Paper Group ANR 397
Architectural Resilience to Foreground-and-Background Adversarial Noise. HRINet: Alternative Supervision Network for High-resolution CT image Interpolation. Improving Calibration in Mixup-trained Deep Neural Networks through Confidence-Based Loss Functions. Deep NRSfM++: Towards 3D Reconstruction in the Wild. Synergetic Reconstruction from 2D Pose …
Architectural Resilience to Foreground-and-Background Adversarial Noise
| Title | Architectural Resilience to Foreground-and-Background Adversarial Noise |
| Authors | Carl Cheng, Evan Hu |
| Abstract | Adversarial attacks in the form of imperceptible perturbations of normal images have been extensively studied, and for every new defense methodology created, multiple adversarial attacks are found to counteract it. In particular, a popular style of attack, exemplified in recent years by DeepFool and Carlini-Wagner, relies solely on white-box scenarios in which full access to the predictive model and its weights are required. In this work, we instead propose distinct model-agnostic benchmark perturbations of images in order to investigate the resilience and robustness of different network architectures. Results empirically determine that increasing depth within most types of Convolutional Neural Networks typically improves model resilience towards general attacks, with improvement steadily decreasing as the model becomes deeper. Additionally, we find that a notable difference in adversarial robustness exists between residual architectures with skip connections and non-residual architectures of similar complexity. Our findings provide direction for future understanding of residual connections and depth on network robustness. |
| Tasks | |
| Published | 2020-03-23 |
| URL | https://arxiv.org/abs/2003.10045v1 |
| https://arxiv.org/pdf/2003.10045v1.pdf | |
| PWC | https://paperswithcode.com/paper/architectural-resilience-to-foreground-and |
| Repo | |
| Framework | |
HRINet: Alternative Supervision Network for High-resolution CT image Interpolation
| Title | HRINet: Alternative Supervision Network for High-resolution CT image Interpolation |
| Authors | Jiawei Li, Jae Chul Koh, Won-Sook Lee |
| Abstract | Image interpolation in medical area is of high importance as most 3D biomedical volume images are sampled where the distance between consecutive slices significantly greater than the in-plane pixel size due to radiation dose or scanning time. Image interpolation creates a number of new slices between known slices in order to obtain an isotropic volume image. The results can be used for the higher quality of 3D reconstruction and visualization of human body structures. Semantic interpolation on the manifold has been proved to be very useful for smoothing image interpolation. Nevertheless, all previous methods focused on low-resolution image interpolation, and most of them work poorly on high-resolution image. We propose a novel network, High Resolution Interpolation Network (HRINet), aiming at producing high-resolution CT image interpolations. We combine the idea of ACAI and GANs, and propose a novel idea of alternative supervision method by applying supervised and unsupervised training alternatively to raise the accuracy of human organ structures in CT while keeping high quality. We compare an MSE based and a perceptual based loss optimizing methods for high quality interpolation, and show the tradeoff between the structural correctness and sharpness. Our experiments show the great improvement on 256 2 and 5122 images quantitatively and qualitatively. |
| Tasks | 3D Reconstruction |
| Published | 2020-02-11 |
| URL | https://arxiv.org/abs/2002.04455v1 |
| https://arxiv.org/pdf/2002.04455v1.pdf | |
| PWC | https://paperswithcode.com/paper/hrinet-alternative-supervision-network-for |
| Repo | |
| Framework | |
Improving Calibration in Mixup-trained Deep Neural Networks through Confidence-Based Loss Functions
| Title | Improving Calibration in Mixup-trained Deep Neural Networks through Confidence-Based Loss Functions |
| Authors | Juan Maroñas, Daniel Ramos, Roberto Paredes |
| Abstract | Deep Neural Networks (DNN) represent the state of the art in many tasks. However, due to their overparameterization, their generalization capabilities are in doubt and are still under study. Consequently, DNN can overfit and assign overconfident predictions, as they tend to learn highly oscillating decision thresholds. This has been shown to affect the calibration of the confidences assigned to unseen data. Data Augmentation (DA) strategies have been proposed to overcome some of these limitations. One of the most popular is Mixup, which has shown a great ability to improve the accuracy of these models. Recent work has provided evidence that Mixup also improves the uncertainty quantification and calibration of DNN. In this work, we argue and provide empirical evidence that, due to its fundamentals, Mixup does not necessarily improve calibration. Based on our observations we propose a new loss function that improves the calibration, and also sometimes the accuracy. Our loss is inspired by Bayes decision theory and introduces a new training framework for designing losses for probabilistic modelling. We provide state-of-the-art accuracy with consistent improvements in calibration performance. |
