Paper Group ANR 6
Few-Shot Relation Learning with Attention for EEG-based Motor Imagery Classification. Enhanced POET: Open-Ended Reinforcement Learning through Unbounded Invention of Learning Challenges and their Solutions. Review of Probability Distributions for Modeling Count Data. Deep Local Shapes: Learning Local SDF Priors for Detailed 3D Reconstruction. Atlas …
Few-Shot Relation Learning with Attention for EEG-based Motor Imagery Classification
| Title | Few-Shot Relation Learning with Attention for EEG-based Motor Imagery Classification |
| Authors | Sion An, Soopil Kim, Philip Chikontwe, Sang Hyun Park |
| Abstract | Brain-Computer Interfaces (BCI) based on Electroencephalography (EEG) signals, in particular motor imagery (MI) data have received a lot of attention and show the potential towards the design of key technologies both in healthcare and other industries. MI data is generated when a subject imagines movement of limbs and can be used to aid rehabilitation as well as in autonomous driving scenarios. Thus, classification of MI signals is vital for EEG-based BCI systems. Recently, MI EEG classification techniques using deep learning have shown improved performance over conventional techniques. However, due to inter-subject variability, the scarcity of unseen subject data, and low signal-to-noise ratio, extracting robust features and improving accuracy is still challenging. In this context, we propose a novel two-way few shot network that is able to efficiently learn how to learn representative features of unseen subject categories and how to classify them with limited MI EEG data. The pipeline includes an embedding module that learns feature representations from a set of samples, an attention mechanism for key signal feature discovery, and a relation module for final classification based on relation scores between a support set and a query signal. In addition to the unified learning of feature similarity and a few shot classifier, our method leads to emphasize informative features in support data relevant to the query data, which generalizes better on unseen subjects. For evaluation, we used the BCI competition IV 2b dataset and achieved an 9.3% accuracy improvement in the 20-shot classification task with state-of-the-art performance. Experimental results demonstrate the effectiveness of employing attention and the overall generality of our method. |
| Tasks | Autonomous Driving, EEG |
| Published | 2020-03-03 |
| URL | https://arxiv.org/abs/2003.01300v1 |
| https://arxiv.org/pdf/2003.01300v1.pdf | |
| PWC | https://paperswithcode.com/paper/few-shot-relation-learning-with-attention-for |
| Repo | |
| Framework | |
Enhanced POET: Open-Ended Reinforcement Learning through Unbounded Invention of Learning Challenges and their Solutions
| Title | Enhanced POET: Open-Ended Reinforcement Learning through Unbounded Invention of Learning Challenges and their Solutions |
| Authors | Rui Wang, Joel Lehman, Aditya Rawal, Jiale Zhi, Yulun Li, Jeff Clune, Kenneth O. Stanley |
| Abstract | Creating open-ended algorithms, which generate their own never-ending stream of novel and appropriately challenging learning opportunities, could help to automate and accelerate progress in machine learning. A recent step in this direction is the Paired Open-Ended Trailblazer (POET), an algorithm that generates and solves its own challenges, and allows solutions to goal-switch between challenges to avoid local optima. However, the original POET was unable to demonstrate its full creative potential because of limitations of the algorithm itself and because of external issues including a limited problem space and lack of a universal progress measure. Importantly, both limitations pose impediments not only for POET, but for the pursuit of open-endedness in general. Here we introduce and empirically validate two new innovations to the original algorithm, as well as two external innovations designed to help elucidate its full potential. Together, these four advances enable the most open-ended algorithmic demonstration to date. The algorithmic innovations are (1) a domain-general measure of how meaningfully novel new challenges are, enabling the system to potentially create and solve interesting challenges endlessly, and (2) an efficient heuristic for determining when agents should goal-switch from one problem to another (helping open-ended search better scale). Outside the algorithm itself, to enable a more definitive demonstration of open-endedness, we introduce (3) a novel, more flexible way to encode environmental challenges, and (4) a generic measure of the extent to which a system continues to exhibit open-ended innovation. Enhanced POET produces a diverse range of sophisticated behaviors that solve a wide range of environmental challenges, many of which cannot be solved through other means. |
| Tasks | |
| Published | 2020-03-19 |
| URL | https://arxiv.org/abs/2003.08536v1 |
| https://arxiv.org/pdf/2003.08536v1.pdf | |
