Paper Group ANR 133
Private PAC learning implies finite Littlestone dimension. Narrow Artificial Intelligence with Machine Learning for Real-Time Estimation of a Mobile Agents Location Using Hidden Markov Models. HybridNet: Classification and Reconstruction Cooperation for Semi-Supervised Learning. The Focus-Aspect-Polarity Model for Predicting Subjective Noun Attribu …
Private PAC learning implies finite Littlestone dimension
Title | Private PAC learning implies finite Littlestone dimension |
Authors | Noga Alon, Roi Livni, Maryanthe Malliaris, Shay Moran |
Abstract | We show that every approximately differentially private learning algorithm (possibly improper) for a class $H$ with Littlestone dimension~$d$ requires $\Omega\bigl(\log^*(d)\bigr)$ examples. As a corollary it follows that the class of thresholds over $\mathbb{N}$ can not be learned in a private manner; this resolves open question due to [Bun et al., 2015, Feldman and Xiao, 2015]. We leave as an open question whether every class with a finite Littlestone dimension can be learned by an approximately differentially private algorithm. |
Tasks | |
Published | 2018-06-04 |
URL | http://arxiv.org/abs/1806.00949v3 |
http://arxiv.org/pdf/1806.00949v3.pdf | |
PWC | https://paperswithcode.com/paper/private-pac-learning-implies-finite |
Repo | |
Framework | |
Narrow Artificial Intelligence with Machine Learning for Real-Time Estimation of a Mobile Agents Location Using Hidden Markov Models
Title | Narrow Artificial Intelligence with Machine Learning for Real-Time Estimation of a Mobile Agents Location Using Hidden Markov Models |
Authors | Cédric Beaulac, Fabrice Larribe |
Abstract | We propose to use a supervised machine learning technique to track the location of a mobile agent in real time. Hidden Markov Models are used to build artificial intelligence that estimates the unknown position of a mobile target moving in a defined environment. This narrow artificial intelligence performs two distinct tasks. First, it provides real-time estimation of the mobile agent’s position using the forward algorithm. Second, it uses the Baum-Welch algorithm as a statistical learning tool to gain knowledge of the mobile target. Finally, an experimental environment is proposed, namely a video game that we use to test our artificial intelligence. We present statistical and graphical results to illustrate the efficiency of our method. |
Tasks | |
Published | 2018-02-09 |
URL | http://arxiv.org/abs/1802.03417v1 |
http://arxiv.org/pdf/1802.03417v1.pdf | |
PWC | https://paperswithcode.com/paper/narrow-artificial-intelligence-with-machine |
Repo | |
Framework | |
HybridNet: Classification and Reconstruction Cooperation for Semi-Supervised Learning
Title | HybridNet: Classification and Reconstruction Cooperation for Semi-Supervised Learning |
Authors | Thomas Robert, Nicolas Thome, Matthieu Cord |
Abstract | In this paper, we introduce a new model for leveraging unlabeled data to improve generalization performances of image classifiers: a two-branch encoder-decoder architecture called HybridNet. The first branch receives supervision signal and is dedicated to the extraction of invariant class-related representations. The second branch is fully unsupervised and dedicated to model information discarded by the first branch to reconstruct input data. To further support the expected behavior of our model, we propose an original training objective. It favors stability in the discriminative branch and complementarity between the learned representations in the two branches. HybridNet is able to outperform state-of-the-art results on CIFAR-10, SVHN and STL-10 in various semi-supervised settings. In addition, visualizations and ablation studies validate our contributions and the behavior of the model on both CIFAR-10 and STL-10 datasets. |
Tasks | |
Published | 2018-07-30 |
URL | http://arxiv.org/abs/1807.11407v1 |
http://arxiv.org/pdf/1807.11407v1.pdf | |
PWC | https://paperswithcode.com/paper/hybridnet-classification-and-reconstruction |
Repo | |
Framework | |
The Focus-Aspect-Polarity Model for Predicting Subjective Noun Attributes in Images
Title | The Focus-Aspect-Polarity Model for Predicting Subjective Noun Attributes in Images |
Authors | Tushar Karayil, Philipp Blandfort, Jörn Hees, Andreas Dengel |