| Tasks | Calibration, Data Augmentation |
| Published | 2020-03-22 |
| URL | https://arxiv.org/abs/2003.09946v1 |
| https://arxiv.org/pdf/2003.09946v1.pdf | |
| PWC | https://paperswithcode.com/paper/improving-calibration-in-mixup-trained-deep |
| Repo | |
| Framework | |
Deep NRSfM++: Towards 3D Reconstruction in the Wild
| Title | Deep NRSfM++: Towards 3D Reconstruction in the Wild |
| Authors | Chaoyang Wang, Chen-Hsuan Lin, Simon Lucey |
| Abstract | The recovery of 3D shape and pose solely from 2D landmarks stemming from a large ensemble of images can be viewed as a non-rigid structure from motion (NRSfM) problem. To date, however, the application of NRSfM to problems in the wild has been problematic. Classical NRSfM approaches do not scale to large numbers of images and can only handle certain types of 3D structure (e.g. low-rank). A recent breakthrough in this problem has allowed for the reconstruction of a substantially broader set of 3D structures, dramatically expanding the approach’s importance to many problems in computer vision. However, the approach is still limited in that (i) it cannot handle missing/occluded points, and (ii) it is applicable only to weak-perspective camera models. In this paper, we present Deep NRSfM++, an approach to allow NRSfM to be truly applicable in the wild by offering up innovative solutions to the above two issues. Furthermore, we demonstrate state-of-the-art performance across numerous benchmarks, even against recent methods based on deep neural networks. |
| Tasks | 3D Reconstruction |
| Published | 2020-01-27 |
| URL | https://arxiv.org/abs/2001.10090v1 |
| https://arxiv.org/pdf/2001.10090v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-nrsfm-towards-3d-reconstruction-in-the |
| Repo | |
| Framework | |
Synergetic Reconstruction from 2D Pose and 3D Motion for Wide-Space Multi-Person Video Motion Capture in the Wild
| Title | Synergetic Reconstruction from 2D Pose and 3D Motion for Wide-Space Multi-Person Video Motion Capture in the Wild |
| Authors | Takuya Ohashi, Yosuke Ikegami, Yoshihiko Nakamura |
| Abstract | Although many studies have been made on markerless motion capture, it has not been applied to real sports or concerts. In this paper, we propose a markerless motion capture method with spatiotemporal accuracy and smoothness from multiple cameras, even in wide and multi-person environments. The key idea is predicting each person’s 3D pose and determining the bounding box of multi-camera images small enough. This prediction and spatiotemporal filtering based on human skeletal structure eases 3D reconstruction of the person and yields accuracy. The accurate 3D reconstruction is then used to predict the bounding box of each camera image in the next frame. This is a feedback from 3D motion to 2D pose, and provides a synergetic effect to the total performance of video motion capture. We demonstrate the method using various datasets and a real sports field. The experimental results show the mean per joint position error was 31.6mm and the percentage of correct parts was 99.3% under five people moving dynamically, with satisfying the range of motion. Video demonstration, datasets, and additional materials are posted on our project page. |
| Tasks | 3D Reconstruction, Markerless Motion Capture, Motion Capture |
| Published | 2020-01-16 |
| URL | https://arxiv.org/abs/2001.05613v1 |
| https://arxiv.org/pdf/2001.05613v1.pdf | |
| PWC | https://paperswithcode.com/paper/synergetic-reconstruction-from-2d-pose-and-3d |
| Repo | |
| Framework | |
Text-to-Image Generation with Attention Based Recurrent Neural Networks
| Title | Text-to-Image Generation with Attention Based Recurrent Neural Networks |
| Authors | Tehseen Zia, Shahan Arif, Shakeeb Murtaza, Mirza Ahsan Ullah |
| Abstract | Conditional image modeling based on textual descriptions is a relatively new domain in unsupervised learning. Previous approaches use a latent variable model and generative adversarial networks. While the formers are approximated by using variational auto-encoders and rely on the intractable inference that can hamper their performance, the latter is unstable to train due to Nash equilibrium based objective function. We develop a tractable and stable caption-based image generation model. The model uses an attention-based encoder to learn word-to-pixel dependencies. A conditional autoregressive based decoder is used for learning pixel-to-pixel dependencies and generating images. Experimentations are performed on Microsoft COCO, and MNIST-with-captions datasets and performance is evaluated by using the Structural Similarity Index. Results show that the proposed model performs better than contemporary approaches and generate better quality images. Keywords: Generative image modeling, autoregressive image modeling, caption-based image generation, neural attention, recurrent neural networks. |
