Paper Group ANR 859
Unsupervised Primitive Discovery for Improved 3D Generative Modeling. Behavior Planning of Autonomous Cars with Social Perception. Efficient 8-Bit Quantization of Transformer Neural Machine Language Translation Model. Neural networks for option pricing and hedging: a literature review. Focusing and Diffusion: Bidirectional Attentive Graph Convoluti …
Unsupervised Primitive Discovery for Improved 3D Generative Modeling
| Title | Unsupervised Primitive Discovery for Improved 3D Generative Modeling |
| Authors | Salman H. Khan, Yulan Guo, Munawar Hayat, Nick Barnes |
| Abstract | 3D shape generation is a challenging problem due to the high-dimensional output space and complex part configurations of real-world objects. As a result, existing algorithms experience difficulties in accurate generative modeling of 3D shapes. Here, we propose a novel factorized generative model for 3D shape generation that sequentially transitions from coarse to fine scale shape generation. To this end, we introduce an unsupervised primitive discovery algorithm based on a higher-order conditional random field model. Using the primitive parts for shapes as attributes, a parameterized 3D representation is modeled in the first stage. This representation is further refined in the next stage by adding fine scale details to shape. Our results demonstrate improved representation ability of the generative model and better quality samples of newly generated 3D shapes. Further, our primitive generation approach can accurately parse common objects into a simplified representation. |
| Tasks | 3D Shape Generation |
| Published | 2019-06-09 |
| URL | https://arxiv.org/abs/1906.03650v1 |
| https://arxiv.org/pdf/1906.03650v1.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-primitive-discovery-for-improved-1 |
| Repo | |
| Framework | |
Behavior Planning of Autonomous Cars with Social Perception
| Title | Behavior Planning of Autonomous Cars with Social Perception |
| Authors | Liting Sun, Wei Zhan, Ching-Yao Chan, Masayoshi Tomizuka |
| Abstract | Autonomous cars have to navigate in dynamic environment which can be full of uncertainties. The uncertainties can come either from sensor limitations such as occlusions and limited sensor range, or from probabilistic prediction of other road participants, or from unknown social behavior in a new area. To safely and efficiently drive in the presence of these uncertainties, the decision-making and planning modules of autonomous cars should intelligently utilize all available information and appropriately tackle the uncertainties so that proper driving strategies can be generated. In this paper, we propose a social perception scheme which treats all road participants as distributed sensors in a sensor network. By observing the individual behaviors as well as the group behaviors, uncertainties of the three types can be updated uniformly in a belief space. The updated beliefs from the social perception are then explicitly incorporated into a probabilistic planning framework based on Model Predictive Control (MPC). The cost function of the MPC is learned via inverse reinforcement learning (IRL). Such an integrated probabilistic planning module with socially enhanced perception enables the autonomous vehicles to generate behaviors which are defensive but not overly conservative, and socially compatible. The effectiveness of the proposed framework is verified in simulation on an representative scenario with sensor occlusions. |
| Tasks | Autonomous Vehicles, Decision Making |
| Published | 2019-05-02 |
| URL | https://arxiv.org/abs/1905.00988v1 |
| https://arxiv.org/pdf/1905.00988v1.pdf | |
| PWC | https://paperswithcode.com/paper/behavior-planning-of-autonomous-cars-with |
| Repo | |
| Framework | |
Efficient 8-Bit Quantization of Transformer Neural Machine Language Translation Model
| Title | Efficient 8-Bit Quantization of Transformer Neural Machine Language Translation Model |
| Authors | Aishwarya Bhandare, Vamsi Sripathi, Deepthi Karkada, Vivek Menon, Sun Choi, Kushal Datta, Vikram Saletore |
| Abstract | In this work, we quantize a trained Transformer machine language translation model leveraging INT8/VNNI instructions in the latest Intel$^\circledR$ Xeon$^\circledR$ Cascade Lake processors to improve inference performance while maintaining less than 0.5$%$ drop in accuracy. To the best of our knowledge, this is the first attempt in the industry to quantize the Transformer model. This has high impact as it clearly demonstrates the various complexities of quantizing the language translation model. We present novel quantization techniques directly in TensorFlow to opportunistically replace 32-bit floating point (FP32) computations with 8-bit integers (INT8) and transform the FP32 computational graph. We also present a bin-packing parallel batching technique to maximize CPU utilization. Overall, our optimizations with INT8/VNNI deliver 1.5X improvement over the best FP32 performance. Furthermore, it reveals the opportunities and challenges to boost performance of quantized deep learning inference and establishes best practices to run inference with high efficiency on Intel CPUs. |
