Paper Group ANR 257
Window detection in aerial texture images of the Berlin 3D CityGML Model. Reachability-based safe learning for optimal control problem. Automatic Assessment of Artistic Quality of Photos. Grounding Perception: A Developmental Approach to Sensorimotor Contingencies. A simple probabilistic deep generative model for learning generalizable disentangled …
Window detection in aerial texture images of the Berlin 3D CityGML Model
| Title | Window detection in aerial texture images of the Berlin 3D CityGML Model |
| Authors | Franziska Lippoldt, Marius Erdt |
| Abstract | This article explores the usage of the state-of-art neural network Mask R-CNN to be used for window detection of texture files from the CityGML model of Berlin. As texture files are very irregular in terms of size, exposure settings and orientation, we use several parameter optimisation methods to improve the precision. Those textures are cropped from aerial photos, which implies that the angle of the facade, the exposure as well as contrast are calibrated towards the mean and not towards the single facade. The analysis of a single texture image with the human eye itself is challenging: A combination of window and facade estimation and perspective analysis is necessary in order to determine the facades and windows. We train and detect bounding boxes and masks from two data sets with image size 128 and 256. We explore various configuration optimisation methods and the relation of the Region Proposal Network, detected ROIs and the mask output. Our final results shows that the we can improve the average precision scores for both data set sizes, yet the initial AP score varies and leads to different resulting scores. |
| Tasks | Window Detection |
| Published | 2018-12-19 |
| URL | http://arxiv.org/abs/1812.08095v1 |
| http://arxiv.org/pdf/1812.08095v1.pdf | |
| PWC | https://paperswithcode.com/paper/window-detection-in-aerial-texture-images-of |
| Repo | |
| Framework | |
Reachability-based safe learning for optimal control problem
| Title | Reachability-based safe learning for optimal control problem |
| Authors | Stanislav Fedorov, Antonio Candelieri |
| Abstract | In this work we seek for an approach to integrate safety in the learning process that relies on a partly known state-space model of the system and regards the unknown dynamics as an additive bounded disturbance. We introduce a framework for safely learning a control strategy for a given system with an additive disturbance. On the basis of the known part of the model, a safe set in which the system can learn safely, the algorithm can choose optimal actions for pursuing the target set as long as the safety-preserving condition is satisfied. After some learning episodes, the disturbance can be updated based on real-world data. To this end, Gaussian Process regression is conducted on the collected disturbance samples. Since the unstable nature of the law of the real world, for example, change of friction or conductivity with the temperature, we expect to have the more robust solution of optimal control problem. For evaluation of approach described above we choose an inverted pendulum as a benchmark model. The proposed algorithm manages to learn a policy that does not violate the pre-specified safety constraints. Observed performance is improved when it was incorporated exploration set up to make sure that an optimal policy is learned everywhere in the safe set. Finally, we outline some promising directions for future research beyond the scope of this paper. |
| Tasks | |
| Published | 2018-11-09 |
| URL | http://arxiv.org/abs/1811.04006v1 |
| http://arxiv.org/pdf/1811.04006v1.pdf | |
| PWC | https://paperswithcode.com/paper/reachability-based-safe-learning-for-optimal |
| Repo | |
| Framework | |
Automatic Assessment of Artistic Quality of Photos
| Title | Automatic Assessment of Artistic Quality of Photos |
| Authors | Ashish Verma, Kranthi Koukuntla, Rohit Varma, Snehasis Mukherjee |
| Abstract | This paper proposes a technique to assess the aesthetic quality of photographs. The goal of the study is to predict whether a given photograph is captured by professional photographers, or by common people, based on a measurement of artistic quality of the photograph. We propose a Multi-Layer-Perceptron based system to analyze some low, mid and high level image features and find their effectiveness to measure artistic quality of the image and produce a measurement of the artistic quality of the image on a scale of 10. We validate the proposed system on a large dataset, containing images downloaded from the internet. The dataset contains some images captured by professional photographers and the rest of the images captured by common people. The proposed measurement of artistic quality of images provides higher value of photo quality for the images captured by professional photographers, compared to the values provided for the other images. |