| Tasks | Image Generation, Text-to-Image Generation |
| Published | 2020-01-18 |
| URL | https://arxiv.org/abs/2001.06658v1 |
| https://arxiv.org/pdf/2001.06658v1.pdf | |
| PWC | https://paperswithcode.com/paper/text-to-image-generation-with-attention-based |
| Repo | |
| Framework | |
Descriptive and Predictive Analysis of Euroleague Basketball Games and the Wisdom of Basketball Crowds
| Title | Descriptive and Predictive Analysis of Euroleague Basketball Games and the Wisdom of Basketball Crowds |
| Authors | Georgios Giasemidis |
| Abstract | In this study we focus on the prediction of basketball games in the Euroleague competition using machine learning modelling. The prediction is a binary classification problem, predicting whether a match finishes 1 (home win) or 2 (away win). Data is collected from the Euroleague’s official website for the seasons 2016-2017, 2017-2018 and 2018-2019, i.e. in the new format era. Features are extracted from matches’ data and off-the-shelf supervised machine learning techniques are applied. We calibrate and validate our models. We find that simple machine learning models give accuracy not greater than 67% on the test set, worse than some sophisticated benchmark models. Additionally, the importance of this study lies in the “wisdom of the basketball crowd” and we demonstrate how the predicting power of a collective group of basketball enthusiasts can outperform machine learning models discussed in this study. We argue why the accuracy level of this group of “experts” should be set as the benchmark for future studies in the prediction of (European) basketball games using machine learning. |
| Tasks | |
| Published | 2020-02-19 |
| URL | https://arxiv.org/abs/2002.08465v1 |
| https://arxiv.org/pdf/2002.08465v1.pdf | |
| PWC | https://paperswithcode.com/paper/descriptive-and-predictive-analysis-of |
| Repo | |
| Framework | |
Tuning-free ridge estimators for high-dimensional generalized linear models
| Title | Tuning-free ridge estimators for high-dimensional generalized linear models |
| Authors | Shih-Ting Huang, Fang Xie, Johannes Lederer |
| Abstract | Ridge estimators regularize the squared Euclidean lengths of parameters. Such estimators are mathematically and computationally attractive but involve tuning parameters that can be difficult to calibrate. In this paper, we show that ridge estimators can be modified such that tuning parameters can be avoided altogether. We also show that these modified versions can improve on the empirical prediction accuracies of standard ridge estimators combined with cross-validation, and we provide first theoretical guarantees. |
| Tasks | |
| Published | 2020-02-27 |
| URL | https://arxiv.org/abs/2002.11916v1 |
| https://arxiv.org/pdf/2002.11916v1.pdf | |
| PWC | https://paperswithcode.com/paper/tuning-free-ridge-estimators-for-high |
| Repo | |
| Framework | |
Intrinsic Motivation and Episodic Memories for Robot Exploration of High-Dimensional Sensory Spaces
| Title | Intrinsic Motivation and Episodic Memories for Robot Exploration of High-Dimensional Sensory Spaces |
| Authors | Guido Schillaci, Antonio Pico Villalpando, Verena Vanessa Hafner, Peter Hanappe, David Colliaux, Timothée Wintz |
| Abstract | This work presents an architecture that generates curiosity-driven goal-directed exploration behaviours for an image sensor of a microfarming robot. A combination of deep neural networks for offline unsupervised learning of low-dimensional features from images, and of online learning of shallow neural networks representing the inverse and forward kinematics of the system have been used. The artificial curiosity system assigns interest values to a set of pre-defined goals, and drives the exploration towards those that are expected to maximise the learning progress. We propose the integration of an episodic memory in intrinsic motivation systems to face catastrophic forgetting issues, typically experienced when performing online updates of artificial neural networks. Our results show that adopting an episodic memory system not only prevents the computational models from quickly forgetting knowledge that has been previously acquired, but also provides new avenues for modulating the balance between plasticity and stability of the models. |
| Tasks | |
| Published | 2020-01-07 |
| URL | https://arxiv.org/abs/2001.01982v1 |
| https://arxiv.org/pdf/2001.01982v1.pdf | |
| PWC | https://paperswithcode.com/paper/intrinsic-motivation-and-episodic-memories |