| Tasks | Quantization |
| Published | 2019-06-03 |
| URL | https://arxiv.org/abs/1906.00532v2 |
| https://arxiv.org/pdf/1906.00532v2.pdf | |
| PWC | https://paperswithcode.com/paper/190600532 |
| Repo | |
| Framework | |
Neural networks for option pricing and hedging: a literature review
| Title | Neural networks for option pricing and hedging: a literature review |
| Authors | Johannes Ruf, Weiguan Wang |
| Abstract | Neural networks have been used as a nonparametric method for option pricing and hedging since the early 1990s. Far over a hundred papers have been published on this topic. This note intends to provide a comprehensive review. Papers are compared in terms of input features, output variables, benchmark models, performance measures, data partition methods, and underlying assets. Furthermore, related work and regularisation techniques are discussed. |
| Tasks | |
| Published | 2019-11-13 |
| URL | https://arxiv.org/abs/1911.05620v1 |
| https://arxiv.org/pdf/1911.05620v1.pdf | |
| PWC | https://paperswithcode.com/paper/neural-networks-for-option-pricing-and |
| Repo | |
| Framework | |
Focusing and Diffusion: Bidirectional Attentive Graph Convolutional Networks for Skeleton-based Action Recognition
| Title | Focusing and Diffusion: Bidirectional Attentive Graph Convolutional Networks for Skeleton-based Action Recognition |
| Authors | Jialin Gao, Tong He, Xi Zhou, Shiming Ge |
| Abstract | A collection of approaches based on graph convolutional networks have proven success in skeleton-based action recognition by exploring neighborhood information and dense dependencies between intra-frame joints. However, these approaches usually ignore the spatial-temporal global context as well as the local relation between inter-frame and intra-frame. In this paper, we propose a focusing and diffusion mechanism to enhance graph convolutional networks by paying attention to the kinematic dependence of articulated human pose in a frame and their implicit dependencies over frames. In the focusing process, we introduce an attention module to learn a latent node over the intra-frame joints to convey spatial contextual information. In this way, the sparse connections between joints in a frame can be well captured, while the global context over the entire sequence is further captured by these hidden nodes with a bidirectional LSTM. In the diffusing process, the learned spatial-temporal contextual information is passed back to the spatial joints, leading to a bidirectional attentive graph convolutional network (BAGCN) that can facilitate skeleton-based action recognition. Extensive experiments on the challenging NTU RGB+D and Skeleton-Kinetics benchmarks demonstrate the efficacy of our approach. |
| Tasks | Skeleton Based Action Recognition |
| Published | 2019-12-24 |
| URL | https://arxiv.org/abs/1912.11521v1 |
| https://arxiv.org/pdf/1912.11521v1.pdf | |
| PWC | https://paperswithcode.com/paper/focusing-and-diffusion-bidirectional |
| Repo | |
| Framework | |
Global Convergence of Adaptive Gradient Methods for An Over-parameterized Neural Network
| Title | Global Convergence of Adaptive Gradient Methods for An Over-parameterized Neural Network |
| Authors | Xiaoxia Wu, Simon S. Du, Rachel Ward |
| Abstract | Adaptive gradient methods like AdaGrad are widely used in optimizing neural networks. Yet, existing convergence guarantees for adaptive gradient methods require either convexity or smoothness, and, in the smooth setting, only guarantee convergence to a stationary point. We propose an adaptive gradient method and show that for two-layer over-parameterized neural networks – if the width is sufficiently large (polynomially) – then the proposed method converges \emph{to the global minimum} in polynomial time, and convergence is robust, \emph{ without the need to fine-tune hyper-parameters such as the step-size schedule and with the level of over-parametrization independent of the training error}. Our analysis indicates in particular that over-parametrization is crucial for the harnessing the full potential of adaptive gradient methods in the setting of neural networks. |
| Tasks | |
| Published | 2019-02-19 |
| URL | https://arxiv.org/abs/1902.07111v2 |
| https://arxiv.org/pdf/1902.07111v2.pdf | |
| PWC | https://paperswithcode.com/paper/global-convergence-of-adaptive-gradient |
| Repo | |
| Framework | |
Applying Adversarial Auto-encoder for Estimating Human Walking Gait Abnormality Index