| Tasks | |
| Published | 2018-04-17 |
| URL | http://arxiv.org/abs/1804.06124v1 |
| http://arxiv.org/pdf/1804.06124v1.pdf | |
| PWC | https://paperswithcode.com/paper/automatic-assessment-of-artistic-quality-of |
| Repo | |
| Framework | |
Grounding Perception: A Developmental Approach to Sensorimotor Contingencies
| Title | Grounding Perception: A Developmental Approach to Sensorimotor Contingencies |
| Authors | Alban Laflaquière, Nikolas Hemion, Michaël Garcia Ortiz, Jean-Christophe Baillie |
| Abstract | Sensorimotor contingency theory offers a promising account of the nature of perception, a topic rarely addressed in the robotics community. We propose a developmental framework to address the problem of the autonomous acquisition of sensorimotor contingencies by a naive robot. While exploring the world, the robot internally encodes contingencies as predictive models that capture the structure they imply in its sensorimotor experience. Three preliminary applications are presented to illustrate our approach to the acquisition of perceptive abilities: discovering the environment, discovering objects, and discovering a visual field. |
| Tasks | |
| Published | 2018-10-03 |
| URL | http://arxiv.org/abs/1810.01870v1 |
| http://arxiv.org/pdf/1810.01870v1.pdf | |
| PWC | https://paperswithcode.com/paper/grounding-perception-a-developmental-approach |
| Repo | |
| Framework | |
A simple probabilistic deep generative model for learning generalizable disentangled representations from grouped data
| Title | A simple probabilistic deep generative model for learning generalizable disentangled representations from grouped data |
| Authors | Haruo Hosoya |
| Abstract | The disentangling problem is to discover multiple complex factors of variations hidden in data. One recent approach is to take a dataset with grouping structure and separately estimate a factor common within a group (content) and a factor specific to each group member (transformation). Notably, this approach can learn to represent a continuous space of contents, which allows for generalization to data with unseen contents. In this study, we aim at cultivating this approach within probabilistic deep generative models. Motivated by technical complication in existing group-based methods, we propose a simpler probabilistic method, called group-contrastive variational autoencoders. Despite its simplicity, our approach achieves reasonable disentanglement with generalizability for three grouped datasets of 3D object images. In comparison with a previous model, although conventional qualitative evaluation shows little difference, our qualitative evaluation using few-shot classification exhibits superior performances for some datasets. We analyze the content representations from different methods and discuss their transformation-dependency and potential performance impacts. |
| Tasks | |
| Published | 2018-09-07 |
| URL | http://arxiv.org/abs/1809.02383v1 |
| http://arxiv.org/pdf/1809.02383v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-simple-probabilistic-deep-generative-model |
| Repo | |
| Framework | |
Asynchronous, Photometric Feature Tracking using Events and Frames
| Title | Asynchronous, Photometric Feature Tracking using Events and Frames |
| Authors | Daniel Gehrig, Henri Rebecq, Guillermo Gallego, Davide Scaramuzza |
| Abstract | We present a method that leverages the complementarity of event cameras and standard cameras to track visual features with low-latency. Event cameras are novel sensors that output pixel-level brightness changes, called “events”. They offer significant advantages over standard cameras, namely a very high dynamic range, no motion blur, and a latency in the order of microseconds. However, because the same scene pattern can produce different events depending on the motion direction, establishing event correspondences across time is challenging. By contrast, standard cameras provide intensity measurements (frames) that do not depend on motion direction. Our method extracts features on frames and subsequently tracks them asynchronously using events, thereby exploiting the best of both types of data: the frames provide a photometric representation that does not depend on motion direction and the events provide low-latency updates. In contrast to previous works, which are based on heuristics, this is the first principled method that uses raw intensity measurements directly, based on a generative event model within a maximum-likelihood framework. As a result, our method produces feature tracks that are both more accurate (subpixel accuracy) and longer than the state of the art, across a wide variety of scenes. |