| Repo | |
| Framework | |
Discover Your Social Identity from What You Tweet: a Content Based Approach
| Title | Discover Your Social Identity from What You Tweet: a Content Based Approach |
| Authors | Binxuan Huang, Kathleen M. Carley |
| Abstract | An identity denotes the role an individual or a group plays in highly differentiated contemporary societies. In this paper, our goal is to classify Twitter users based on their role identities. We first collect a coarse-grained public figure dataset automatically, then manually label a more fine-grained identity dataset. We propose a hierarchical self-attention neural network for Twitter user role identity classification. Our experiments demonstrate that the proposed model significantly outperforms multiple baselines. We further propose a transfer learning scheme that improves our model’s performance by a large margin. Such transfer learning also greatly reduces the need for a large amount of human labeled data. |
| Tasks | Transfer Learning |
| Published | 2020-03-03 |
| URL | https://arxiv.org/abs/2003.01797v1 |
| https://arxiv.org/pdf/2003.01797v1.pdf | |
| PWC | https://paperswithcode.com/paper/discover-your-social-identity-from-what-you |
| Repo | |
| Framework | |
Sparse Semi-supervised Heterogeneous Interbattery Bayesian Analysis
| Title | Sparse Semi-supervised Heterogeneous Interbattery Bayesian Analysis |
| Authors | Carlos Sevilla-Salcedo, Vanessa Gómez-Verdejo, Pablo M. Olmos |
| Abstract | The Bayesian approach to feature extraction, known as factor analysis (FA), has been widely studied in machine learning to obtain a latent representation of the data. An adequate selection of the probabilities and priors of these bayesian models allows the model to better adapt to the data nature (i.e. heterogeneity, sparsity), obtaining a more representative latent space. The objective of this article is to propose a general FA framework capable of modelling any problem. To do so, we start from the Bayesian Inter-Battery Factor Analysis (BIBFA) model, enhancing it with new functionalities to be able to work with heterogeneous data, include feature selection, and handle missing values as well as semi-supervised problems. The performance of the proposed model, Sparse Semi-supervised Heterogeneous Interbattery Bayesian Analysis (SSHIBA) has been tested on 4 different scenarios to evaluate each one of its novelties, showing not only a great versatility and an interpretability gain, but also outperforming most of the state-of-the-art algorithms. |
| Tasks | Feature Selection |
| Published | 2020-01-24 |
| URL | https://arxiv.org/abs/2001.08975v1 |
| https://arxiv.org/pdf/2001.08975v1.pdf | |
| PWC | https://paperswithcode.com/paper/sparse-semi-supervised-heterogeneous |
| Repo | |
| Framework | |
Generalized Hindsight for Reinforcement Learning
| Title | Generalized Hindsight for Reinforcement Learning |
| Authors | Alexander C. Li, Lerrel Pinto, Pieter Abbeel |
| Abstract | One of the key reasons for the high sample complexity in reinforcement learning (RL) is the inability to transfer knowledge from one task to another. In standard multi-task RL settings, low-reward data collected while trying to solve one task provides little to no signal for solving that particular task and is hence effectively wasted. However, we argue that this data, which is uninformative for one task, is likely a rich source of information for other tasks. To leverage this insight and efficiently reuse data, we present Generalized Hindsight: an approximate inverse reinforcement learning technique for relabeling behaviors with the right tasks. Intuitively, given a behavior generated under one task, Generalized Hindsight returns a different task that the behavior is better suited for. Then, the behavior is relabeled with this new task before being used by an off-policy RL optimizer. Compared to standard relabeling techniques, Generalized Hindsight provides a substantially more efficient reuse of samples, which we empirically demonstrate on a suite of multi-task navigation and manipulation tasks. Videos and code can be accessed here: https://sites.google.com/view/generalized-hindsight. |
| Tasks | |
| Published | 2020-02-26 |
| URL | https://arxiv.org/abs/2002.11708v1 |
| https://arxiv.org/pdf/2002.11708v1.pdf | |
| PWC | https://paperswithcode.com/paper/generalized-hindsight-for-reinforcement |
| Repo | |
| Framework | |
Debate Dynamics for Human-comprehensible Fact-checking on Knowledge Graphs
| Title | Debate Dynamics for Human-comprehensible Fact-checking on Knowledge Graphs |
| Authors | Marcel Hildebrandt, Jorge Andres Quintero Serna, Yunpu Ma, Martin Ringsquandl, Mitchell Joblin, Volker Tresp |
