Paper Group NANR 246
EEG emotion recognition using dynamical graph convolutional neural networks. SDC-Net: Video prediction using spatially-displaced convolution. Hierarchy of Alternating Specialists for Scene Recognition. Deep learning mutation prediction enables early stage lung cancer detection in liquid biopsy. Three Dimensions of Reproducibility in Natural Languag …
EEG emotion recognition using dynamical graph convolutional neural networks
| Title | EEG emotion recognition using dynamical graph convolutional neural networks |
| Authors | Zhenyang Zhang, Wenming Zheng, Peng Song, Zhen Cui |
| Abstract | In this paper, a multichannel EEG emotion recognition method based on a novel dynamical graph convolutional neural networks (DGCNN) is proposed. The basic idea of the proposed EEG emotion recognition method is to use a graph to model the multichannel EEG features and then perform EEG emotion classification based on this model. Different from the traditional graph convolutional neural networks (GCNN) methods, however, the proposed DGCNN method can dynamically learn the intrinsic relationship between different electroencephalogram (EEG) channels, represented by an adjacency matrix, via training a neural network so as to benefit for more discriminative EEG feature extraction. Then, the learned adjacency matrix is used for learning more discriminative features for improving the EEG emotion recognition. We conduct extensive experiments on the SJTU emotion EEG dataset (SEED) and DREAMER dataset. The experimental results demonstrate that the proposed method achieves better recognition performance than the state-of-the-art methods, in which the average recognition accuracy of 90.4% is achieved for subject dependent experiment while 79.95% for subject independent cross-validation one on the SEED database, and the average accuracies of 86.23%, 84.54% and 85.02% are respectively obtained for valence, arousal and dominance classifications on the DREAMER database. |
| Tasks | EEG, Emotion Classification, Emotion Recognition |
| Published | 2018-03-21 |
| URL | https://doi.org/10.1109/taffc.2018.2817622 |
| https://pdfs.semanticscholar.org/3378/0d6c82a0c060a9a35fd07effbd2fbb3e5b82.pdf?_ga=2.118713866.2007402716.1567967863-1098133910.1548150455 | |
| PWC | https://paperswithcode.com/paper/eeg-emotion-recognition-using-dynamical-graph |
| Repo | |
| Framework | |
SDC-Net: Video prediction using spatially-displaced convolution
| Title | SDC-Net: Video prediction using spatially-displaced convolution |
| Authors | Fitsum A. Reda, Guilin Liu, Kevin J. Shih, Robert Kirby, Jon Barker, David Tarjan, Andrew Tao, Bryan Catanzaro |
| Abstract | We present an approach for high-resolution video frame prediction by conditioning on both past frames and past optical flows. Previous approaches rely on resampling past frames, guided by a learned future optical flow, or on direct generation of pixels. Resampling based on flow is insufficient because it cannot deal with disocclusions. Generative models currently lead to blurry results. Recent approaches synthesis a pixel by convolving input patches with a predicted kernel. However, their memory requirement increases with kernel size. Here, we present spatially-displaced convolution (SDC) module for video frame prediction. We learn a motion vector and a kernel for each pixel and synthesize a pixel by applying the kernel at a displaced location in the source image, defined by the predicted motion vector. Our approach inherits the merits of both vector-based and kernel-based approaches, while ameliorating their respective disadvantages. We train our model on 428K unlabelled 1080p video game frames. Our approach produces state-of-the-art results, achieving an SSIM score of 0.904 on high-definition YouTube-8M videos, 0.918 on Caltech Pedestrian videos. Our model handles large motion effectively and synthesizes crisp frames with consistent motion. |
| Tasks | Optical Flow Estimation, Video Prediction |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Fitsum_Reda_SDC-Net_Video_prediction_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Fitsum_Reda_SDC-Net_Video_prediction_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/sdc-net-video-prediction-using-spatially |
| Repo | |
| Framework | |
Hierarchy of Alternating Specialists for Scene Recognition
| Title | Hierarchy of Alternating Specialists for Scene Recognition |
| Authors | Hyo Jin Kim, Jan-Michael Frahm |
| Abstract | We introduce a method for improving convolutional neural networks (CNNs) for scene classification. We present a hierarchy of specialist networks, which disentangles the intra-class variation and inter-class similarity in a coarse to fine manner. Our key insight is that each subset within a class is often associated with different types of inter-class similarity. This suggests that existing network of experts approaches that organize classes into coarse categories are suboptimal. In contrast, we group images based on high-level appearance features rather than their class membership and dedicate a specialist model per group. In addition, we propose an alternating architecture with a global ordered- and a global orderless-representation to account for both the coarse layout of the scene and the transient objects. We demonstrate that it leads to better performance than using a single type of representation as well as the fused features. We also introduce a mini-batch soft k-means that allows end-to-end fine-tuning, as well as a novel routing function for assigning images to specialists. Experimental results show that the proposed approach achieves a significant improvement over baselines including the existing tree-structured CNNs with class-based grouping. |