| Title | Applying Adversarial Auto-encoder for Estimating Human Walking Gait Abnormality Index |
| Authors | Trong-Nguyen Nguyen, Jean Meunier |
| Abstract | This paper proposes an approach that estimates human walking gait quality index using an adversarial auto-encoder (AAE), i.e. a combination of auto-encoder and generative adversarial network (GAN). Since most GAN-based models have been employed as data generators, our work introduces another perspective of their application. This method directly works on a sequence of 3D point clouds representing the walking postures of a subject. By fitting a cylinder onto each point cloud and feeding obtained histograms to an appropriate AAE, our system is able to provide different measures that may be used as gait quality indices. The combinations of such quantities are also investigated to obtain improved indicators. The ability of our method is demonstrated by experimenting on a large dataset of nearly 100 thousands point clouds and the results outperform related approaches that employ different input data types. |
| Tasks | |
| Published | 2019-08-16 |
| URL | https://arxiv.org/abs/1908.06188v1 |
| https://arxiv.org/pdf/1908.06188v1.pdf | |
| PWC | https://paperswithcode.com/paper/applying-adversarial-auto-encoder-for |
| Repo | |
| Framework | |
Nuclear Instance Segmentation using a Proposal-Free Spatially Aware Deep Learning Framework
| Title | Nuclear Instance Segmentation using a Proposal-Free Spatially Aware Deep Learning Framework |
| Authors | Navid Alemi Koohbanani, Mostafa Jahanifar, Ali Gooya, Nasir Rajpoot |
| Abstract | Nuclear segmentation in histology images is a challenging task due to significant variations in the shape and appearance of nuclei. One of the main hurdles in nuclear instance segmentation is overlapping nuclei where a smart algorithm is needed to separate each nucleus. In this paper, we introduce a proposal-free deep learning based framework to address these challenges. To this end, we propose a spatially-aware network (SpaNet) to capture spatial information in a multi-scale manner. A dual-head variation of the SpaNet is first utilized to predict the pixel-wise segmentation and centroid detection maps of nuclei. Based on these outputs, a single-head SpaNet predicts the positional information related to each nucleus instance. Spectral clustering method is applied on the output of the last SpaNet, which utilizes the nuclear mask and the Gaussian-like detection map for determining the connected components and associated cluster identifiers, respectively. The output of the clustering method is the final nuclear instance segmentation mask. We applied our method on a publicly available multi-organ data set and achieved state-of-the-art performance for nuclear segmentation. |
| Tasks | Instance Segmentation, Nuclear Segmentation, Semantic Segmentation |
| Published | 2019-08-27 |
| URL | https://arxiv.org/abs/1908.10356v1 |
| https://arxiv.org/pdf/1908.10356v1.pdf | |
| PWC | https://paperswithcode.com/paper/nuclear-instance-segmentation-using-a |
| Repo | |
| Framework | |
Variable Selection with Copula Entropy
| Title | Variable Selection with Copula Entropy |
| Authors | Ma Jian |
| Abstract | Variable selection is of significant importance for classification and regression tasks in machine learning and statistical applications where both predictability and explainability are needed. In this paper, a Copula Entropy (CE) based method for variable selection which use CE based ranks to select variables is proposed. The method is both model-free and tuning-free. Comparison experiments between the proposed method and traditional variable selection methods, such as Stepwise Selection, regularized generalized linear models and Adaptive LASSO, were conducted on the UCI heart disease data. Experimental results show that CE based method can select the `right’ variables out effectively and derive better interpretable results than traditional methods do without sacrificing accuracy performance. It is believed that CE based variable selection can help to build more explainable models. | |
| Tasks | |
| Published | 2019-10-28 |
| URL | https://arxiv.org/abs/1910.12389v1 |
| https://arxiv.org/pdf/1910.12389v1.pdf | |
| PWC | https://paperswithcode.com/paper/variable-selection-with-copula-entropy |
| Repo | |
| Framework | |
Extreme Learning Machine design for dealing with unrepresentative features
| Title | Extreme Learning Machine design for dealing with unrepresentative features |
| Authors | Nicolás Nieto, Francisco Ibarrola, Victoria Peterson, Hugo Rufiner, Ruben Spies |
