Paper Group ANR 96
Exploring High-Dimensional Structure via Axis-Aligned Decomposition of Linear Projections. Probabilistic Graphical Models for Credibility Analysis in Evolving Online Communities. Exploration of object recognition from 3D point cloud. Pseudorehearsal in actor-critic agents. Knowledge Transfer for Out-of-Knowledge-Base Entities: A Graph Neural Networ …
Exploring High-Dimensional Structure via Axis-Aligned Decomposition of Linear Projections
| Title | Exploring High-Dimensional Structure via Axis-Aligned Decomposition of Linear Projections |
| Authors | Jayaraman J. Thiagarajan, Shusen Liu, Karthikeyan Natesan Ramamurthy, Peer-Timo Bremer |
| Abstract | Two-dimensional embeddings remain the dominant approach to visualize high dimensional data. The choice of embeddings ranges from highly non-linear ones, which can capture complex relationships but are difficult to interpret quantitatively, to axis-aligned projections, which are easy to interpret but are limited to bivariate relationships. Linear project can be considered as a compromise between complexity and interpretability, as they allow explicit axes labels, yet provide significantly more degrees of freedom compared to axis-aligned projections. Nevertheless, interpreting the axes directions, which are linear combinations often with many non-trivial components, remains difficult. To address this problem we introduce a structure aware decomposition of (multiple) linear projections into sparse sets of axis aligned projections, which jointly capture all information of the original linear ones. In particular, we use tools from Dempster-Shafer theory to formally define how relevant a given axis aligned project is to explain the neighborhood relations displayed in some linear projection. Furthermore, we introduce a new approach to discover a diverse set of high quality linear projections and show that in practice the information of $k$ linear projections is often jointly encoded in $\sim k$ axis aligned plots. We have integrated these ideas into an interactive visualization system that allows users to jointly browse both linear projections and their axis aligned representatives. Using a number of case studies we show how the resulting plots lead to more intuitive visualizations and new insight. |
| Tasks | |
| Published | 2017-12-19 |
| URL | http://arxiv.org/abs/1712.07106v2 |
| http://arxiv.org/pdf/1712.07106v2.pdf | |
| PWC | https://paperswithcode.com/paper/exploring-high-dimensional-structure-via-axis |
| Repo | |
| Framework | |
Probabilistic Graphical Models for Credibility Analysis in Evolving Online Communities
| Title | Probabilistic Graphical Models for Credibility Analysis in Evolving Online Communities |
| Authors | Subhabrata Mukherjee |
| Abstract | One of the major hurdles preventing the full exploitation of information from online communities is the widespread concern regarding the quality and credibility of user-contributed content. Prior works in this domain operate on a static snapshot of the community, making strong assumptions about the structure of the data (e.g., relational tables), or consider only shallow features for text classification. To address the above limitations, we propose probabilistic graphical models that can leverage the joint interplay between multiple factors in online communities — like user interactions, community dynamics, and textual content — to automatically assess the credibility of user-contributed online content, and the expertise of users and their evolution with user-interpretable explanation. To this end, we devise new models based on Conditional Random Fields for different settings like incorporating partial expert knowledge for semi-supervised learning, and handling discrete labels as well as numeric ratings for fine-grained analysis. This enables applications such as extracting reliable side-effects of drugs from user-contributed posts in healthforums, and identifying credible content in news communities. Online communities are dynamic, as users join and leave, adapt to evolving trends, and mature over time. To capture this dynamics, we propose generative models based on Hidden Markov Model, Latent Dirichlet Allocation, and Brownian Motion to trace the continuous evolution of user expertise and their language model over time. This allows us to identify expert users and credible content jointly over time, improving state-of-the-art recommender systems by explicitly considering the maturity of users. This also enables applications such as identifying helpful product reviews, and detecting fake and anomalous reviews with limited information. |
| Tasks | Language Modelling, Recommendation Systems, Text Classification |
| Published | 2017-07-26 |
| URL | http://arxiv.org/abs/1707.08309v1 |
| http://arxiv.org/pdf/1707.08309v1.pdf | |
| PWC | https://paperswithcode.com/paper/probabilistic-graphical-models-for |
