Paper Group ANR 1048
MCScript2.0: A Machine Comprehension Corpus Focused on Script Events and Participants. Residual Networks as Nonlinear Systems: Stability Analysis using Linearization. Multi-Element Long Distance Dependencies: Using SPk Languages to Explore the Characteristics of Long-Distance Dependencies. An Elo-based rating system for TopCoder SRM. Adversarial Tr …
MCScript2.0: A Machine Comprehension Corpus Focused on Script Events and Participants
| Title | MCScript2.0: A Machine Comprehension Corpus Focused on Script Events and Participants |
| Authors | Simon Ostermann, Michael Roth, Manfred Pinkal |
| Abstract | We introduce MCScript2.0, a machine comprehension corpus for the end-to-end evaluation of script knowledge. MCScript2.0 contains approx. 20,000 questions on approx. 3,500 texts, crowdsourced based on a new collection process that results in challenging questions. Half of the questions cannot be answered from the reading texts, but require the use of commonsense and, in particular, script knowledge. We give a thorough analysis of our corpus and show that while the task is not challenging to humans, existing machine comprehension models fail to perform well on the data, even if they make use of a commonsense knowledge base. The dataset is available at http://www.sfb1102.uni-saarland.de/?page_id=2582 |
| Tasks | Reading Comprehension |
| Published | 2019-05-23 |
| URL | https://arxiv.org/abs/1905.09531v2 |
| https://arxiv.org/pdf/1905.09531v2.pdf | |
| PWC | https://paperswithcode.com/paper/mcscript20-a-machine-comprehension-corpus |
| Repo | |
| Framework | |
Residual Networks as Nonlinear Systems: Stability Analysis using Linearization
| Title | Residual Networks as Nonlinear Systems: Stability Analysis using Linearization |
| Authors | Kai Rothauge, Zhewei Yao, Zixi Hu, Michael W. Mahoney |
| Abstract | We regard pre-trained residual networks (ResNets) as nonlinear systems and use linearization, a common method used in the qualitative analysis of nonlinear systems, to understand the behavior of the networks under small perturbations of the input images. We work with ResNet-56 and ResNet-110 trained on the CIFAR-10 data set. We linearize these networks at the level of residual units and network stages, and the singular value decomposition is used in the stability analysis of these components. It is found that most of the singular values of the linearizations of residual units are 1 and, in spite of the fact that the linearizations depend directly on the activation maps, the singular values differ only slightly for different input images. However, adjusting the scaling of the skip connection or the values of the weights in a residual unit has a significant impact on the singular value distributions. Inspection of how random and adversarial perturbations of input images propagate through the network reveals that there is a dramatic jump in the magnitude of adversarial perturbations towards the end of the final stage of the network that is not present in the case of random perturbations. We attempt to gain a better understanding of this phenomenon by projecting the perturbations onto singular vectors of the linearizations of the residual units. |
| Tasks | |
| Published | 2019-05-31 |
| URL | https://arxiv.org/abs/1905.13386v1 |
| https://arxiv.org/pdf/1905.13386v1.pdf | |
| PWC | https://paperswithcode.com/paper/residual-networks-as-nonlinear-systems |
| Repo | |
| Framework | |
Multi-Element Long Distance Dependencies: Using SPk Languages to Explore the Characteristics of Long-Distance Dependencies
| Title | Multi-Element Long Distance Dependencies: Using SPk Languages to Explore the Characteristics of Long-Distance Dependencies |
| Authors | Abhijit Mahalunkar, John D. Kelleher |
| Abstract | In order to successfully model Long Distance Dependencies (LDDs) it is necessary to understand the full-range of the characteristics of the LDDs exhibited in a target dataset. In this paper, we use Strictly k-Piecewise languages to generate datasets with various properties. We then compute the characteristics of the LDDs in these datasets using mutual information and analyze the impact of factors such as (i) k, (ii) length of LDDs, (iii) vocabulary size, (iv) forbidden subsequences, and (v) dataset size. This analysis reveal that the number of interacting elements in a dependency is an important characteristic of LDDs. This leads us to the challenge of modelling multi-element long-distance dependencies. Our results suggest that attention mechanisms in neural networks may aide in modeling datasets with multi-element long-distance dependencies. However, we conclude that there is a need to develop more efficient attention mechanisms to address this issue. |
