transfer Learning |
Published | 2018-01-07 |
URL | http://arxiv.org/abs/1801.02268v1 |
http://arxiv.org/pdf/1801.02268v1.pdf | |
PWC | https://paperswithcode.com/paper/sample-efficient-reinforcement-learning-1 |
Repo | |
Framework | |
Efficient learning of neighbor representations for boundary trees and forests
Title | Efficient learning of neighbor representations for boundary trees and forests |
Authors | Tharindu Adikari, Stark C. Draper |
Abstract | We introduce a semiparametric approach to neighbor-based classification. We build off the recently proposed Boundary Trees algorithm by Mathy et al.(2015) which enables fast neighbor-based classification, regression and retrieval in large datasets. While boundary trees use an Euclidean measure of similarity, the Differentiable Boundary Tree algorithm by Zoran et al.(2017) was introduced to learn low-dimensional representations of complex input data, on which semantic similarity can be calculated to train boundary trees. As is pointed out by its authors, the differentiable boundary tree approach contains a few limitations that prevents it from scaling to large datasets. In this paper, we introduce Differentiable Boundary Sets, an algorithm that overcomes the computational issues of the differentiable boundary tree scheme and also improves its classification accuracy and data representability. Our algorithm is efficiently implementable with existing tools and offers a significant reduction in training time. We test and compare the algorithms on the well known MNIST handwritten digits dataset and the newer Fashion-MNIST dataset by Xiao et al.(2017). |
Tasks | Semantic Similarity, Semantic Textual Similarity |
Published | 2018-10-26 |
URL | http://arxiv.org/abs/1810.11165v1 |
http://arxiv.org/pdf/1810.11165v1.pdf | |
PWC | https://paperswithcode.com/paper/efficient-learning-of-neighbor |
Repo | |
Framework | |
Feature selection in weakly coherent matrices
Title | Feature selection in weakly coherent matrices |
Authors | Stephane Chretien, Zhen-Wai Olivier Ho |
Abstract | A problem of paramount importance in both pure (Restricted Invertibility problem) and applied mathematics (Feature extraction) is the one of selecting a submatrix of a given matrix, such that this submatrix has its smallest singular value above a specified level. Such problems can be addressed using perturbation analysis. In this paper, we propose a perturbation bound for the smallest singular value of a given matrix after appending a column, under the assumption that its initial coherence is not large, and we use this bound to derive a fast algorithm for feature extraction. |
Tasks | Feature Selection |
Published | 2018-04-03 |
URL | http://arxiv.org/abs/1804.01119v1 |
http://arxiv.org/pdf/1804.01119v1.pdf | |
PWC | https://paperswithcode.com/paper/feature-selection-in-weakly-coherent-matrices |
Repo | |
Framework | |
Zooming Network
Title | Zooming Network |
Authors | Yukun Yan, Daqi Zheng, Zhengdong Lu, Sen Song |
Abstract | Structural information is important in natural language understanding. Although some current neural net-based models have a limited ability to take local syntactic information, they fail to use high-level and large-scale structures of documents. This information is valuable for text understanding since it contains the author’s strategy to express information, in building an effective representation and forming appropriate output modes. We propose a neural net-based model, Zooming Network, capable of representing and leveraging text structure of long document and developing its own analyzing rhythm to extract critical information. Generally, ZN consists of an encoding neural net that can build a hierarchical representation of a document, and an interpreting neural model that can read the information at multi-levels and issuing labeling actions through a policy-net. Our model is trained with a hybrid paradigm of supervised learning (distinguishing right and wrong decision) and reinforcement learning (determining the goodness among multiple right paths). We applied the proposed model to long text sequence labeling tasks, with performance exceeding baseline model (biLSTM-crf) by 10 F1-measure. |
Tasks | |
Published | 2018-10-04 |
URL | http://arxiv.org/abs/1810.02114v1 |
http://arxiv.org/pdf/1810.02114v1.pdf | |
PWC | https://paperswithcode.com/paper/zooming-network |
Repo | |
Framework | |
Measurement-wise Occlusion in Multi-object Tracking
Title | Measurement-wise Occlusion in Multi-object Tracking |
Authors | Michael Motro, Joydeep Ghosh |
Abstract | Handling object interaction is a fundamental challenge in practical multi-object tracking, even for simple interactive effects such as one object temporarily occluding another. We formalize the problem of occlusion in tracking with two different abstractions. In object-wise occlusion, objects that are occluded by other objects do not generate measurements. In measurement-wise occlusion, a previously unstudied approach, all objects may generate measurements but some measurements may be occluded by others. While the relative validity of each abstraction depends on the situation and sensor, measurement-wise occlusion fits into probabilistic multi-object tracking algorithms with much looser assumptions on object interaction. Its value is demonstrated by showing that it naturally derives a popular approximation for lidar tracking, and by an example of visual tracking in image space. |