| Repo | |
| Framework | |
Exploration of object recognition from 3D point cloud
| Title | Exploration of object recognition from 3D point cloud |
| Authors | Lin Duan |
| Abstract | We present our latest experiment results of object recognition from 3D point cloud data collected through moving car. |
| Tasks | Object Recognition |
| Published | 2017-07-05 |
| URL | http://arxiv.org/abs/1707.01243v1 |
| http://arxiv.org/pdf/1707.01243v1.pdf | |
| PWC | https://paperswithcode.com/paper/exploration-of-object-recognition-from-3d |
| Repo | |
| Framework | |
Pseudorehearsal in actor-critic agents
| Title | Pseudorehearsal in actor-critic agents |
| Authors | Marochko Vladimir, Leonard Johard, Manuel Mazzara |
| Abstract | Catastrophic forgetting has a serious impact in reinforcement learning, as the data distribution is generally sparse and non-stationary over time. The purpose of this study is to investigate whether pseudorehearsal can increase performance of an actor-critic agent with neural-network based policy selection and function approximation in a pole balancing task and compare different pseudorehearsal approaches. We expect that pseudorehearsal assists learning even in such very simple problems, given proper initialization of the rehearsal parameters. |
| Tasks | |
| Published | 2017-04-17 |
| URL | http://arxiv.org/abs/1704.04912v1 |
| http://arxiv.org/pdf/1704.04912v1.pdf | |
| PWC | https://paperswithcode.com/paper/pseudorehearsal-in-actor-critic-agents |
| Repo | |
| Framework | |
Knowledge Transfer for Out-of-Knowledge-Base Entities: A Graph Neural Network Approach
| Title | Knowledge Transfer for Out-of-Knowledge-Base Entities: A Graph Neural Network Approach |
| Authors | Takuo Hamaguchi, Hidekazu Oiwa, Masashi Shimbo, Yuji Matsumoto |
| Abstract | Knowledge base completion (KBC) aims to predict missing information in a knowledge base.In this paper, we address the out-of-knowledge-base (OOKB) entity problem in KBC:how to answer queries concerning test entities not observed at training time. Existing embedding-based KBC models assume that all test entities are available at training time, making it unclear how to obtain embeddings for new entities without costly retraining. To solve the OOKB entity problem without retraining, we use graph neural networks (Graph-NNs) to compute the embeddings of OOKB entities, exploiting the limited auxiliary knowledge provided at test time.The experimental results show the effectiveness of our proposed model in the OOKB setting.Additionally, in the standard KBC setting in which OOKB entities are not involved, our model achieves state-of-the-art performance on the WordNet dataset. The code and dataset are available at https://github.com/takuo-h/GNN-for-OOKB |
| Tasks | Knowledge Base Completion, Transfer Learning |
| Published | 2017-06-18 |
| URL | http://arxiv.org/abs/1706.05674v2 |
| http://arxiv.org/pdf/1706.05674v2.pdf | |
| PWC | https://paperswithcode.com/paper/knowledge-transfer-for-out-of-knowledge-base |
| Repo | |
| Framework | |
A weighting strategy for Active Shape Models
| Title | A weighting strategy for Active Shape Models |
| Authors | Alma Eguizabal, Peter J. Schreier |
| Abstract | Active Shape Models (ASM) are an iterative segmentation technique to find a landmark-based contour of an object. In each iteration, a least-squares fit of a plausible shape to some detected target landmarks is determined. Finding these targets is a critical step: some landmarks are more reliably detected than others, and some landmarks may not be within the field of view of their detectors. To add robustness while preserving simplicity at the same time, a generalized least-squares approach can be used, where a weighting matrix incorporates reliability information about the landmarks. We propose a strategy to choose this matrix, based on the covariance of empirically determined residuals of the fit. We perform a further step to determine whether the target landmarks are within the range of their detectors. We evaluate our strategy on fluoroscopic X-ray images to segment the femur. We show that our technique outperforms the standard ASM as well as other more heuristic weighted least-squares strategies. |
| Tasks | |
| Published | 2017-07-28 |
| URL | http://arxiv.org/abs/1707.09233v1 |
| http://arxiv.org/pdf/1707.09233v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-weighting-strategy-for-active-shape-models |
| Repo | |
| Framework | |
3D Face Morphable Models “In-the-Wild”
| Title | 3D Face Morphable Models “In-the-Wild” |
| Authors | James Booth, Epameinondas Antonakos, Stylianos Ploumpis, George Trigeorgis, Yannis Panagakis, Stefanos Zafeiriou |