| Tasks | |
| Published | 2019-07-13 |
| URL | https://arxiv.org/abs/1907.06048v1 |
| https://arxiv.org/pdf/1907.06048v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-element-long-distance-dependencies |
| Repo | |
| Framework | |
An Elo-based rating system for TopCoder SRM
| Title | An Elo-based rating system for TopCoder SRM |
| Authors | Fred Batty, Dmitry Kamenetsky |
| Abstract | We present an Elo-based rating system for programming contests. We justify a definition of performance using the logarithm of a player’s rank. We apply the definition to rating TopCoder SRM. We improve the accuracy, guided by experimental results. We compare results with SRM ratings. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://arxiv.org/abs/1905.00961v6 |
| https://arxiv.org/pdf/1905.00961v6.pdf | |
| PWC | https://paperswithcode.com/paper/elo-ratings-applied-to-topcoder-srm |
| Repo | |
| Framework | |
Adversarial Training with Voronoi Constraints
| Title | Adversarial Training with Voronoi Constraints |
| Authors | Marc Khoury, Dylan Hadfield-Menell |
| Abstract | Adversarial examples are a pervasive phenomenon of machine learning models where seemingly imperceptible perturbations to the input lead to misclassifications for otherwise statistically accurate models. We propose a geometric framework, drawing on tools from the manifold reconstruction literature, to analyze the high-dimensional geometry of adversarial examples. In particular, we highlight the importance of codimension: for low-dimensional data manifolds embedded in high-dimensional space there are many directions off the manifold in which an adversary could construct adversarial examples. Adversarial examples are a natural consequence of learning a decision boundary that classifies the low-dimensional data manifold well, but classifies points near the manifold incorrectly. Using our geometric framework we prove that adversarial training is sample inefficient, and show sufficient sampling conditions under which nearest neighbor classifiers and ball-based adversarial training are robust. Finally we introduce adversarial training with Voronoi constraints, which replaces the norm ball constraint with the Voronoi cell for each point in the training set. We show that adversarial training with Voronoi constraints produces robust models which significantly improve over the state-of-the-art on MNIST and are competitive on CIFAR-10. |
| Tasks | |
| Published | 2019-05-02 |
| URL | https://arxiv.org/abs/1905.01019v1 |
| https://arxiv.org/pdf/1905.01019v1.pdf | |
| PWC | https://paperswithcode.com/paper/adversarial-training-with-voronoi-constraints |
| Repo | |
| Framework | |
Chaotic Genetic Algorithm and The Effects of Entropy in Performance Optimization
| Title | Chaotic Genetic Algorithm and The Effects of Entropy in Performance Optimization |
| Authors | Guillermo Fuertes, Manuel Vargas, Miguel Alfaro, Rodrigo Soto-Garrido, Jorge Sabattin, Maria Alejandra Peralta |
| Abstract | This work proposes a new edge about the Chaotic Genetic Algorithm (CGA) and the importance of the entropy in the initial population. Inspired by chaos theory the CGA uses chaotic maps to modify the stochastic parameters of Genetic Algorithm (GA). The algorithm modifies the parameters of the initial population using chaotic series and then analyzes the entropy of such population. This strategy exhibits the relationship between entropy and performance optimization in complex search spaces. Our study includes the optimization of nine benchmark functions using eight different chaotic maps for each of the benchmark functions. The numerical experiment demonstrates a direct relation between entropy and performance of the algorithm. |
| Tasks | |
| Published | 2019-01-16 |
| URL | http://arxiv.org/abs/1903.01896v1 |
| http://arxiv.org/pdf/1903.01896v1.pdf | |
| PWC | https://paperswithcode.com/paper/chaotic-genetic-algorithm-and-the-effects-of |