| PWC | https://paperswithcode.com/paper/enhanced-poet-open-ended-reinforcement |
| Repo | |
| Framework | |
Review of Probability Distributions for Modeling Count Data
| Title | Review of Probability Distributions for Modeling Count Data |
| Authors | F. William Townes |
| Abstract | Count data take on non-negative integer values and are challenging to properly analyze using standard linear-Gaussian methods such as linear regression and principal components analysis. Generalized linear models enable direct modeling of counts in a regression context using distributions such as the Poisson and negative binomial. When counts contain only relative information, multinomial or Dirichlet-multinomial models can be more appropriate. We review some of the fundamental connections between multinomial and count models from probability theory, providing detailed proofs. These relationships are useful for methods development in applications such as topic modeling of text data and genomics. |
| Tasks | |
| Published | 2020-01-10 |
| URL | https://arxiv.org/abs/2001.04343v1 |
| https://arxiv.org/pdf/2001.04343v1.pdf | |
| PWC | https://paperswithcode.com/paper/review-of-probability-distributions-for |
| Repo | |
| Framework | |
Deep Local Shapes: Learning Local SDF Priors for Detailed 3D Reconstruction
| Title | Deep Local Shapes: Learning Local SDF Priors for Detailed 3D Reconstruction |
| Authors | Rohan Chabra, Jan Eric Lenssen, Eddy Ilg, Tanner Schmidt, Julian Straub, Steven Lovegrove, Richard Newcombe |
| Abstract | Efficiently reconstructing complex and intricate surfaces at scale is a long-standing goal in machine perception. To address this problem we introduce Deep Local Shapes (DeepLS), a deep shape representation that enables encoding and reconstruction of high-quality 3D shapes without prohibitive memory requirements. DeepLS replaces the dense volumetric signed distance function (SDF) representation used in traditional surface reconstruction systems with a set of locally learned continuous SDFs defined by a neural network, inspired by recent work such as DeepSDF. Unlike DeepSDF, which represents an object-level SDF with a neural network and a single latent code, we store a grid of independent latent codes, each responsible for storing information about surfaces in a small local neighborhood. This decomposition of scenes into local shapes simplifies the prior distribution that the network must learn, and also enables efficient inference. We demonstrate the effectiveness and generalization power of DeepLS by showing object shape encoding and reconstructions of full scenes, where DeepLS delivers high compression, accuracy, and local shape completion. |
| Tasks | 3D Reconstruction |
| Published | 2020-03-24 |
| URL | https://arxiv.org/abs/2003.10983v1 |
| https://arxiv.org/pdf/2003.10983v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-local-shapes-learning-local-sdf-priors |
| Repo | |
| Framework | |
Atlas: End-to-End 3D Scene Reconstruction from Posed Images
| Title | Atlas: End-to-End 3D Scene Reconstruction from Posed Images |
| Authors | Zak Murez, Tarrence van As, James Bartolozzi, Ayan Sinha, Vijay Badrinarayanan, Andrew Rabinovich |
| Abstract | We present an end-to-end 3D reconstruction method for a scene by directly regressing a truncated signed distance function (TSDF) from a set of posed RGB images. Traditional approaches to 3D reconstruction rely on an intermediate representation of depth maps prior to estimating a full 3D model of a scene. We hypothesize that a direct regression to 3D is more effective. A 2D CNN extracts features from each image independently which are then back-projected and accumulated into a voxel volume using the camera intrinsics and extrinsics. After accumulation, a 3D CNN refines the accumulated features and predicts the TSDF values. Additionally, semantic segmentation of the 3D model is obtained without significant computation. This approach is evaluated on the Scannet dataset where we significantly outperform state-of-the-art baselines (deep multiview stereo followed by traditional TSDF fusion) both quantitatively and qualitatively. We compare our 3D semantic segmentation to prior methods that use a depth sensor since no previous work attempts the problem with only RGB input. |
| Tasks | 3D Reconstruction, 3D Scene Reconstruction, 3D Semantic Segmentation, Semantic Segmentation |
| Published | 2020-03-23 |
| URL | https://arxiv.org/abs/2003.10432v1 |
| https://arxiv.org/pdf/2003.10432v1.pdf | |
| PWC | https://paperswithcode.com/paper/atlas-end-to-end-3d-scene-reconstruction-from |
| Repo | |
| Framework | |
Learning Overlapping Representations for the Estimation of Individualized Treatment Effects
| Title | Learning Overlapping Representations for the Estimation of Individualized Treatment Effects |
| Authors | Yao Zhang, Alexis Bellot, Mihaela van der Schaar |