| Abstract | 3D Morphable Models (3DMMs) are powerful statistical models of 3D facial shape and texture, and among the state-of-the-art methods for reconstructing facial shape from single images. With the advent of new 3D sensors, many 3D facial datasets have been collected containing both neutral as well as expressive faces. However, all datasets are captured under controlled conditions. Thus, even though powerful 3D facial shape models can be learnt from such data, it is difficult to build statistical texture models that are sufficient to reconstruct faces captured in unconstrained conditions (“in-the-wild”). In this paper, we propose the first, to the best of our knowledge, “in-the-wild” 3DMM by combining a powerful statistical model of facial shape, which describes both identity and expression, with an “in-the-wild” texture model. We show that the employment of such an “in-the-wild” texture model greatly simplifies the fitting procedure, because there is no need to optimize with regards to the illumination parameters. Furthermore, we propose a new fast algorithm for fitting the 3DMM in arbitrary images. Finally, we have captured the first 3D facial database with relatively unconstrained conditions and report quantitative evaluations with state-of-the-art performance. Complementary qualitative reconstruction results are demonstrated on standard “in-the-wild” facial databases. An open source implementation of our technique is released as part of the Menpo Project. |
| Tasks | 3D Face Reconstruction |
| Published | 2017-01-19 |
| URL | http://arxiv.org/abs/1701.05360v1 |
| http://arxiv.org/pdf/1701.05360v1.pdf | |
| PWC | https://paperswithcode.com/paper/3d-face-morphable-models-in-the-wild |
| Repo | |
| Framework | |
Image Quality Assessment Techniques Show Improved Training and Evaluation of Autoencoder Generative Adversarial Networks
| Title | Image Quality Assessment Techniques Show Improved Training and Evaluation of Autoencoder Generative Adversarial Networks |
| Authors | Michael O. Vertolli, Jim Davies |
| Abstract | We propose a training and evaluation approach for autoencoder Generative Adversarial Networks (GANs), specifically the Boundary Equilibrium Generative Adversarial Network (BEGAN), based on methods from the image quality assessment literature. Our approach explores a multidimensional evaluation criterion that utilizes three distance functions: an $l_1$ score, the Gradient Magnitude Similarity Mean (GMSM) score, and a chrominance score. We show that each of the different distance functions captures a slightly different set of properties in image space and, consequently, requires its own evaluation criterion to properly assess whether the relevant property has been adequately learned. We show that models using the new distance functions are able to produce better images than the original BEGAN model in predicted ways. |
| Tasks | Image Quality Assessment |
| Published | 2017-08-06 |
| URL | http://arxiv.org/abs/1708.02237v1 |
| http://arxiv.org/pdf/1708.02237v1.pdf | |
| PWC | https://paperswithcode.com/paper/image-quality-assessment-techniques-show |
| Repo | |
| Framework | |
Set-to-Set Hashing with Applications in Visual Recognition
| Title | Set-to-Set Hashing with Applications in Visual Recognition |
| Authors | I-Hong Jhuo, Jun Wang |
| Abstract | Visual data, such as an image or a sequence of video frames, is often naturally represented as a point set. In this paper, we consider the fundamental problem of finding a nearest set from a collection of sets, to a query set. This problem has obvious applications in large-scale visual retrieval and recognition, and also in applied fields beyond computer vision. One challenge stands out in solving the problem—set representation and measure of similarity. Particularly, the query set and the sets in dataset collection can have varying cardinalities. The training collection is large enough such that linear scan is impractical. We propose a simple representation scheme that encodes both statistical and structural information of the sets. The derived representations are integrated in a kernel framework for flexible similarity measurement. For the query set process, we adopt a learning-to-hash pipeline that turns the kernel representations into hash bits based on simple learners, using multiple kernel learning. Experiments on two visual retrieval datasets show unambiguously that our set-to-set hashing framework outperforms prior methods that do not take the set-to-set search setting. |
| Tasks | |
| Published | 2017-11-02 |
| URL | https://arxiv.org/abs/1711.00888v2 |
| https://arxiv.org/pdf/1711.00888v2.pdf | |
| PWC | https://paperswithcode.com/paper/set-to-set-hashing-with-applications-in |
| Repo | |
| Framework | |
Structural Feature Selection for Event Logs
| Title | Structural Feature Selection for Event Logs |
| Authors | Markku Hinkka, Teemu Lehto, Keijo Heljanko, Alexander Jung |