| Tasks | Scene Classification, Scene Recognition |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Hyo_Jin_Kim_Hierarchy_of_Alternating_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Hyo_Jin_Kim_Hierarchy_of_Alternating_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/hierarchy-of-alternating-specialists-for |
| Repo | |
| Framework | |
Deep learning mutation prediction enables early stage lung cancer detection in liquid biopsy
| Title | Deep learning mutation prediction enables early stage lung cancer detection in liquid biopsy |
| Authors | Steven T. Kothen-Hill, Asaf Zviran, Rafael C. Schulman, Sunil Deochand, Federico Gaiti, Dillon Maloney, Kevin Y. Huang, Will Liao, Nicolas Robine, Nathaniel D. Omans, Dan A. Landau |
| Abstract | Somatic cancer mutation detection at ultra-low variant allele frequencies (VAFs) is an unmet challenge that is intractable with current state-of-the-art mutation calling methods. Specifically, the limit of VAF detection is closely related to the depth of coverage, due to the requirement of multiple supporting reads in extant methods, precluding the detection of mutations at VAFs that are orders of magnitude lower than the depth of coverage. Nevertheless, the ability to detect cancer-associated mutations in ultra low VAFs is a fundamental requirement for low-tumor burden cancer diagnostics applications such as early detection, monitoring, and therapy nomination using liquid biopsy methods (cell-free DNA). Here we defined a spatial representation of sequencing information adapted for convolutional architecture that enables variant detection at VAFs, in a manner independent of the depth of sequencing. This method enables the detection of cancer mutations even in VAFs as low as 10x-4^, >2 orders of magnitude below the current state-of-the-art. We validated our method on both simulated plasma and on clinical cfDNA plasma samples from cancer patients and non-cancer controls. This method introduces a new domain within bioinformatics and personalized medicine – somatic whole genome mutation calling for liquid biopsy. |
| Tasks | |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=H1DkN7ZCZ |
| https://openreview.net/pdf?id=H1DkN7ZCZ | |
| PWC | https://paperswithcode.com/paper/deep-learning-mutation-prediction-enables |
| Repo | |
| Framework | |
Three Dimensions of Reproducibility in Natural Language Processing
| Title | Three Dimensions of Reproducibility in Natural Language Processing |
| Authors | K. Bretonnel Cohen, Jingbo Xia, Pierre Zweigenbaum, Tiffany Callahan, Orin Hargraves, Foster Goss, Nancy Ide, Aur{'e}lie N{'e}v{'e}ol, Cyril Grouin, Lawrence E. Hunter |
| Abstract | |
| Tasks | |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1025/ |
| https://www.aclweb.org/anthology/L18-1025 | |
| PWC | https://paperswithcode.com/paper/three-dimensions-of-reproducibility-in |
| Repo | |
| Framework | |
Deep Bilinear Learning for RGB-D Action Recognition
| Title | Deep Bilinear Learning for RGB-D Action Recognition |
| Authors | Jian-Fang Hu, Wei-Shi Zheng, Jiahui Pan, Jianhuang Lai, Jianguo Zhang |
| Abstract | In this paper, we focus on exploring modality-temporal mutual information for RGB-D action recognition. In order to learn time-varying information and multi-modal features jointly, we propose a novel deep bilinear learning framework. In the framework, we propose bilinear blocks that consist of two linear pooling layers for pooling the input cube features from both modality and temporal directions, separately. To capture rich modality-temporal information and facilitate our deep bilinear learning, a new action feature called modality-temporal cube is presented in a tensor structure for characterizing RGB-D actions from a comprehensive perspective. Our method is extensively tested on two public datasets with four different evaluation settings, and the results show that the proposed method outperforms the state-of-the-art approaches. |
| Tasks | Temporal Action Localization |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/HU_Jian-Fang_Deep_Bilinear_Learning_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/HU_Jian-Fang_Deep_Bilinear_Learning_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/deep-bilinear-learning-for-rgb-d-action |
| Repo | |
| Framework | |
Multi-Task Learning by Maximizing Statistical Dependence
| Title | Multi-Task Learning by Maximizing Statistical Dependence |
| Authors | Youssef A. Mejjati, Darren Cosker, Kwang In Kim |