| Repo | |
| Framework | |
Learning Feature Aggregation in Temporal Domain for Re-Identification
| Title | Learning Feature Aggregation in Temporal Domain for Re-Identification |
| Authors | Jakub Špaňhel, Jakub Sochor, Roman Juránek, Petr Dobeš, Vojtěch Bartl, Adam Herout |
| Abstract | Person re-identification is a standard and established problem in the computer vision community. In recent years, vehicle re-identification is also getting more attention. In this paper, we focus on both these tasks and propose a method for aggregation of features in temporal domain as it is common to have multiple observations of the same object. The aggregation is based on weighting different elements of the feature vectors by different weights and it is trained in an end-to-end manner by a Siamese network. The experimental results show that our method outperforms other existing methods for feature aggregation in temporal domain on both vehicle and person re-identification tasks. Furthermore, to push research in vehicle re-identification further, we introduce a novel dataset CarsReId74k. The dataset is not limited to frontal/rear viewpoints. It contains 17,681 unique vehicles, 73,976 observed tracks, and 277,236 positive pairs. The dataset was captured by 66 cameras from various angles. |
| Tasks | Person Re-Identification, Vehicle Re-Identification |
| Published | 2019-03-12 |
| URL | http://arxiv.org/abs/1903.05244v1 |
| http://arxiv.org/pdf/1903.05244v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-feature-aggregation-in-temporal |
| Repo | |
| Framework | |
Vehicle Re-Identification: an Efficient Baseline Using Triplet Embedding
| Title | Vehicle Re-Identification: an Efficient Baseline Using Triplet Embedding |
| Authors | Ratnesh Kumar, Edwin Weill, Farzin Aghdasi, Parthsarathy Sriram |
| Abstract | In this paper we tackle the problem of vehicle re-identification in a camera network utilizing triplet embeddings. Re-identification is the problem of matching appearances of objects across different cameras. With the proliferation of surveillance cameras enabling smart and safer cities, there is an ever-increasing need to re-identify vehicles across cameras. Typical challenges arising in smart city scenarios include variations of viewpoints, illumination and self occlusions. Most successful approaches for re-identification involve (deep) learning an embedding space such that the vehicles of same identities are projected closer to one another, compared to the vehicles representing different identities. Popular loss functions for learning an embedding (space) include contrastive or triplet loss. In this paper we provide an extensive evaluation of these losses applied to vehicle re-identification and demonstrate that using the best practices for learning embeddings outperform most of the previous approaches proposed in the vehicle re-identification literature. Compared to most existing state-of-the-art approaches, our approach is simpler and more straightforward for training utilizing only identity-level annotations, along with one of the smallest published embedding dimensions for efficient inference. Furthermore in this work we introduce a formal evaluation of a triplet sampling variant (batch sample) into the re-identification literature. |
| Tasks | Vehicle Re-Identification |
| Published | 2019-01-04 |
| URL | https://arxiv.org/abs/1901.01015v4 |
| https://arxiv.org/pdf/1901.01015v4.pdf | |
| PWC | https://paperswithcode.com/paper/vehicle-re-identification-an-efficient |
| Repo | |
| Framework | |
On the Robustness of Unsupervised and Semi-supervised Cross-lingual Word Embedding Learning
| Title | On the Robustness of Unsupervised and Semi-supervised Cross-lingual Word Embedding Learning |
| Authors | Yerai Doval, Jose Camacho-Collados, Luis Espinosa-Anke, Steven Schockaert |
| Abstract | Cross-lingual word embeddings are vector representations of words in different languages where words with similar meaning are represented by similar vectors, regardless of the language. Recent developments which construct these embeddings by aligning monolingual spaces have shown that accurate alignments can be obtained with little or no supervision. However, the focus has been on a particular controlled scenario for evaluation, and there is no strong evidence on how current state-of-the-art systems would fare with noisy text or for language pairs with major linguistic differences. In this paper we present an extensive evaluation over multiple cross-lingual embedding models, analyzing their strengths and limitations with respect to different variables such as target language, training corpora and amount of supervision. Our conclusions put in doubt the view that high-quality cross-lingual embeddings can always be learned without much supervision. |