| Abstract | We consider the problem of classifying business process instances based on structural features derived from event logs. The main motivation is to provide machine learning based techniques with quick response times for interactive computer assisted root cause analysis. In particular, we create structural features from process mining such as activity and transition occurrence counts, and ordering of activities to be evaluated as potential features for classification. We show that adding such structural features increases the amount of information thus potentially increasing classification accuracy. However, there is an inherent trade-off as using too many features leads to too long run-times for machine learning classification models. One way to improve the machine learning algorithms’ run-time is to only select a small number of features by a feature selection algorithm. However, the run-time required by the feature selection algorithm must also be taken into account. Also, the classification accuracy should not suffer too much from the feature selection. The main contributions of this paper are as follows: First, we propose and compare six different feature selection algorithms by means of an experimental setup comparing their classification accuracy and achievable response times. Second, we discuss the potential use of feature selection results for computer assisted root cause analysis as well as the properties of different types of structural features in the context of feature selection. |
| Tasks | Feature Selection |
| Published | 2017-10-08 |
| URL | http://arxiv.org/abs/1710.02823v2 |
| http://arxiv.org/pdf/1710.02823v2.pdf | |
| PWC | https://paperswithcode.com/paper/structural-feature-selection-for-event-logs |
| Repo | |
| Framework | |
Face Parsing via a Fully-Convolutional Continuous CRF Neural Network
| Title | Face Parsing via a Fully-Convolutional Continuous CRF Neural Network |
| Authors | Lei Zhou, Zhi Liu, Xiangjian He |
| Abstract | In this work, we address the face parsing task with a Fully-Convolutional continuous CRF Neural Network (FC-CNN) architecture. In contrast to previous face parsing methods that apply region-based subnetwork hundreds of times, our FC-CNN is fully convolutional with high segmentation accuracy. To achieve this goal, FC-CNN integrates three subnetworks, a unary network, a pairwise network and a continuous Conditional Random Field (C-CRF) network into a unified framework. The high-level semantic information and low-level details across different convolutional layers are captured by the convolutional and deconvolutional structures in the unary network. The semantic edge context is learnt by the pairwise network branch to construct pixel-wise affinity. Based on a differentiable superpixel pooling layer and a differentiable C-CRF layer, the unary network and pairwise network are combined via a novel continuous CRF network to achieve spatial consistency in both training and test procedure of a deep neural network. Comprehensive evaluations on LFW-PL and HELEN datasets demonstrate that FC-CNN achieves better performance over the other state-of-arts for accurate face labeling on challenging images. |
| Tasks | |
| Published | 2017-08-12 |
| URL | http://arxiv.org/abs/1708.03736v1 |
| http://arxiv.org/pdf/1708.03736v1.pdf | |
| PWC | https://paperswithcode.com/paper/face-parsing-via-a-fully-convolutional |
| Repo | |
| Framework | |
e-QRAQ: A Multi-turn Reasoning Dataset and Simulator with Explanations
| Title | e-QRAQ: A Multi-turn Reasoning Dataset and Simulator with Explanations |
| Authors | Clemens Rosenbaum, Tian Gao, Tim Klinger |
| Abstract | In this paper we present a new dataset and user simulator e-QRAQ (explainable Query, Reason, and Answer Question) which tests an Agent’s ability to read an ambiguous text; ask questions until it can answer a challenge question; and explain the reasoning behind its questions and answer. The User simulator provides the Agent with a short, ambiguous story and a challenge question about the story. The story is ambiguous because some of the entities have been replaced by variables. At each turn the Agent may ask for the value of a variable or try to answer the challenge question. In response the User simulator provides a natural language explanation of why the Agent’s query or answer was useful in narrowing down the set of possible answers, or not. To demonstrate one potential application of the e-QRAQ dataset, we train a new neural architecture based on End-to-End Memory Networks to successfully generate both predictions and partial explanations of its current understanding of the problem. We observe a strong correlation between the quality of the prediction and explanation. |
| Tasks | |
| Published | 2017-08-05 |
| URL | http://arxiv.org/abs/1708.01776v1 |
| http://arxiv.org/pdf/1708.01776v1.pdf | |
| PWC | https://paperswithcode.com/paper/e-qraq-a-multi-turn-reasoning-dataset-and |
| Repo | |