| Abstract | The choice of making an intervention depends on its potential benefit or harm in comparison to alternatives. Estimating the likely outcome of alternatives from observational data is a challenging problem as all outcomes are never observed, and selection bias precludes the direct comparison of differently intervened groups. Despite their empirical success, we show that algorithms that learn domain-invariant representations of inputs (on which to make predictions) are often inappropriate, and develop generalization bounds that demonstrate the dependence on domain overlap and highlight the need for invertible latent maps. Based on these results, we develop a deep kernel regression algorithm and posterior regularization framework that substantially outperforms the state-of-the-art on a variety of benchmarks data sets. |
| Tasks | |
| Published | 2020-01-14 |
| URL | https://arxiv.org/abs/2001.04754v3 |
| https://arxiv.org/pdf/2001.04754v3.pdf | |
| PWC | https://paperswithcode.com/paper/learning-overlapping-representations-for-the |
| Repo | |
| Framework | |
A Bayes-Optimal View on Adversarial Examples
| Title | A Bayes-Optimal View on Adversarial Examples |
| Authors | Eitan Richardson, Yair Weiss |
| Abstract | The ability to fool modern CNN classifiers with tiny perturbations of the input has lead to the development of a large number of candidate defenses and often conflicting explanations. In this paper, we argue for examining adversarial examples from the perspective of Bayes-Optimal classification. We construct realistic image datasets for which the Bayes-Optimal classifier can be efficiently computed and derive analytic conditions on the distributions so that the optimal classifier is either robust or vulnerable. By training different classifiers on these datasets (for which the “gold standard” optimal classifiers are known), we can disentangle the possible sources of vulnerability and avoid the accuracy-robustness tradeoff that may occur in commonly used datasets. Our results show that even when the optimal classifier is robust, standard CNN training consistently learns a vulnerable classifier. At the same time, for exactly the same training data, RBF SVMs consistently learn a robust classifier. The same trend is observed in experiments with real images. |
| Tasks | |
| Published | 2020-02-20 |
| URL | https://arxiv.org/abs/2002.08859v1 |
| https://arxiv.org/pdf/2002.08859v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-bayes-optimal-view-on-adversarial-examples-1 |
| Repo | |
| Framework | |
BiLingUNet: Image Segmentation by Modulating Top-Down and Bottom-Up Visual Processing with Referring Expressions
| Title | BiLingUNet: Image Segmentation by Modulating Top-Down and Bottom-Up Visual Processing with Referring Expressions |
| Authors | Ozan Arkan Can, İlker Kesen, Deniz Yuret |
| Abstract | We present BiLingUNet, a state-of-the-art model for image segmentation using referring expressions. BiLingUNet uses language to customize visual filters and outperforms approaches that concatenate a linguistic representation to the visual input. We find that using language to modulate both bottom-up and top-down visual processing works better than just making the top-down processing language-conditional. We argue that common 1x1 language-conditional filters cannot represent relational concepts and experimentally demonstrate that wider filters work better. Our model achieves state-of-the-art performance on four referring expression datasets. |
| Tasks | Semantic Segmentation |
| Published | 2020-03-28 |
| URL | https://arxiv.org/abs/2003.12739v1 |
| https://arxiv.org/pdf/2003.12739v1.pdf | |
| PWC | https://paperswithcode.com/paper/bilingunet-image-segmentation-by-modulating |
| Repo | |
| Framework | |
A Graph to Graphs Framework for Retrosynthesis Prediction
| Title | A Graph to Graphs Framework for Retrosynthesis Prediction |
| Authors | Chence Shi, Minkai Xu, Hongyu Guo, Ming Zhang, Jian Tang |
| Abstract | A fundamental problem in computational chemistry is to find a set of reactants to synthesize a target molecule, a.k.a. retrosynthesis prediction. Existing state-of-the-art methods rely on matching the target molecule with a large set of reaction templates, which are very computationally expensive and also suffer from the problem of coverage. In this paper, we propose a novel template-free approach called G2Gs by transforming a target molecular graph into a set of reactant molecular graphs. G2Gs first splits the target molecular graph into a set of synthons by identifying the reaction centers, and then translates the synthons to the final reactant graphs via a variational graph translation framework. Experimental results show that G2Gs significantly outperforms existing template-free approaches by up to 63% in terms of the top-1 accuracy and achieves a performance close to that of state-of-the-art template based approaches, but does not require domain knowledge and is much more scalable. |
| Tasks | |
| Published | 2020-03-28 |
| URL | https://arxiv.org/abs/2003.12725v1 |
| https://arxiv.org/pdf/2003.12725v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-graph-to-graphs-framework-for |