| Tasks | |
| Published | 2018-07-25 |
| URL | http://arxiv.org/abs/1807.09713v1 |
| http://arxiv.org/pdf/1807.09713v1.pdf | |
| PWC | https://paperswithcode.com/paper/asynchronous-photometric-feature-tracking |
| Repo | |
| Framework | |
Early Prediction of Course Grades: Models and Feature Selection
| Title | Early Prediction of Course Grades: Models and Feature Selection |
| Authors | Hengxuan Li, Collin F. Lynch, Tiffany Barnes |
| Abstract | In this paper, we compare predictive models for students’ final performance in a blended course using a set of generic features collected from the first six weeks of class. These features were extracted from students’ online homework submission logs as well as other online actions. We compare the effectiveness of 5 different ML algorithms (SVMs, Support Vector Regression, Decision Tree, Naive Bayes and K-Nearest Neighbor). We found that SVMs outperform other models and improve when compared to the baseline. This study demonstrates feasible implementations for predictive models that rely on common data from blended courses that can be used to monitor students’ progress and to tailor instruction. |
| Tasks | Feature Selection |
| Published | 2018-12-03 |
| URL | http://arxiv.org/abs/1812.00843v1 |
| http://arxiv.org/pdf/1812.00843v1.pdf | |
| PWC | https://paperswithcode.com/paper/early-prediction-of-course-grades-models-and |
| Repo | |
| Framework | |
A Study of Clustering Techniques and Hierarchical Matrix Formats for Kernel Ridge Regression
| Title | A Study of Clustering Techniques and Hierarchical Matrix Formats for Kernel Ridge Regression |
| Authors | Elizaveta Rebrova, Gustavo Chavez, Yang Liu, Pieter Ghysels, Xiaoye Sherry Li |
| Abstract | We present memory-efficient and scalable algorithms for kernel methods used in machine learning. Using hierarchical matrix approximations for the kernel matrix the memory requirements, the number of floating point operations, and the execution time are drastically reduced compared to standard dense linear algebra routines. We consider both the general $\mathcal{H}$ matrix hierarchical format as well as Hierarchically Semi-Separable (HSS) matrices. Furthermore, we investigate the impact of several preprocessing and clustering techniques on the hierarchical matrix compression. Effective clustering of the input leads to a ten-fold increase in efficiency of the compression. The algorithms are implemented using the STRUMPACK solver library. These results confirm that — with correct tuning of the hyperparameters — classification using kernel ridge regression with the compressed matrix does not lose prediction accuracy compared to the exact — not compressed — kernel matrix and that our approach can be extended to $\mathcal{O}(1M)$ datasets, for which computation with the full kernel matrix becomes prohibitively expensive. We present numerical experiments in a distributed memory environment up to 1,024 processors of the NERSC’s Cori supercomputer using well-known datasets to the machine learning community that range from dimension 8 up to 784. |
| Tasks | |
| Published | 2018-03-27 |
| URL | http://arxiv.org/abs/1803.10274v1 |
| http://arxiv.org/pdf/1803.10274v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-study-of-clustering-techniques-and |
| Repo | |
| Framework | |
Dynamic Visual Analytics for Elicitation Meetings with ELICA
| Title | Dynamic Visual Analytics for Elicitation Meetings with ELICA |
| Authors | Zahra Shakeri Hossein Abad, Munib Rahman, Abdullah Cheema, Vincenzo Gervasi, Didar Zowghi, Ken Barker |
| Abstract | Requirements elicitation can be very challenging in projects that require deep domain knowledge about the system at hand. As analysts have the full control over the elicitation process, their lack of knowledge about the system under study inhibits them from asking related questions and reduces the accuracy of requirements provided by stakeholders. We present ELICA, a generic interactive visual analytics tool to assist analysts during requirements elicitation process. ELICA uses a novel information extraction algorithm based on a combination of Weighted Finite State Transducers (WFSTs) (generative model) and SVMs (discriminative model). ELICA presents the extracted relevant information in an interactive GUI (including zooming, panning, and pinching) that allows analysts to explore which parts of the ongoing conversation (or specification document) match with the extracted information. In this demonstration, we show that ELICA is usable and effective in practice, and is able to extract the related information in real-time. We also demonstrate how carefully designed features in ELICA facilitate the interactive and dynamic process of information extraction. |
