Paper Group ANR 698
Disentangling 3D Pose in A Dendritic CNN for Unconstrained 2D Face Alignment. Object Detection in Satellite Imagery using 2-Step Convolutional Neural Networks. Deep Stacked Stochastic Configuration Networks for Lifelong Learning of Non-Stationary Data Streams. Attend Before you Act: Leveraging human visual attention for continual learning. Dirichle …
Disentangling 3D Pose in A Dendritic CNN for Unconstrained 2D Face Alignment
Title | Disentangling 3D Pose in A Dendritic CNN for Unconstrained 2D Face Alignment |
Authors | Amit Kumar, Rama Chellappa |
Abstract | Heatmap regression has been used for landmark localization for quite a while now. Most of the methods use a very deep stack of bottleneck modules for heatmap classification stage, followed by heatmap regression to extract the keypoints. In this paper, we present a single dendritic CNN, termed as Pose Conditioned Dendritic Convolution Neural Network (PCD-CNN), where a classification network is followed by a second and modular classification network, trained in an end to end fashion to obtain accurate landmark points. Following a Bayesian formulation, we disentangle the 3D pose of a face image explicitly by conditioning the landmark estimation on pose, making it different from multi-tasking approaches. Extensive experimentation shows that conditioning on pose reduces the localization error by making it agnostic to face pose. The proposed model can be extended to yield variable number of landmark points and hence broadening its applicability to other datasets. Instead of increasing depth or width of the network, we train the CNN efficiently with Mask-Softmax Loss and hard sample mining to achieve upto $15%$ reduction in error compared to state-of-the-art methods for extreme and medium pose face images from challenging datasets including AFLW, AFW, COFW and IBUG. |
Tasks | Face Alignment |
Published | 2018-02-19 |
URL | http://arxiv.org/abs/1802.06713v3 |
http://arxiv.org/pdf/1802.06713v3.pdf | |
PWC | https://paperswithcode.com/paper/disentangling-3d-pose-in-a-dendritic-cnn-for |
Repo | |
Framework | |
Object Detection in Satellite Imagery using 2-Step Convolutional Neural Networks
Title | Object Detection in Satellite Imagery using 2-Step Convolutional Neural Networks |
Authors | Hiroki Miyamoto, Kazuki Uehara, Masahiro Murakawa, Hidenori Sakanashi, Hirokazu Nosato, Toru Kouyama, Ryosuke Nakamura |
Abstract | This paper presents an efficient object detection method from satellite imagery. Among a number of machine learning algorithms, we proposed a combination of two convolutional neural networks (CNN) aimed at high precision and high recall, respectively. We validated our models using golf courses as target objects. The proposed deep learning method demonstrated higher accuracy than previous object identification methods. |
Tasks | Object Detection |
Published | 2018-08-09 |
URL | http://arxiv.org/abs/1808.02996v1 |
http://arxiv.org/pdf/1808.02996v1.pdf | |
PWC | https://paperswithcode.com/paper/object-detection-in-satellite-imagery-using-2 |
Repo | |
Framework | |
Deep Stacked Stochastic Configuration Networks for Lifelong Learning of Non-Stationary Data Streams
Title | Deep Stacked Stochastic Configuration Networks for Lifelong Learning of Non-Stationary Data Streams |
Authors | Mahardhika Pratama, Dianhui Wang |
Abstract | The concept of SCN offers a fast framework with universal approximation guarantee for lifelong learning of non-stationary data streams. Its adaptive scope selection property enables for proper random generation of hidden unit parameters advancing conventional randomized approaches constrained with a fixed scope of random parameters. This paper proposes deep stacked stochastic configuration network (DSSCN) for continual learning of non-stationary data streams which contributes two major aspects: 1) DSSCN features a self-constructing methodology of deep stacked network structure where hidden unit and hidden layer are extracted automatically from continuously generated data streams; 2) the concept of SCN is developed to randomly assign inverse covariance matrix of multivariate Gaussian function in the hidden node addition step bypassing its computationally prohibitive tuning phase. Numerical evaluation and comparison with prominent data stream algorithms under two procedures: periodic hold-out and prequential test-then-train processes demonstrate the advantage of proposed methodology. |