Abstract | Subjective visual interpretation is a challenging yet important topic in computer vision. Many approaches reduce this problem to the prediction of adjective- or attribute-labels from images. However, most of these do not take attribute semantics into account, or only process the image in a holistic manner. Furthermore, there is a lack of relevant datasets with fine-grained subjective labels. In this paper, we propose the Focus-Aspect-Polarity model to structure the process of capturing subjectivity in image processing, and introduce a novel dataset following this way of modeling. We run experiments on this dataset to compare several deep learning methods and find that incorporating context information based on tensor multiplication in several cases outperforms the default way of information fusion (concatenation). |
Tasks | |
Published | 2018-10-15 |
URL | http://arxiv.org/abs/1810.06219v1 |
http://arxiv.org/pdf/1810.06219v1.pdf | |
PWC | https://paperswithcode.com/paper/the-focus-aspect-polarity-model-for |
Repo | |
Framework | |
Continuous-time Intensity Estimation Using Event Cameras
Title | Continuous-time Intensity Estimation Using Event Cameras |
Authors | Cedric Scheerlinck, Nick Barnes, Robert Mahony |
Abstract | Event cameras provide asynchronous, data-driven measurements of local temporal contrast over a large dynamic range with extremely high temporal resolution. Conventional cameras capture low-frequency reference intensity information. These two sensor modalities provide complementary information. We propose a computationally efficient, asynchronous filter that continuously fuses image frames and events into a single high-temporal-resolution, high-dynamic-range image state. In absence of conventional image frames, the filter can be run on events only. We present experimental results on high-speed, high-dynamic-range sequences, as well as on new ground truth datasets we generate to demonstrate the proposed algorithm outperforms existing state-of-the-art methods. |
Tasks | |
Published | 2018-11-01 |
URL | http://arxiv.org/abs/1811.00386v1 |
http://arxiv.org/pdf/1811.00386v1.pdf | |
PWC | https://paperswithcode.com/paper/continuous-time-intensity-estimation-using |
Repo | |
Framework | |
VideoKifu, or the automatic transcription of a Go game
Title | VideoKifu, or the automatic transcription of a Go game |
Authors | Mario Corsolini, Andrea Carta |
Abstract | In two previous papers [arXiv:1508.03269, arXiv:1701.05419] we described the techniques we employed for reconstructing the whole move sequence of a Go game. That task was at first accomplished by means of a series of photographs, manually shot, as explained during the scientific conference held within the LIX European Go Congress (Liberec, CZ). The photographs were subsequently replaced by a possibly unattended video live stream (provided by webcams, videocameras, smartphones and so on) or, were the live stream not available, by means of a pre-recorded video of the game itself, on condition that the goban and the stones were clearly visible more often than not. As we hinted in the latter paper, in the last two years we have improved both the algorithms employed for reconstructing the grid and detecting the stones, making extensive usage of the multicore capabilities offered by modern CPUs. Those capabilities prompted us to develop some asynchronous routines, capable of double-checking the position of the grid and the number and colour of any stone previously detected, in order to get rid of minor errors possibly occurred during the main analysis, and that may pass undetected especially in the course of an unattended live streaming. Those routines will be described in details, as they address some problems that are of general interest when reconstructing the move sequence, for example what to do when large movements of the whole goban occur (deliberate or not) and how to deal with captures of dead stones $-$ that could be wrongly detected and recorded as “fresh” moves if not promptly removed. |
Tasks | |
Published | 2018-07-04 |
URL | http://arxiv.org/abs/1807.01577v1 |
http://arxiv.org/pdf/1807.01577v1.pdf | |
PWC | https://paperswithcode.com/paper/videokifu-or-the-automatic-transcription-of-a |
Repo | |
Framework | |
RAM: A Region-Aware Deep Model for Vehicle Re-Identification