| Abstract | We propose a novel method for fact-checking on knowledge graphs based on debate dynamics. The underlying idea is to frame the task of triple classification as a debate game between two reinforcement learning agents which extract arguments – paths in the knowledge graph – with the goal to justify the fact being true (thesis) or the fact being false (antithesis), respectively. Based on these arguments, a binary classifier, referred to as the judge, decides whether the fact is true or false. The two agents can be considered as sparse feature extractors that present interpretable evidence for either the thesis or the antithesis. In contrast to black-box methods, the arguments enable the user to gain an understanding for the decision of the judge. Moreover, our method allows for interactive reasoning on knowledge graphs where the users can raise additional arguments or evaluate the debate taking common sense reasoning and external information into account. Such interactive systems can increase the acceptance of various AI applications based on knowledge graphs and can further lead to higher efficiency, robustness, and fairness. |
| Tasks | Common Sense Reasoning, Knowledge Graphs |
| Published | 2020-01-09 |
| URL | https://arxiv.org/abs/2001.03436v1 |
| https://arxiv.org/pdf/2001.03436v1.pdf | |
| PWC | https://paperswithcode.com/paper/debate-dynamics-for-human-comprehensible-fact |
| Repo | |
| Framework | |
HATSUKI : An anime character like robot figure platform with anime-style expressions and imitation learning based action generation
| Title | HATSUKI : An anime character like robot figure platform with anime-style expressions and imitation learning based action generation |
| Authors | Pin-Chu Yang, Mohammed Al-Sada, Chang-Chieh Chiu, Kevin Kuo, Tito Pradhono Tomo, Kanata Suzuki, Nelson Yalta, Kuo-Hao Shu, Tetsuya Ogata |
| Abstract | Japanese character figurines are popular and have pivot position in Otaku culture. Although numerous robots have been developed, less have focused on otaku-culture or on embodying the anime character figurine. Therefore, we take the first steps to bridge this gap by developing Hatsuki, which is a humanoid robot platform with anime based design. Hatsuki’s novelty lies in aesthetic design, 2D facial expressions, and anime-style behaviors that allows it to deliver rich interaction experiences resembling anime-characters. We explain our design implementation process of Hatsuki, followed by our evaluations. In order to explore user impressions and opinions towards Hatsuki, we conducted a questionnaire in the world’s largest anime-figurine event. The results indicate that participants were generally very satisfied with Hatsuki’s design, and proposed various use case scenarios and deployment contexts for Hatsuki. The second evaluation focused on imitation learning, as such method can provide better interaction ability in the real world and generate rich, context-adaptive behavior in different situations. We made Hatsuki learn 11 actions, combining voice, facial expressions and motions, through neuron network based policy model with our proposed interface. Results show our approach was successfully able to generate the actions through self-organized contexts, which shows the potential for generalizing our approach in further actions under different contexts. Lastly, we present our future research direction for Hatsuki, and provide our conclusion. |
| Tasks | Imitation Learning |
| Published | 2020-03-31 |
| URL | https://arxiv.org/abs/2003.14121v1 |
| https://arxiv.org/pdf/2003.14121v1.pdf | |
| PWC | https://paperswithcode.com/paper/hatsuki-an-anime-character-like-robot-figure |
| Repo | |
| Framework | |
Knowledge Graphs for Innovation Ecosystems
| Title | Knowledge Graphs for Innovation Ecosystems |
| Authors | Alberto Tejero, Victor Rodriguez-Doncel, Ivan Pau |
| Abstract | Innovation ecosystems can be naturally described as a collection of networked entities, such as experts, institutions, projects, technologies and products. Representing in a machine-readable form these entities and their relations is not entirely attainable, due to the existence of abstract concepts such as knowledge and due to the confidential, non-public nature of this information, but even its partial depiction is of strong interest. The representation of innovation ecosystems incarnated as knowledge graphs would enable the generation of reports with new insights, the execution of advanced data analysis tasks. An ontology to capture the essential entities and relations is presented, as well as the description of data sources, which can be used to populate innovation knowledge graphs. Finally, the application case of the Universidad Politecnica de Madrid is presented, as well as an insight of future applications. |
| Tasks | Knowledge Graphs |
| Published | 2020-01-09 |
| URL | https://arxiv.org/abs/2001.08615v1 |
| https://arxiv.org/pdf/2001.08615v1.pdf | |
| PWC | https://paperswithcode.com/paper/knowledge-graphs-for-innovation-ecosystems |
| Repo | |
| Framework | |