Tasks | Continual Learning |
Published | 2018-08-07 |
URL | https://arxiv.org/abs/1808.02234v3 |
https://arxiv.org/pdf/1808.02234v3.pdf | |
PWC | https://paperswithcode.com/paper/deep-stacked-stochastic-configuration |
Repo | |
Framework | |
Attend Before you Act: Leveraging human visual attention for continual learning
Title | Attend Before you Act: Leveraging human visual attention for continual learning |
Authors | Khimya Khetarpal, Doina Precup |
Abstract | When humans perform a task, such as playing a game, they selectively pay attention to certain parts of the visual input, gathering relevant information and sequentially combining it to build a representation from the sensory data. In this work, we explore leveraging where humans look in an image as an implicit indication of what is salient for decision making. We build on top of the UNREAL architecture in DeepMind Lab’s 3D navigation maze environment. We train the agent both with original images and foveated images, which were generated by overlaying the original images with saliency maps generated using a real-time spectral residual technique. We investigate the effectiveness of this approach in transfer learning by measuring performance in the context of noise in the environment. |
Tasks | Continual Learning, Decision Making, Transfer Learning |
Published | 2018-07-25 |
URL | http://arxiv.org/abs/1807.09664v1 |
http://arxiv.org/pdf/1807.09664v1.pdf | |
PWC | https://paperswithcode.com/paper/attend-before-you-act-leveraging-human-visual |
Repo | |
Framework | |
Dirichlet Mixture Model based VQ Performance Prediction for Line Spectral Frequency
Title | Dirichlet Mixture Model based VQ Performance Prediction for Line Spectral Frequency |
Authors | Zhanyu Ma |
Abstract | In this paper, we continue our previous work on the Dirichlet mixture model (DMM)-based VQ to derive the performance bound of the LSF VQ. The LSF parameters are transformed into the $\Delta$LSF domain and the underlying distribution of the $\Delta$LSF parameters are modelled by a DMM with finite number of mixture components. The quantization distortion, in terms of the mean squared error (MSE), is calculated with the high rate theory. The mapping relation between the perceptually motivated log spectral distortion (LSD) and the MSE is empirically approximated by a polynomial. With this mapping function, the minimum required bit rate for transparent coding of the LSF is estimated. |
Tasks | Quantization |
Published | 2018-08-02 |
URL | https://arxiv.org/abs/1808.00818v2 |
https://arxiv.org/pdf/1808.00818v2.pdf | |
PWC | https://paperswithcode.com/paper/dirichlet-mixture-model-based-vq-performance |
Repo | |
Framework | |
Coherence-Aware Neural Topic Modeling
Title | Coherence-Aware Neural Topic Modeling |
Authors | Ran Ding, Ramesh Nallapati, Bing Xiang |
Abstract | Topic models are evaluated based on their ability to describe documents well (i.e. low perplexity) and to produce topics that carry coherent semantic meaning. In topic modeling so far, perplexity is a direct optimization target. However, topic coherence, owing to its challenging computation, is not optimized for and is only evaluated after training. In this work, under a neural variational inference framework, we propose methods to incorporate a topic coherence objective into the training process. We demonstrate that such a coherence-aware topic model exhibits a similar level of perplexity as baseline models but achieves substantially higher topic coherence. |
Tasks | Topic Models |
Published | 2018-09-07 |
URL | http://arxiv.org/abs/1809.02687v1 |
http://arxiv.org/pdf/1809.02687v1.pdf | |
PWC | https://paperswithcode.com/paper/coherence-aware-neural-topic-modeling |
Repo | |
Framework | |
Pre-trainable Reservoir Computing with Recursive Neural Gas
Title | Pre-trainable Reservoir Computing with Recursive Neural Gas |
Authors | Luca Carcano, Emanuele Plebani, Danilo Pietro Pau, Marco Piastra |