Title | RAM: A Region-Aware Deep Model for Vehicle Re-Identification |
Authors | Xiaobin Liu, Shiliang Zhang, Qingming Huang, Wen Gao |
Abstract | Previous works on vehicle Re-ID mainly focus on extracting global features and learning distance metrics. Because some vehicles commonly share same model and maker, it is hard to distinguish them based on their global appearances. Compared with the global appearance, local regions such as decorations and inspection stickers attached to the windshield, may be more distinctive for vehicle Re-ID. To embed the detailed visual cues in those local regions, we propose a Region-Aware deep Model (RAM). Specifically, in addition to extracting global features, RAM also extracts features from a series of local regions. As each local region conveys more distinctive visual cues, RAM encourages the deep model to learn discriminative features. We also introduce a novel learning algorithm to jointly use vehicle IDs, types/models, and colors to train the RAM. This strategy fuses more cues for training and results in more discriminative global and regional features. We evaluate our methods on two large-scale vehicle Re-ID datasets, i.e., VeRi and VehicleID. Experimental results show our methods achieve promising performance in comparison with recent works. |
Tasks | Vehicle Re-Identification |
Published | 2018-06-25 |
URL | http://arxiv.org/abs/1806.09283v1 |
http://arxiv.org/pdf/1806.09283v1.pdf | |
PWC | https://paperswithcode.com/paper/ram-a-region-aware-deep-model-for-vehicle-re |
Repo | |
Framework | |
Formal Verification of CNN-based Perception Systems
Title | Formal Verification of CNN-based Perception Systems |
Authors | Panagiotis Kouvaros, Alessio Lomuscio |
Abstract | We address the problem of verifying neural-based perception systems implemented by convolutional neural networks. We define a notion of local robustness based on affine and photometric transformations. We show the notion cannot be captured by previously employed notions of robustness. The method proposed is based on reachability analysis for feed-forward neural networks and relies on MILP encodings of both the CNNs and transformations under question. We present an implementation and discuss the experimental results obtained for a CNN trained from the MNIST data set. |
Tasks | |
Published | 2018-11-28 |
URL | http://arxiv.org/abs/1811.11373v1 |
http://arxiv.org/pdf/1811.11373v1.pdf | |
PWC | https://paperswithcode.com/paper/formal-verification-of-cnn-based-perception |
Repo | |
Framework | |
Multimodal feature fusion for CNN-based gait recognition: an empirical comparison
Title | Multimodal feature fusion for CNN-based gait recognition: an empirical comparison |
Authors | Francisco Manuel Castro, Manuel Jesús Marín-Jiménez, Nicolás Guil, Nicolás Pérez de la Blanca |
Abstract | People identification in video based on the way they walk (i.e. gait) is a relevant task in computer vision using a non-invasive approach. Standard and current approaches typically derive gait signatures from sequences of binary energy maps of subjects extracted from images, but this process introduces a large amount of non-stationary noise, thus, conditioning their efficacy. In contrast, in this paper we focus on the raw pixels, or simple functions derived from them, letting advanced learning techniques to extract relevant features. Therefore, we present a comparative study of different Convolutional Neural Network (CNN) architectures by using three different modalities (i.e. gray pixels, optical flow channels and depth maps) on two widely-adopted and challenging datasets: TUM-GAID and CASIA-B. In addition, we perform a comparative study between different early and late fusion methods used to combine the information obtained from each kind of modalities. Our experimental results suggest that (i) the raw pixel values represent a competitive input modality, compared to the traditional state-of-the-art silhouette-based features (e.g. GEI), since equivalent or better results are obtained; (ii) the fusion of the raw pixel information with information from optical flow and depth maps allows to obtain state-of-the-art results on the gait recognition task with an image resolution several times smaller than the previously reported results; and, (iii) the selection and the design of the CNN architecture are critical points that can make a difference between state-of-the-art results or poor ones. |