| Repo | |
| Framework | |
Consumer-Driven Explanations for Machine Learning Decisions: An Empirical Study of Robustness
| Title | Consumer-Driven Explanations for Machine Learning Decisions: An Empirical Study of Robustness |
| Authors | Michael Hind, Dennis Wei, Yunfeng Zhang |
| Abstract | Many proposed methods for explaining machine learning predictions are in fact challenging to understand for nontechnical consumers. This paper builds upon an alternative consumer-driven approach called TED that asks for explanations to be provided in training data, along with target labels. Using semi-synthetic data from credit approval and employee retention applications, experiments are conducted to investigate some practical considerations with TED, including its performance with different classification algorithms, varying numbers of explanations, and variability in explanations. A new algorithm is proposed to handle the case where some training examples do not have explanations. Our results show that TED is robust to increasing numbers of explanations, noisy explanations, and large fractions of missing explanations, thus making advances toward its practical deployment. |
| Tasks | |
| Published | 2020-01-13 |
| URL | https://arxiv.org/abs/2001.05573v1 |
| https://arxiv.org/pdf/2001.05573v1.pdf | |
| PWC | https://paperswithcode.com/paper/consumer-driven-explanations-for-machine |
| Repo | |
| Framework | |
Multi-Marginal Optimal Transport Defines a Generalized Metric
| Title | Multi-Marginal Optimal Transport Defines a Generalized Metric |
| Authors | Liang Mi, José Bento |
| Abstract | We prove that the multi-marginal optimal transport (MMOT) problem defines a generalized metric. In addition, we prove that the distance induced by MMOT satisfies a generalized triangle inequality that, to leading order, cannot be improved. |
| Tasks | |
| Published | 2020-01-29 |
| URL | https://arxiv.org/abs/2001.11114v2 |
| https://arxiv.org/pdf/2001.11114v2.pdf | |
| PWC | https://paperswithcode.com/paper/multi-marginal-optimal-transport-defines-a |
| Repo | |
| Framework | |
Real-World Considerations for Deep Learning in Wireless Signal Identification Based on Spectral Correlation Function
| Title | Real-World Considerations for Deep Learning in Wireless Signal Identification Based on Spectral Correlation Function |
| Authors | Kürşat Tekbıyık, Özkan Akbunar, Ali Rıza Ekti, Ali Görçin, Güneş Karabulut Kurt |
| Abstract | This paper proposes a convolutional neural network (CNN) model which utilizes the spectral correlation function (SCF) for wireless radio access technology identification without any prior information about bandwidth and/or the center frequency. The sensing and classification methods are applied to the baseband equivalent signals. Two different approaches are elaborated. The proposed method is implemented in two different settings; in the first setting, signals are jointly sensed and classified. Sensing and classification are conducted in a sequential manner in the second setting. The performance of both approaches is discussed in detail. The proposed method eliminates the threshold estimation processes of classical estimators. It also eliminates the need to know the distinct features of signals beforehand. Over-the-air real-world measurements are used to show the robustness and the validity of the proposed method and various wireless signals are successfully distinguished from each other without any a priori knowledge. The over-the-air real-world measurements are also shared in the format of SCF. The performance of SCF-based identification is compared with the cases when fast Fourier transform and amplitude-phase representation are used as the training inputs for CNN. The comparative performance of the proposed method is quantified by precision, recall, and F1-score metrics. Moreover, a setup to compare the performance of the proposed approach with classical cyclostationary features detection (CFD) is prepared. Measurement results indicate the superiority of the proposed method against CFD, especially at the low signal-to-noise ratio regime. |
| Tasks | |
| Published | 2020-03-17 |
| URL | https://arxiv.org/abs/2003.08359v1 |
| https://arxiv.org/pdf/2003.08359v1.pdf | |
| PWC | https://paperswithcode.com/paper/real-world-considerations-for-deep-learning |
| Repo | |
| Framework | |
Automated detection of pitting and stress corrosion cracks in used nuclear fuel dry storage canisters using residual neural networks
| Title | Automated detection of pitting and stress corrosion cracks in used nuclear fuel dry storage canisters using residual neural networks |
| Authors | Theodore Papamarkou, Hayley Guy, Bryce Kroencke, Jordan Miller, Preston Robinette, Daniel Schultz, Jacob Hinkle, Laura Pullum, Catherine Schuman, Jeremy Renshaw, Stylianos Chatzidakis |