Tasks | Multi-Object Tracking, Object Tracking, Visual Tracking |
Published | 2018-05-21 |
URL | http://arxiv.org/abs/1805.08324v1 |
http://arxiv.org/pdf/1805.08324v1.pdf | |
PWC | https://paperswithcode.com/paper/measurement-wise-occlusion-in-multi-object |
Repo | |
Framework | |
Unleashing Linear Optimizers for Group-Fair Learning and Optimization
Title | Unleashing Linear Optimizers for Group-Fair Learning and Optimization |
Authors | Daniel Alabi, Nicole Immorlica, Adam Tauman Kalai |
Abstract | Most systems and learning algorithms optimize average performance or average loss – one reason being computational complexity. However, many objectives of practical interest are more complex than simply average loss. This arises, for example, when balancing performance or loss with fairness across people. We prove that, from a computational perspective, optimizing arbitrary objectives that take into account performance over a small number of groups is not significantly harder to optimize than average performance. Our main result is a polynomial-time reduction that uses a linear optimizer to optimize an arbitrary (Lipschitz continuous) function of performance over a (constant) number of possibly-overlapping groups. This includes fairness objectives over small numbers of groups, and we further point out that other existing notions of fairness such as individual fairness can be cast as convex optimization and hence more standard convex techniques can be used. Beyond learning, our approach applies to multi-objective optimization, more generally. |
Tasks | |
Published | 2018-04-11 |
URL | http://arxiv.org/abs/1804.04503v2 |
http://arxiv.org/pdf/1804.04503v2.pdf | |
PWC | https://paperswithcode.com/paper/unleashing-linear-optimizers-for-group-fair |
Repo | |
Framework | |
A Neural Markovian Concurrent Image Labeling Algorithm
Title | A Neural Markovian Concurrent Image Labeling Algorithm |
Authors | John Mashford |
Abstract | This paper describes the MCV image labeling algorithm which is a (semi-) hierarchical algorithm commencing with a partition made up of single pixel regions and merging regions or subsets of regions using a Markov random field (MRF) image model. It is an example of a general approach to computer vision called concurrent vision in which the operations of image segmentation and image classification are carried out concurrently. The output of the MCV algorithm can be a simple segmentation partition or a sequence of partitions which can provide useful information to higher level vision systems. In the case of an autoregressive Gaussian MRF the evaluation of sub-images for homogeneity is computationally inexpensive and may be effected by a hardwired feed-forward neural network. The merge operation of the algorithm is massively parallelizable. While being applicable to images (i.e. 2D signals), the algorithm is equally applicable to 1D signals (e.g. speech) or 3D signals (e.g. video sequences) |
Tasks | Image Classification, Semantic Segmentation |
Published | 2018-03-20 |
URL | http://arxiv.org/abs/1804.04540v1 |
http://arxiv.org/pdf/1804.04540v1.pdf | |
PWC | https://paperswithcode.com/paper/a-neural-markovian-concurrent-image-labeling |
Repo | |
Framework | |
Local Kernels that Approximate Bayesian Regularization and Proximal Operators
Title | Local Kernels that Approximate Bayesian Regularization and Proximal Operators |
Authors | Frank Ong, Peyman Milanfar, Pascal Getreuer |
Abstract | In this work, we broadly connect kernel-based filtering (e.g. approaches such as the bilateral filters and nonlocal means, but also many more) with general variational formulations of Bayesian regularized least squares, and the related concept of proximal operators. The latter set of variational/Bayesian/proximal formulations often result in optimization problems that do not have closed-form solutions, and therefore typically require global iterative solutions. Our main contribution here is to establish how one can approximate the solution of the resulting global optimization problems with use of locally adaptive filters with specific kernels. Our results are valid for small regularization strength but the approach is powerful enough to be useful for a wide range of applications because we expose how to derive a “kernelized” solution to these problems that approximates the global solution in one-shot, using only local operations. As another side benefit in the reverse direction, given a local data-adaptive filter constructed with a particular choice of kernel, we enable the interpretation of such filters in the variational/Bayesian/proximal framework. |
Tasks | |
Published | 2018-03-09 |
URL | http://arxiv.org/abs/1803.03711v1 |
http://arxiv.org/pdf/1803.03711v1.pdf | |
PWC | https://paperswithcode.com/paper/local-kernels-that-approximate-bayesian |
Repo | |
Framework | |