| Tasks | Word Embeddings |
| Published | 2019-08-21 |
| URL | https://arxiv.org/abs/1908.07742v4 |
| https://arxiv.org/pdf/1908.07742v4.pdf | |
| PWC | https://paperswithcode.com/paper/190807742 |
| Repo | |
| Framework | |
MaxEntropy Pursuit Variational Inference
| Title | MaxEntropy Pursuit Variational Inference |
| Authors | Evgenii Egorov, Kirill Neklydov, Ruslan Kostoev, Evgeny Burnaev |
| Abstract | One of the core problems in variational inference is a choice of approximate posterior distribution. It is crucial to trade-off between efficient inference with simple families as mean-field models and accuracy of inference. We propose a variant of a greedy approximation of the posterior distribution with tractable base learners. Using Max-Entropy approach, we obtain a well-defined optimization problem. We demonstrate the ability of the method to capture complex multimodal posterior via continual learning setting for neural networks. |
| Tasks | Continual Learning |
| Published | 2019-05-20 |
| URL | https://arxiv.org/abs/1905.07855v1 |
| https://arxiv.org/pdf/1905.07855v1.pdf | |
| PWC | https://paperswithcode.com/paper/maxentropy-pursuit-variational-inference |
| Repo | |
| Framework | |
Robustness of Brain Tumor Segmentation
| Title | Robustness of Brain Tumor Segmentation |
| Authors | Sabine Müller, Joachim Weickert, Norbert Graf |
| Abstract | We address the generalization behavior of deep neural networks in the context of brain tumor segmentation. While current topologies show an increasingly complex structure, the overall benchmark performance does improve negligibly. In our experiments, we demonstrate that a well trained U-Net shows the best generalization behavior and is sufficient to solve this segmentation problem. We illustrate why extensions of this model cannot only be pointless but even harmful in a realistic scenario. Also, we suggest two simple modifications (that do not alter the topology) to further improve its generalization performance. |
| Tasks | Brain Tumor Segmentation |
| Published | 2019-12-24 |
| URL | https://arxiv.org/abs/1912.11312v2 |
| https://arxiv.org/pdf/1912.11312v2.pdf | |
| PWC | https://paperswithcode.com/paper/robustness-of-brain-tumor-segmentation |
| Repo | |
| Framework | |
Classifier Suites for Insider Threat Detection
| Title | Classifier Suites for Insider Threat Detection |
| Authors | David Noever |
| Abstract | Better methods to detect insider threats need new anticipatory analytics to capture risky behavior prior to losing data. In search of the best overall classifier, this work empirically scores 88 machine learning algorithms in 16 major families. We extract risk features from the large CERT dataset, which blends real network behavior with individual threat narratives. We discover the predictive importance of measuring employee sentiment. Among major classifier families tested on CERT, the random forest algorithms offer the best choice, with different implementations scoring over 98% accurate. In contrast to more obscure or black-box alternatives, random forests are ensembles of many decision trees and thus offer a deep but human-readable set of detection rules (>2000 rules). We address performance rankings by penalizing long execution times against higher median accuracies using cross-fold validation. We address the relative rarity of threats as a case of low signal-to-noise (< 0.02% malicious to benign activities), and then train on both under-sampled and over-sampled data which is statistically balanced to identify nefarious actors. |
| Tasks | |
| Published | 2019-01-30 |
| URL | http://arxiv.org/abs/1901.10948v1 |
| http://arxiv.org/pdf/1901.10948v1.pdf | |
| PWC | https://paperswithcode.com/paper/classifier-suites-for-insider-threat |
| Repo | |
| Framework | |
Face De-occlusion using 3D Morphable Model and Generative Adversarial Network