| Abstract | Extreme Learning Machines (ELMs) have become a popular tool in the field of Artificial Intelligence due to their very high training speed and generalization capabilities. Another advantage is that they have a single hyper-parameter that must be tuned up: the number of hidden nodes. Most traditional approaches dictate that this parameter should be chosen smaller than the number of available training samples in order to avoid over-fitting. In fact, it has been proved that choosing the number of hidden nodes equal to the number of training samples yields a perfect training classification with probability 1 (w.r.t. the random parameter initialization). In this article we argue that in spite of this, in some cases it may be beneficial to choose a much larger number of hidden nodes, depending on certain properties of the data. We explain why this happens and show some examples to illustrate how the model behaves. In addition, we present a pruning algorithm to cope with the additional computational burden associated to the enlarged ELM. Experimental results using electroencephalography (EEG) signals show an improvement in performance with respect to traditional ELM approaches, while diminishing the extra computing time associated to the use of large architectures. |
| Tasks | EEG |
| Published | 2019-12-04 |
| URL | https://arxiv.org/abs/1912.02154v1 |
| https://arxiv.org/pdf/1912.02154v1.pdf | |
| PWC | https://paperswithcode.com/paper/extreme-learning-machine-design-for-dealing |
| Repo | |
| Framework | |
Connecting First and Second Order Recurrent Networks with Deterministic Finite Automata
| Title | Connecting First and Second Order Recurrent Networks with Deterministic Finite Automata |
| Authors | Qinglong Wang, Kaixuan Zhang, Xue Liu, C. Lee Giles |
| Abstract | We propose an approach that connects recurrent networks with different orders of hidden interaction with regular grammars of different levels of complexity. We argue that the correspondence between recurrent networks and formal computational models gives understanding to the analysis of the complicated behaviors of recurrent networks. We introduce an entropy value that categorizes all regular grammars into three classes with different levels of complexity, and show that several existing recurrent networks match grammars from either all or partial classes. As such, the differences between regular grammars reveal the different properties of these models. We also provide a unification of all investigated recurrent networks. Our evaluation shows that the unified recurrent network has improved performance in learning grammars, and demonstrates comparable performance on a real-world dataset with more complicated models. |
| Tasks | |
| Published | 2019-11-12 |
| URL | https://arxiv.org/abs/1911.04644v1 |
| https://arxiv.org/pdf/1911.04644v1.pdf | |
| PWC | https://paperswithcode.com/paper/connecting-first-and-second-order-recurrent |
| Repo | |
| Framework | |
State-of-the-Art Vietnamese Word Segmentation
| Title | State-of-the-Art Vietnamese Word Segmentation |
| Authors | Song Nguyen Duc Cong, Quoc Hung Ngo, Rachsuda Jiamthapthaksin |
| Abstract | Word segmentation is the first step of any tasks in Vietnamese language processing. This paper reviews stateof-the-art approaches and systems for word segmentation in Vietnamese. To have an overview of all stages from building corpora to developing toolkits, we discuss building the corpus stage, approaches applied to solve the word segmentation and existing toolkits to segment words in Vietnamese sentences. In addition, this study shows clearly the motivations on building corpus and implementing machine learning techniques to improve the accuracy for Vietnamese word segmentation. According to our observation, this study also reports a few of achivements and limitations in existing Vietnamese word segmentation systems. |
| Tasks | |
| Published | 2019-06-18 |
| URL | https://arxiv.org/abs/1906.07662v1 |
| https://arxiv.org/pdf/1906.07662v1.pdf | |
| PWC | https://paperswithcode.com/paper/state-of-the-art-vietnamese-word-segmentation |
| Repo | |
| Framework | |
NormGrad: Finding the Pixels that Matter for Training
| Title | NormGrad: Finding the Pixels that Matter for Training |
| Authors | Sylvestre-Alvise Rebuffi, Ruth Fong, Xu Ji, Hakan Bilen, Andrea Vedaldi |
| Abstract | The different families of saliency methods, either based on contrastive signals, closed-form formulas mixing gradients with activations or on perturbation masks, all focus on which parts of an image are responsible for the model’s inference. In this paper, we are rather interested by the locations of an image that contribute to the model’s training. First, we propose a principled attribution method that we extract from the summation formula used to compute the gradient of the weights for a 1x1 convolutional layer. The resulting formula is fast to compute and can used throughout the network, allowing us to efficiently produce fined-grained importance maps. We will show how to extend it in order to compute saliency maps at any targeted point within the network. Secondly, to make the attribution really specific to the training of the model, we introduce a meta-learning approach for saliency methods by considering an inner optimisation step within the loss. This way, we do not aim at identifying the parts of an image that contribute to the model’s output but rather the locations that are responsible for the good training of the model on this image. Conversely, we also show that a similar meta-learning approach can be used to extract the adversarial locations which can lead to the degradation of the model. |