| Tasks | |
| Published | 2018-07-10 |
| URL | http://arxiv.org/abs/1807.06076v1 |
| http://arxiv.org/pdf/1807.06076v1.pdf | |
| PWC | https://paperswithcode.com/paper/dynamic-visual-analytics-for-elicitation |
| Repo | |
| Framework | |
Dissecting Contextual Word Embeddings: Architecture and Representation
| Title | Dissecting Contextual Word Embeddings: Architecture and Representation |
| Authors | Matthew E. Peters, Mark Neumann, Luke Zettlemoyer, Wen-tau Yih |
| Abstract | Contextual word representations derived from pre-trained bidirectional language models (biLMs) have recently been shown to provide significant improvements to the state of the art for a wide range of NLP tasks. However, many questions remain as to how and why these models are so effective. In this paper, we present a detailed empirical study of how the choice of neural architecture (e.g. LSTM, CNN, or self attention) influences both end task accuracy and qualitative properties of the representations that are learned. We show there is a tradeoff between speed and accuracy, but all architectures learn high quality contextual representations that outperform word embeddings for four challenging NLP tasks. Additionally, all architectures learn representations that vary with network depth, from exclusively morphological based at the word embedding layer through local syntax based in the lower contextual layers to longer range semantics such coreference at the upper layers. Together, these results suggest that unsupervised biLMs, independent of architecture, are learning much more about the structure of language than previously appreciated. |
| Tasks | Word Embeddings |
| Published | 2018-08-27 |
| URL | http://arxiv.org/abs/1808.08949v2 |
| http://arxiv.org/pdf/1808.08949v2.pdf | |
| PWC | https://paperswithcode.com/paper/dissecting-contextual-word-embeddings |
| Repo | |
| Framework | |
Non-deterministic Behavior of Ranking-based Metrics when Evaluating Embeddings
| Title | Non-deterministic Behavior of Ranking-based Metrics when Evaluating Embeddings |
| Authors | Anguelos Nicolaou, Sounak Dey, Vincent Christlein, Andreas Maier, Dimosthenis Karatzas |
| Abstract | Embedding data into vector spaces is a very popular strategy of pattern recognition methods. When distances between embeddings are quantized, performance metrics become ambiguous. In this paper, we present an analysis of the ambiguity quantized distances introduce and provide bounds on the effect. We demonstrate that it can have a measurable effect in empirical data in state-of-the-art systems. We also approach the phenomenon from a computer security perspective and demonstrate how someone being evaluated by a third party can exploit this ambiguity and greatly outperform a random predictor without even access to the input data. We also suggest a simple solution making the performance metrics, which rely on ranking, totally deterministic and impervious to such exploits. |
| Tasks | |
| Published | 2018-06-19 |
| URL | http://arxiv.org/abs/1806.07171v2 |
| http://arxiv.org/pdf/1806.07171v2.pdf | |
| PWC | https://paperswithcode.com/paper/non-deterministic-behavior-of-ranking-based |
| Repo | |
| Framework | |
Sometimes You Want to Go Where Everybody Knows your Name
| Title | Sometimes You Want to Go Where Everybody Knows your Name |
| Authors | Reuben Brasher, Nat Roth, Justin Wagle |
| Abstract | We introduce a new metric for measuring how well a model personalizes to a user’s specific preferences. We define personalization as a weighting between performance on user specific data and performance on a more general global dataset that represents many different users. This global term serves as a form of regularization that forces us to not overfit to individual users who have small amounts of data. In order to protect user privacy, we add the constraint that we may not centralize or share user data. We also contribute a simple experiment in which we simulate classifying sentiment for users with very distinct vocabularies. This experiment functions as an example of the tension between doing well globally on all users, and doing well on any specific individual user. It also provides a concrete example of how to employ our new metric to help reason about and resolve this tension. We hope this work can help frame and ground future work into personalization. |
| Tasks | |
| Published | 2018-01-30 |
| URL | http://arxiv.org/abs/1801.10182v1 |
| http://arxiv.org/pdf/1801.10182v1.pdf | |
| PWC | https://paperswithcode.com/paper/sometimes-you-want-to-go-where-everybody |