| Title | Face De-occlusion using 3D Morphable Model and Generative Adversarial Network |
| Authors | Xiaowei Yuan, In Kyu Park |
| Abstract | In recent decades, 3D morphable model (3DMM) has been commonly used in image-based photorealistic 3D face reconstruction. However, face images are often corrupted by serious occlusion by non-face objects including eyeglasses, masks, and hands. Such objects block the correct capture of landmarks and shading information. Therefore, the reconstructed 3D face model is hardly reusable. In this paper, a novel method is proposed to restore de-occluded face images based on inverse use of 3DMM and generative adversarial network. We utilize the 3DMM prior to the proposed adversarial network and combine a global and local adversarial convolutional neural network to learn face de-occlusion model. The 3DMM serves not only as geometric prior but also proposes the face region for the local discriminator. Experiment results confirm the effectiveness and robustness of the proposed algorithm in removing challenging types of occlusions with various head poses and illumination. Furthermore, the proposed method reconstructs the correct 3D face model with de-occluded textures. |
| Tasks | 3D Face Reconstruction, Face Reconstruction |
| Published | 2019-04-12 |
| URL | https://arxiv.org/abs/1904.06109v2 |
| https://arxiv.org/pdf/1904.06109v2.pdf | |
| PWC | https://paperswithcode.com/paper/face-de-occlusion-using-3d-morphable-model |
| Repo | |
| Framework | |
AMR-to-Text Generation with Cache Transition Systems
| Title | AMR-to-Text Generation with Cache Transition Systems |
| Authors | Lisa Jin, Daniel Gildea |
| Abstract | Text generation from AMR involves emitting sentences that reflect the meaning of their AMR annotations. Neural sequence-to-sequence models have successfully been used to decode strings from flattened graphs (e.g., using depth-first or random traversal). Such models often rely on attention-based decoders to map AMR node to English token sequences. Instead of linearizing AMR, we directly encode its graph structure and delegate traversal to the decoder. To enforce a sentence-aligned graph traversal and provide local graph context, we predict transition-based parser actions in addition to English words. We present two model variants: one generates parser actions prior to words, while the other interleaves actions with words. |
| Tasks | Text Generation |
| Published | 2019-12-03 |
| URL | https://arxiv.org/abs/1912.01682v1 |
| https://arxiv.org/pdf/1912.01682v1.pdf | |
| PWC | https://paperswithcode.com/paper/amr-to-text-generation-with-cache-transition |
| Repo | |
| Framework | |
A New Technique of Camera Calibration: A Geometric Approach Based on Principal Lines
| Title | A New Technique of Camera Calibration: A Geometric Approach Based on Principal Lines |
| Authors | Jen-Hui Chuang, Chih-Hui Ho, Ardian Umam, HsinYi Chen, Mu-Tien Lu, Jenq-Neng Hwang, Tai-An Chen |
| Abstract | Camera calibration is a crucial prerequisite in many applications of computer vision. In this paper, a new, geometry-based camera calibration technique is proposed, which resolves two main issues associated with the widely used Zhang’s method: (i) the lack of guidelines to avoid outliers in the computation and (ii) the assumption of fixed camera focal length. The proposed approach is based on the closed-form solution of principal lines (PLs), with their intersection being the principal point while each PL can concisely represent relative orientation/position (up to one degree of freedom for both) between a special pair of coordinate systems of image plane and calibration pattern. With such analytically tractable image features, computations associated with the calibration are greatly simplified, while the guidelines in (i) can be established intuitively. Experimental results for synthetic and real data show that the proposed approach does compare favorably with Zhang’s method, in terms of correctness, robustness, and flexibility, and addresses issues (i) and (ii) satisfactorily. |
| Tasks | Calibration |
| Published | 2019-08-18 |
| URL | https://arxiv.org/abs/1908.06539v1 |
| https://arxiv.org/pdf/1908.06539v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-new-technique-of-camera-calibration-a |
| Repo | |
| Framework | |