| Tasks | Meta-Learning |
| Published | 2019-10-19 |
| URL | https://arxiv.org/abs/1910.08823v1 |
| https://arxiv.org/pdf/1910.08823v1.pdf | |
| PWC | https://paperswithcode.com/paper/normgrad-finding-the-pixels-that-matter-for |
| Repo | |
| Framework | |
Learning to Crawl
| Title | Learning to Crawl |
| Authors | Utkarsh Upadhyay, Robert Busa-Fekete, Wojciech Kotlowski, David Pal, Balazs Szorenyi |
| Abstract | Web crawling is the problem of keeping a cache of webpages fresh, i.e., having the most recent copy available when a page is requested. This problem is usually coupled with the natural restriction that the bandwidth available to the web crawler is limited. The corresponding optimization problem was solved optimally by Azar et al. [2018] under the assumption that, for each webpage, both the elapsed time between two changes and the elapsed time between two requests follow a Poisson distribution with known parameters. In this paper, we study the same control problem but under the assumption that the change rates are unknown a priori, and thus we need to estimate them in an online fashion using only partial observations (i.e., single-bit signals indicating whether the page has changed since the last refresh). As a point of departure, we characterise the conditions under which one can solve the problem with such partial observability. Next, we propose a practical estimator and compute confidence intervals for it in terms of the elapsed time between the observations. Finally, we show that the explore-and-commit algorithm achieves an $\mathcal{O}(\sqrt{T})$ regret with a carefully chosen exploration horizon. Our simulation study shows that our online policy scales well and achieves close to optimal performance for a wide range of the parameters. |
| Tasks | |
| Published | 2019-05-29 |
| URL | https://arxiv.org/abs/1905.12781v2 |
| https://arxiv.org/pdf/1905.12781v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-to-crawl |
| Repo | |
| Framework | |
Coping with Large Traffic Volumes in Schedule-Driven Traffic Signal Control
| Title | Coping with Large Traffic Volumes in Schedule-Driven Traffic Signal Control |
| Authors | Hsu-Chieh Hu, Stephen F. Smith |
| Abstract | Recent work in decentralized, schedule-driven traffic control has demonstrated the ability to significantly improve traffic flow efficiency in complex urban road networks. However, in situations where vehicle volumes increase to the point that the physical capacity of a road network reaches or exceeds saturation, it has been observed that the effectiveness of a schedule-driven approach begins to degrade, leading to progressively higher network congestion. In essence, the traffic control problem becomes less of a scheduling problem and more of a queue management problem in this circumstance. In this paper we propose a composite approach to real-time traffic control that uses sensed information on queue lengths to influence scheduling decisions and gracefully shift the signal control strategy to queue management in high volume/high congestion settings. Specifically, queue-length information is used to establish weights for the sensed vehicle clusters that must be scheduled through a given intersection at any point, and hence bias the wait time minimization calculation. To compute these weights, we develop a model in which successive movement phases are viewed as different states of an Ising model, and parameters quantify strength of interactions. To ensure scalability, queue information is only exchanged between direct neighbors and the asynchronous nature of local intersection scheduling is preserved. We demonstrate the potential of the approach through microscopic traffic simulation of a real-world road network, showing a 60% reduction in average wait times over the baseline schedule-driven approach in heavy traffic scenarios. We also report initial field test results, which show the ability to reduce queues during heavy traffic periods. |
| Tasks | |
| Published | 2019-03-06 |
| URL | http://arxiv.org/abs/1903.04278v1 |
| http://arxiv.org/pdf/1903.04278v1.pdf | |
| PWC | https://paperswithcode.com/paper/coping-with-large-traffic-volumes-in-schedule |
| Repo | |
| Framework | |