Abstract | Echo State Networks (ESN) are a class of Recurrent Neural Networks (RNN) that has gained substantial popularity due to their effectiveness, ease of use and potential for compact hardware implementation. An ESN contains the three network layers input, reservoir and readout where the reservoir is the truly recurrent network. The input and reservoir layers of an ESN are initialized at random and never trained afterwards and the training of the ESN is applied to the readout layer only. The alternative of Recursive Neural Gas (RNG) is one of the many proposals of fully-trainable reservoirs that can be found in the literature. Although some improvements in performance have been reported with RNG, to the best of authors’ knowledge, no experimental comparative results are known with benchmarks for which ESN is known to yield excellent results. This work describes an accurate model of RNG together with some extensions to the models presented in the literature and shows comparative results on three well-known and accepted datasets. The experimental results obtained show that, under specific circumstances, RNG-based reservoirs can achieve better performance. |
Tasks | |
Published | 2018-07-25 |
URL | http://arxiv.org/abs/1807.09510v1 |
http://arxiv.org/pdf/1807.09510v1.pdf | |
PWC | https://paperswithcode.com/paper/pre-trainable-reservoir-computing-with |
Repo | |
Framework | |
Fusion of an Ensemble of Augmented Image Detectors for Robust Object Detection
Title | Fusion of an Ensemble of Augmented Image Detectors for Robust Object Detection |
Authors | Pan Wei, John E. Ball, Derek T. Anderson |
Abstract | A significant challenge in object detection is accurate identification of an object’s position in image space, whereas one algorithm with one set of parameters is usually not enough, and the fusion of multiple algorithms and/or parameters can lead to more robust results. Herein, a new computational intelligence fusion approach based on the dynamic analysis of agreement among object detection outputs is proposed. Furthermore, we propose an online versus just in training image augmentation strategy. Experiments comparing the results both with and without fusion are presented. We demonstrate that the augmented and fused combination results are the best, with respect to higher accuracy rates and reduction of outlier influences. The approach is demonstrated in the context of cone, pedestrian and box detection for Advanced Driver Assistance Systems (ADAS) applications. |
Tasks | Image Augmentation, Object Detection, Robust Object Detection |
Published | 2018-03-17 |
URL | http://arxiv.org/abs/1803.06554v1 |
http://arxiv.org/pdf/1803.06554v1.pdf | |
PWC | https://paperswithcode.com/paper/fusion-of-an-ensemble-of-augmented-image |
Repo | |
Framework | |
Explainable Deterministic MDPs
Title | Explainable Deterministic MDPs |
Authors | Josh Bertram, Peng Wei |
Abstract | We present a method for a certain class of Markov Decision Processes (MDPs) that can relate the optimal policy back to one or more reward sources in the environment. For a given initial state, without fully computing the value function, q-value function, or the optimal policy the algorithm can determine which rewards will and will not be collected, whether a given reward will be collected only once or continuously, and which local maximum within the value function the initial state will ultimately lead to. We demonstrate that the method can be used to map the state space to identify regions that are dominated by one reward source and can fully analyze the state space to explain all actions. We provide a mathematical framework to show how all of this is possible without first computing the optimal policy or value function. |
Tasks | |
Published | 2018-06-09 |
URL | http://arxiv.org/abs/1806.03492v1 |
http://arxiv.org/pdf/1806.03492v1.pdf | |
PWC | https://paperswithcode.com/paper/explainable-deterministic-mdps |
Repo | |
Framework | |
Learning to Route Efficiently with End-to-End Feedback: The Value of Networked Structure
Title | Learning to Route Efficiently with End-to-End Feedback: The Value of Networked Structure |
Authors | Ruihao Zhu, Eytan Modiano |