| Abstract | Nondestructive evaluation methods play an important role in ensuring component integrity and safety in many industries. Operator fatigue can play a critical role in the reliability of such methods. This is important for inspecting high value assets or assets with a high consequence of failure, such as aerospace and nuclear components. Recent advances in convolution neural networks can support and automate these inspection efforts. This paper proposes using residual neural networks (ResNets) for real-time detection of pitting and stress corrosion cracking, with a focus on dry storage canisters housing used nuclear fuel. The proposed approach crops nuclear canister images into smaller tiles, trains a ResNet on these tiles, and classifies images as corroded or intact using the per-image count of tiles predicted as corroded by the ResNet. The results demonstrate that such a deep learning approach allows to detect the locus of corrosion cracks via smaller tiles, and at the same time to infer with high accuracy whether an image comes from a corroded canister. Thereby, the proposed approach holds promise to automate and speed up nuclear fuel canister inspections, to minimize inspection costs, and to partially replace human-conducted onsite inspections, thus reducing radiation doses to personnel. |
| Tasks | |
| Published | 2020-03-06 |
| URL | https://arxiv.org/abs/2003.03241v1 |
| https://arxiv.org/pdf/2003.03241v1.pdf | |
| PWC | https://paperswithcode.com/paper/automated-detection-of-pitting-and-stress |
| Repo | |
| Framework | |
Sequential Cooperative Bayesian Inference
| Title | Sequential Cooperative Bayesian Inference |
| Authors | Junqi Wang, Pei Wang, Patrick Shafto |
| Abstract | Cooperation is often implicitly assumed when learning from other agents. Cooperation implies that the agent selecting the data, and the agent learning from the data, have the same goal, that the learner infer the intended hypothesis. Recent models in human and machine learning have demonstrated the possibility of cooperation. We seek foundational theoretical results for cooperative inference by Bayesian agents through sequential data. We develop novel approaches analyzing consistency, rate of convergence and stability of Sequential Cooperative Bayesian Inference (SCBI). Our analysis of the effectiveness, sample efficiency and robustness show that cooperation is not only possible in specific instances but theoretically well-founded in general. We discuss implications for human-human and human-machine cooperation. |
| Tasks | Bayesian Inference |
| Published | 2020-02-13 |
| URL | https://arxiv.org/abs/2002.05706v2 |
| https://arxiv.org/pdf/2002.05706v2.pdf | |
| PWC | https://paperswithcode.com/paper/sequential-cooperative-bayesian-inference |
| Repo | |
| Framework | |
Analysis of Gait-Event-related Brain Potentials During Instructed And Spontaneous Treadmill Walking – Technical Affordances and used Methods
| Title | Analysis of Gait-Event-related Brain Potentials During Instructed And Spontaneous Treadmill Walking – Technical Affordances and used Methods |
| Authors | Cornelia Herbert, Jan Nachtsheim, Michael Munz |
| Abstract | To improve the understanding of human gait and to facilitate novel developments in gait rehabilitation, the neural correlates of human gait as measured by means of non-invasive electroencephalography (EEG) have been investigated recently. Particularly, gait-related event-related brain potentials (gERPs) may provide information about the functional role of cortical brain regions in human gait control. The purpose of this paper is to explore possible experimental and technical solutions for time-sensitive analysis of human gait-related ERPs during spontaneous and instructed treadmill walking. A solution (HW/SW) for synchronous recording of gait- and EEG data was developed, tested and piloted. The solution consists of a custom-made USB synchronization interface, a time-synchronization module and a data merging module, allowing temporal synchronization of recording devices for time-sensitive extraction of gait markers for analysis of gait-related ERPs and for the training of artificial neural networks. In the present manuscript, the hardware and software components were tested with the following devices: A treadmill with an integrated pressure plate for gait analysis (zebris FDM-T) and an Acticap non-wireless 32-channel EEG-system (Brain Products GmbH). The usability and validity of the developed solution was tested in a pilot study (n = 3 healthy participants, n=3 females, mean age = 22.75 years). Recorded EEG data was segmented and analyzed according to the detected gait markers for the analysis of gait-related ERPs. Finally, EEG periods were used to train a deep learning artificial neural network as classifier of gait phases. The results obtained in this pilot study, although preliminary, support the feasibility of the solution for the application of gait-related EEG analysis.. |
| Tasks | EEG |
| Published | 2020-03-02 |
| URL | https://arxiv.org/abs/2003.00783v1 |
| https://arxiv.org/pdf/2003.00783v1.pdf | |
| PWC | https://paperswithcode.com/paper/analysis-of-gait-event-related-brain |
| Repo | |
| Framework | |