| Framework | |
SafeDrive: A Robust Lane Tracking System for Autonomous and Assisted Driving Under Limited Visibility
| Title | SafeDrive: A Robust Lane Tracking System for Autonomous and Assisted Driving Under Limited Visibility |
| Authors | Junaed Sattar, Jiawei Mo |
| Abstract | We present an approach towards robust lane tracking for assisted and autonomous driving, particularly under poor visibility. Autonomous detection of lane markers improves road safety, and purely visual tracking is desirable for widespread vehicle compatibility and reducing sensor intrusion, cost, and energy consumption. However, visual approaches are often ineffective because of a number of factors, including but not limited to occlusion, poor weather conditions, and paint wear-off. Our method, named SafeDrive, attempts to improve visual lane detection approaches in drastically degraded visual conditions without relying on additional active sensors. In scenarios where visual lane detection algorithms are unable to detect lane markers, the proposed approach uses location information of the vehicle to locate and access alternate imagery of the road and attempts detection on this secondary image. Subsequently, by using a combination of feature-based and pixel-based alignment, an estimated location of the lane marker is found in the current scene. We demonstrate the effectiveness of our system on actual driving data from locations in the United States with Google Street View as the source of alternate imagery. |
| Tasks | Autonomous Driving, Lane Detection, Visual Tracking |
| Published | 2017-01-29 |
| URL | http://arxiv.org/abs/1701.08449v1 |
| http://arxiv.org/pdf/1701.08449v1.pdf | |
| PWC | https://paperswithcode.com/paper/safedrive-a-robust-lane-tracking-system-for |
| Repo | |
| Framework | |
A Convolutional Neural Network for Search Term Detection
| Title | A Convolutional Neural Network for Search Term Detection |
| Authors | Hojjat Salehinejad, Joseph Barfett, Parham Aarabi, Shahrokh Valaee, Errol Colak, Bruce Gray, Tim Dowdell |
| Abstract | Pathfinding in hospitals is challenging for patients, visitors, and even employees. Many people have experienced getting lost due to lack of clear guidance, large footprint of hospitals, and confusing array of hospital wings. In this paper, we propose Halo; An indoor navigation application based on voice-user interaction to help provide directions for users without assistance of a localization system. The main challenge is accurate detection of origin and destination search terms. A custom convolutional neural network (CNN) is proposed to detect origin and destination search terms from transcription of a submitted speech query. The CNN is trained based on a set of queries tailored specifically for hospital and clinic environments. Performance of the proposed model is studied and compared with Levenshtein distance-based word matching. |
| Tasks | |
| Published | 2017-08-07 |
| URL | http://arxiv.org/abs/1708.02238v3 |
| http://arxiv.org/pdf/1708.02238v3.pdf | |
| PWC | https://paperswithcode.com/paper/a-convolutional-neural-network-for-search |
| Repo | |
| Framework | |
Noisy Softmax: Improving the Generalization Ability of DCNN via Postponing the Early Softmax Saturation
| Title | Noisy Softmax: Improving the Generalization Ability of DCNN via Postponing the Early Softmax Saturation |
| Authors | Binghui Chen, Weihong Deng, Junping Du |
| Abstract | Over the past few years, softmax and SGD have become a commonly used component and the default training strategy in CNN frameworks, respectively. However, when optimizing CNNs with SGD, the saturation behavior behind softmax always gives us an illusion of training well and then is omitted. In this paper, we first emphasize that the early saturation behavior of softmax will impede the exploration of SGD, which sometimes is a reason for model converging at a bad local-minima, then propose Noisy Softmax to mitigating this early saturation issue by injecting annealed noise in softmax during each iteration. This operation based on noise injection aims at postponing the early saturation and further bringing continuous gradients propagation so as to significantly encourage SGD solver to be more exploratory and help to find a better local-minima. This paper empirically verifies the superiority of the early softmax desaturation, and our method indeed improves the generalization ability of CNN model by regularization. We experimentally find that this early desaturation helps optimization in many tasks, yielding state-of-the-art or competitive results on several popular benchmark datasets. |
| Tasks | |
| Published | 2017-08-12 |
| URL | http://arxiv.org/abs/1708.03769v1 |
| http://arxiv.org/pdf/1708.03769v1.pdf | |
| PWC | https://paperswithcode.com/paper/noisy-softmax-improving-the-generalization |
| Repo | |
| Framework | |