Abstract | We introduce efficient algorithms which achieve nearly optimal regrets for the problem of stochastic online shortest path routing with end-to-end feedback. The setting is a natural application of the combinatorial stochastic bandits problem, a special case of the linear stochastic bandits problem. We show how the difficulties posed by the large scale action set can be overcome by the networked structure of the action set. Our approach presents a novel connection between bandit learning and shortest path algorithms. Our main contribution is an adaptive exploration algorithm with nearly optimal instance-dependent regret for any directed acyclic network. We then modify it so that nearly optimal worst case regret is achieved simultaneously. Driven by the carefully designed Top-Two Comparison (TTC) technique, the algorithms are efficiently implementable. We further conduct extensive numerical experiments to show that our proposed algorithms not only achieve superior regret performances, but also reduce the runtime drastically. |
Tasks | |
Published | 2018-10-24 |
URL | http://arxiv.org/abs/1810.10637v2 |
http://arxiv.org/pdf/1810.10637v2.pdf | |
PWC | https://paperswithcode.com/paper/learning-to-route-efficiently-with-end-to-end |
Repo | |
Framework | |
Natural Language Person Search Using Deep Reinforcement Learning
Title | Natural Language Person Search Using Deep Reinforcement Learning |
Authors | Ankit Shah, Tyler Vuong |
Abstract | Recent success in deep reinforcement learning is having an agent learn how to play Go and beat the world champion without any prior knowledge of the game. In that task, the agent has to make a decision on what action to take based on the positions of the pieces. Person Search is recently explored using natural language based text description of images for video surveillance applications (S.Li et.al). We see (Fu.et al) provides an end to end approach for object-based retrieval using deep reinforcement learning without constraints placed on which objects are being detected. However, we believe for real-world applications such as person search defining specific constraints which identify a person as opposed to starting with a general object detection will have benefits in terms of performance and computational resources required. In our task, Deep reinforcement learning would localize the person in an image by reshaping the sizes of the bounding boxes. Deep Reinforcement learning with appropriate constraints would look only for the relevant person in the image as opposed to an unconstrained approach where each individual objects in the image are ranked. For person search, the agent is trying to form a tight bounding box around the person in the image who matches the description. The bounding box is initialized to the full image and at each time step, the agent makes a decision on how to change the current bounding box so that it has a tighter bound around the person based on the description of the person and the pixel values of the current bounding box. After the agent takes an action, it will be given a reward based on the Intersection over Union (IoU) of the current bounding box and the ground truth box. Once the agent believes that the bounding box is covering the person, it will indicate that the person is found. |
Tasks | Object Detection, Person Search |
Published | 2018-09-02 |
URL | http://arxiv.org/abs/1809.00365v1 |
http://arxiv.org/pdf/1809.00365v1.pdf | |
PWC | https://paperswithcode.com/paper/natural-language-person-search-using-deep |
Repo | |
Framework | |
Reliable Uncertain Evidence Modeling in Bayesian Networks by Credal Networks
Title | Reliable Uncertain Evidence Modeling in Bayesian Networks by Credal Networks |
Authors | Sabina Marchetti, Alessandro Antonucci |
Abstract | A reliable modeling of uncertain evidence in Bayesian networks based on a set-valued quantification is proposed. Both soft and virtual evidences are considered. We show that evidence propagation in this setup can be reduced to standard updating in an augmented credal network, equivalent to a set of consistent Bayesian networks. A characterization of the computational complexity for this task is derived together with an efficient exact procedure for a subclass of instances. In the case of multiple uncertain evidences over the same variable, the proposed procedure can provide a set-valued version of the geometric approach to opinion pooling. |
Tasks | |
Published | 2018-02-15 |
URL | http://arxiv.org/abs/1802.05639v1 |
http://arxiv.org/pdf/1802.05639v1.pdf | |
PWC | https://paperswithcode.com/paper/reliable-uncertain-evidence-modeling-in |
Repo | |
Framework | |
Novel digital tissue phenotypic signatures of distant metastasis in colorectal cancer
Title | Novel digital tissue phenotypic signatures of distant metastasis in colorectal cancer |