Tasks | Gait Recognition, Optical Flow Estimation |
Published | 2018-06-19 |
URL | https://arxiv.org/abs/1806.07753v2 |
https://arxiv.org/pdf/1806.07753v2.pdf | |
PWC | https://paperswithcode.com/paper/multimodal-feature-fusion-for-cnn-based-gait |
Repo | |
Framework | |
Precision Sugarcane Monitoring Using SVM Classifier
Title | Precision Sugarcane Monitoring Using SVM Classifier |
Authors | Sachin Kumar, Sumita Mishra, Pooja Khanna, Pragya |
Abstract | India is agriculture based economy and sugarcane is one of the major crops produced in northern India. Productivity of sugarcane decreases due to inappropriate soil conditions and infections caused by various types of diseases , timely and accurate disease diagnosis, plays an important role towards optimizing crop yield. This paper presents a system model for monitoring of sugarcane crop, the proposed model continuously monitor parameters (temperature, humidity and moisture) responsible for healthy growth of the crop in addition KNN clustering along with SVM classifier is utilized for infection identification if any through images obtained at regular intervals. The data has been transmitted wirelessly from the site to the control unit. Model achieves an accuracy of 96% on a sample of 200 images, the model was tested at Lolai, near Malhaur, Gomti Nagar Extension. |
Tasks | |
Published | 2018-03-26 |
URL | http://arxiv.org/abs/1803.09413v1 |
http://arxiv.org/pdf/1803.09413v1.pdf | |
PWC | https://paperswithcode.com/paper/precision-sugarcane-monitoring-using-svm |
Repo | |
Framework | |
Time Reversal as Self-Supervision
Title | Time Reversal as Self-Supervision |
Authors | Suraj Nair, Mohammad Babaeizadeh, Chelsea Finn, Sergey Levine, Vikash Kumar |
Abstract | A longstanding challenge in robot learning for manipulation tasks has been the ability to generalize to varying initial conditions, diverse objects, and changing objectives. Learning based approaches have shown promise in producing robust policies, but require heavy supervision to efficiently learn precise control, especially from visual inputs. We propose a novel self-supervision technique that uses time-reversal to learn goals and provide a high level plan to reach them. In particular, we introduce the time-reversal model (TRM), a self-supervised model which explores outward from a set of goal states and learns to predict these trajectories in reverse. This provides a high level plan towards goals, allowing us to learn complex manipulation tasks with no demonstrations or exploration at test time. We test our method on the domain of assembly, specifically the mating of tetris-style block pairs. Using our method operating atop visual model predictive control, we are able to assemble tetris blocks on a physical robot using only uncalibrated RGB camera input, and generalize to unseen block pairs. sites.google.com/view/time-reversal |
Tasks | |
Published | 2018-10-02 |
URL | http://arxiv.org/abs/1810.01128v1 |
http://arxiv.org/pdf/1810.01128v1.pdf | |
PWC | https://paperswithcode.com/paper/time-reversal-as-self-supervision |
Repo | |
Framework | |
Examining Deep Learning Architectures for Crime Classification and Prediction
Title | Examining Deep Learning Architectures for Crime Classification and Prediction |
Authors | Panagiotis Stalidis, Theodoros Semertzidis, Petros Daras |
Abstract | In this paper, a detailed study on crime classification and prediction using deep learning architectures is presented. We examine the effectiveness of deep learning algorithms on this domain and provide recommendations for designing and training deep learning systems for predicting crime areas, using open data from police reports. Having as training data time-series of crime types per location, a comparative study of 10 state-of-the-art methods against 3 different deep learning configurations is conducted. In our experiments with five publicly available datasets, we demonstrate that the deep learning-based methods consistently outperform the existing best-performing methods. Moreover, we evaluate the effectiveness of different parameters in the deep learning architectures and give insights for configuring them in order to achieve improved performance in crime classification and finally crime prediction. |