| Repo | |
| Framework | |
A Coarse-to-fine Deep Convolutional Neural Network Framework for Frame Duplication Detection and Localization in Forged Videos
| Title | A Coarse-to-fine Deep Convolutional Neural Network Framework for Frame Duplication Detection and Localization in Forged Videos |
| Authors | Chengjiang Long, Arslan Basharat, Anthony Hoogs |
| Abstract | Videos can be manipulated by duplicating a sequence of consecutive frames with the goal of concealing or imitating a specific content in the same video. In this paper, we propose a novel coarse-to-fine framework based on deep Convolutional Neural Networks to automatically detect and localize such frame duplication. First, an I3D network finds coarse-level matches between candidate duplicated frame sequences and the corresponding selected original frame sequences. Then a Siamese network based on ResNet architecture identifies fine-level correspondences between an individual duplicated frame and the corresponding selected frame. We also propose a robust statistical approach to compute a video-level score indicating the likelihood of manipulation or forgery. Additionally, for providing manipulation localization information we develop an inconsistency detector based on the I3D network to distinguish the duplicated frames from the selected original frames. Quantified evaluation on two challenging video forgery datasets clearly demonstrates that this approach performs significantly better than four recent state-of-the-art methods. |
| Tasks | Frame Duplication Detection, Localization In Video Forgery |
| Published | 2018-11-27 |
| URL | https://arxiv.org/abs/1811.10762v2 |
| https://arxiv.org/pdf/1811.10762v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-coarse-to-fine-deep-convolutional-neural |
| Repo | |
| Framework | |
Being curious about the answers to questions: novelty search with learned attention
| Title | Being curious about the answers to questions: novelty search with learned attention |
| Authors | Nicholas Guttenberg, Martin Biehl, Nathaniel Virgo, Ryota Kanai |
| Abstract | We investigate the use of attentional neural network layers in order to learn a behavior characterization' which can be used to drive novelty search and curiosity-based policies. The space is structured towards answering a particular distribution of questions, which are used in a supervised way to train the attentional neural network. We find that in a 2d exploration task, the structure of the space successfully encodes local sensory-motor contingencies such that even a greedy local do the most novel action’ policy with no reinforcement learning or evolution can explore the space quickly. We also apply this to a high/low number guessing game task, and find that guessing according to the learned attention profile performs active inference and can discover the correct number more quickly than an exact but passive approach. |
| Tasks | |
| Published | 2018-06-01 |
| URL | http://arxiv.org/abs/1806.00201v1 |
| http://arxiv.org/pdf/1806.00201v1.pdf | |
| PWC | https://paperswithcode.com/paper/being-curious-about-the-answers-to-questions |
| Repo | |
| Framework | |
GESF: A Universal Discriminative Mapping Mechanism for Graph Representation Learning
| Title | GESF: A Universal Discriminative Mapping Mechanism for Graph Representation Learning |
| Authors | Shupeng Gui, Xiangliang Zhang, Shuang Qiu, Mingrui Wu, Jieping Ye, Ji Liu |
| Abstract | Graph embedding is a central problem in social network analysis and many other applications, aiming to learn the vector representation for each node. While most existing approaches need to specify the neighborhood and the dependence form to the neighborhood, which may significantly degrades the flexibility of representation, we propose a novel graph node embedding method (namely GESF) via the set function technique. Our method can 1) learn an arbitrary form of representation function from neighborhood, 2) automatically decide the significance of neighbors at different distances, and 3) be applied to heterogeneous graph embedding, which may contain multiple types of nodes. Theoretical guarantee for the representation capability of our method has been proved for general homogeneous and heterogeneous graphs and evaluation results on benchmark data sets show that the proposed GESF outperforms the state-of-the-art approaches on producing node vectors for classification tasks. |
| Tasks | Graph Embedding, Graph Representation Learning, Representation Learning |
| Published | 2018-05-28 |
| URL | http://arxiv.org/abs/1805.11182v3 |
| http://arxiv.org/pdf/1805.11182v3.pdf | |
| PWC | https://paperswithcode.com/paper/gesf-a-universal-discriminative-mapping |
| Repo | |
| Framework | |