Authors | Korsuk Sirinukunwattana, David Snead, David Epstein, Zia Aftab, Imaad Mujeeb, Yee Wah Tsang, Ian Cree, Nasir Rajpoot |
Abstract | Distant metastasis is the major cause of death in colorectal cancer (CRC). Patients at high risk of developing distant metastasis could benefit from appropriate adjuvant and follow-up treatments if stratified accurately at an early stage of the disease. Studies have increasingly recognized the role of diverse cellular components within the tumor microenvironment in the development and progression of CRC tumors. In this paper, we show that a new method of automated analysis of digitized images from colorectal cancer tissue slides can provide important estimates of distant metastasis-free survival (DMFS, the time before metastasis is first observed) on the basis of details of the microenvironment. Specifically, we determine what cell types are found in the vicinity of other cell types, and in what numbers, rather than concentrating exclusively on the cancerous cells. We then extract novel tissue phenotypic signatures using statistical measurements about tissue composition. Such signatures can underpin clinical decisions about the advisability of various types of adjuvant therapy. |
Tasks | |
Published | 2018-01-23 |
URL | http://arxiv.org/abs/1801.07451v1 |
http://arxiv.org/pdf/1801.07451v1.pdf | |
PWC | https://paperswithcode.com/paper/novel-digital-tissue-phenotypic-signatures-of |
Repo | |
Framework | |
Rethinking Numerical Representations for Deep Neural Networks
Title | Rethinking Numerical Representations for Deep Neural Networks |
Authors | Parker Hill, Babak Zamirai, Shengshuo Lu, Yu-Wei Chao, Michael Laurenzano, Mehrzad Samadi, Marios Papaefthymiou, Scott Mahlke, Thomas Wenisch, Jia Deng, Lingjia Tang, Jason Mars |
Abstract | With ever-increasing computational demand for deep learning, it is critical to investigate the implications of the numeric representation and precision of DNN model weights and activations on computational efficiency. In this work, we explore unconventional narrow-precision floating-point representations as it relates to inference accuracy and efficiency to steer the improved design of future DNN platforms. We show that inference using these custom numeric representations on production-grade DNNs, including GoogLeNet and VGG, achieves an average speedup of 7.6x with less than 1% degradation in inference accuracy relative to a state-of-the-art baseline platform representing the most sophisticated hardware using single-precision floating point. To facilitate the use of such customized precision, we also present a novel technique that drastically reduces the time required to derive the optimal precision configuration. |
Tasks | |
Published | 2018-08-07 |
URL | http://arxiv.org/abs/1808.02513v1 |
http://arxiv.org/pdf/1808.02513v1.pdf | |
PWC | https://paperswithcode.com/paper/rethinking-numerical-representations-for-deep |
Repo | |
Framework | |
Keep and Learn: Continual Learning by Constraining the Latent Space for Knowledge Preservation in Neural Networks
Title | Keep and Learn: Continual Learning by Constraining the Latent Space for Knowledge Preservation in Neural Networks |
Authors | Hyo-Eun Kim, Seungwook Kim, Jaehwan Lee |
Abstract | Data is one of the most important factors in machine learning. However, even if we have high-quality data, there is a situation in which access to the data is restricted. For example, access to the medical data from outside is strictly limited due to the privacy issues. In this case, we have to learn a model sequentially only with the data accessible in the corresponding stage. In this work, we propose a new method for preserving learned knowledge by modeling the high-level feature space and the output space to be mutually informative, and constraining feature vectors to lie in the modeled space during training. The proposed method is easy to implement as it can be applied by simply adding a reconstruction loss to an objective function. We evaluate the proposed method on CIFAR-10/100 and a chest X-ray dataset, and show benefits in terms of knowledge preservation compared to previous approaches. |
Tasks | Continual Learning |
Published | 2018-05-28 |
URL | http://arxiv.org/abs/1805.10784v1 |
http://arxiv.org/pdf/1805.10784v1.pdf | |
PWC | https://paperswithcode.com/paper/keep-and-learn-continual-learning-by |
Repo | |
Framework | |