Tasks | Crime Prediction, Time Series |
Published | 2018-12-03 |
URL | http://arxiv.org/abs/1812.00602v1 |
http://arxiv.org/pdf/1812.00602v1.pdf | |
PWC | https://paperswithcode.com/paper/examining-deep-learning-architectures-for |
Repo | |
Framework | |
Forecasting Crime with Deep Learning
Title | Forecasting Crime with Deep Learning |
Authors | Alexander Stec, Diego Klabjan |
Abstract | The objective of this work is to take advantage of deep neural networks in order to make next day crime count predictions in a fine-grain city partition. We make predictions using Chicago and Portland crime data, which is augmented with additional datasets covering weather, census data, and public transportation. The crime counts are broken into 10 bins and our model predicts the most likely bin for a each spatial region at a daily level. We train this data using increasingly complex neural network structures, including variations that are suited to the spatial and temporal aspects of the crime prediction problem. With our best model we are able to predict the correct bin for overall crime count with 75.6% and 65.3% accuracy for Chicago and Portland, respectively. The results show the efficacy of neural networks for the prediction problem and the value of using external datasets in addition to standard crime data. |
Tasks | Crime Prediction |
Published | 2018-06-05 |
URL | http://arxiv.org/abs/1806.01486v1 |
http://arxiv.org/pdf/1806.01486v1.pdf | |
PWC | https://paperswithcode.com/paper/forecasting-crime-with-deep-learning |
Repo | |
Framework | |
Predicting Crime Using Spatial Features
Title | Predicting Crime Using Spatial Features |
Authors | Fateha Khanam Bappee, Amilcar Soares Junior, Stan Matwin |
Abstract | Our study aims to build a machine learning model for crime prediction using geospatial features for different categories of crime. The reverse geocoding technique is applied to retrieve open street map (OSM) spatial data. This study also proposes finding hotpoints extracted from crime hotspots area found by Hierarchical Density-Based Spatial Clustering of Applications with Noise (HDBSCAN). A spatial distance feature is then computed based on the position of different hotpoints for various types of crime and this value is used as a feature for classifiers. We test the engineered features in crime data from Royal Canadian Mounted Police of Halifax, NS. We observed a significant performance improvement in crime prediction using the new generated spatial features. |
Tasks | Crime Prediction |
Published | 2018-03-12 |
URL | http://arxiv.org/abs/1803.04474v1 |
http://arxiv.org/pdf/1803.04474v1.pdf | |
PWC | https://paperswithcode.com/paper/predicting-crime-using-spatial-features |
Repo | |
Framework | |
Multilingual NMT with a language-independent attention bridge
Title | Multilingual NMT with a language-independent attention bridge |
Authors | Raúl Vázquez, Alessandro Raganato, Jörg Tiedemann, Mathias Creutz |
Abstract | In this paper, we propose a multilingual encoder-decoder architecture capable of obtaining multilingual sentence representations by means of incorporating an intermediate {\em attention bridge} that is shared across all languages. That is, we train the model with language-specific encoders and decoders that are connected via self-attention with a shared layer that we call attention bridge. This layer exploits the semantics from each language for performing translation and develops into a language-independent meaning representation that can efficiently be used for transfer learning. We present a new framework for the efficient development of multilingual NMT using this model and scheduled training. We have tested the approach in a systematic way with a multi-parallel data set. We show that the model achieves substantial improvements over strong bilingual models and that it also works well for zero-shot translation, which demonstrates its ability of abstraction and transfer learning. |
Tasks | Transfer Learning |
Published | 2018-11-01 |
URL | http://arxiv.org/abs/1811.00498v1 |
http://arxiv.org/pdf/1811.00498v1.pdf | |
PWC | https://paperswithcode.com/paper/multilingual-nmt-with-a-language-independent |
Repo | |
Framework | |