| Abstract | We present a new multi-task learning (MTL) approach that can be applied to multiple heterogeneous task estimators. Our motivation is that the best task estimator could change depending on the task itself. For example, we may have a deep neural network for the first task and a Gaussian process for the second task. Classical MTL approaches cannot handle this case, as they require the same model or even the same parameter types for all tasks. We tackle this by considering task-specific estimators as random variables. Then, the task relationships are discovered by measuring the statistical dependence between each pair of random variables. By doing so, our model is independent of the parametric nature of each task, and is even agnostic to the existence of such parametric formulation. We compare our algorithm with existing MTL approaches on challenging real world ranking and regression datasets, and show that our approach achieves comparable or better performance without knowing the parametric form. |
| Tasks | Multi-Task Learning |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Mejjati_Multi-Task_Learning_by_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Mejjati_Multi-Task_Learning_by_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/multi-task-learning-by-maximizing-statistical |
| Repo | |
| Framework | |
Affine Correspondences between Central Cameras for Rapid Relative Pose Estimation
| Title | Affine Correspondences between Central Cameras for Rapid Relative Pose Estimation |
| Authors | Ivan Eichhardt, Dmitry Chetverikov |
| Abstract | This paper presents a novel algorithm to estimate the relative pose, i.e. the 3D rotation and translation of two cameras, from two affine correspondences (ACs) considering any central camera model. The solver is built on new epipolar constraints describing the relationship of an AC and any central views. We also show that the pinhole case is a specialization of the proposed approach. Benefiting from the low number of required correspondences, robust estimators like LO-RANSAC need fewer samples, and thus terminate earlier than using the five-point method. Tests on publicly available datasets containing pinhole, fisheye and catadioptric camera images confirmed that the method often leads to results superior to the state-of-the-art in terms of geometric accuracy. |
| Tasks | Pose Estimation |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Ivan_Eichhardt_Affine_Correspondences_between_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Ivan_Eichhardt_Affine_Correspondences_between_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/affine-correspondences-between-central |
| Repo | |
| Framework | |
Interleaved Structured Sparse Convolutional Neural Networks
| Title | Interleaved Structured Sparse Convolutional Neural Networks |
| Authors | Guotian Xie, Jingdong Wang, Ting Zhang, Jianhuang Lai, Richang Hong, Guo-Jun Qi |
| Abstract | In this paper, we study the problem of designing efficient convolutional neural network architectures with the interest in eliminating the redundancy in convolution kernels. In addition to structured sparse kernels, low-rank kernels and the product of low-rank kernels,the product of structured sparse kernels, which is a framework for interpreting the recently-developed interleaved group convolutions (IGC) and its variants (e.g. , Xception), has been attracting increasing interests. Motivated by the observation that the convolutions contained in a group convolution in IGC can be further decomposed in the same manner, we present a modularized building block, {IGC-V2:}interleaved structured sparse convolutions. It generalizes interleaved group convolutions, which is composed of two structured sparse kernels, to the product of more structured sparse kernels, further eliminating the redundancy. We present the complementary condition and the balance condition to guide the design of structured sparse kernels, obtaining a balance between three aspects: model size and computation complexity and classification accuracy. Experimental results demonstrate the advantage on the balance between these three aspects compared to interleaved group convolutions and Xception and competitive performance with other state-of-the-art architecture design methods. |
| Tasks | |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Xie_Interleaved_Structured_Sparse_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Xie_Interleaved_Structured_Sparse_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/interleaved-structured-sparse-convolutional |
| Repo | |
| Framework | |
diaNED: Time-Aware Named Entity Disambiguation for Diachronic Corpora
| Title | diaNED: Time-Aware Named Entity Disambiguation for Diachronic Corpora |
| Authors | Prabal Agarwal, Jannik Str{"o}tgen, Luciano del Corro, Johannes Hoffart, Gerhard Weikum |
| Abstract | Named Entity Disambiguation (NED) systems perform well on news articles and other texts covering a specific time interval. However, NED quality drops when inputs span long time periods like in archives or historic corpora. This paper presents the first time-aware method for NED that resolves ambiguities even when mention contexts give only few cues. The method is based on computing temporal signatures for entities and comparing these to the temporal contexts of input mentions. Our experiments show superior quality on a newly created diachronic corpus. |
| Tasks | Entity Disambiguation |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/P18-2109/ |
| https://www.aclweb.org/anthology/P18-2109 | |
| PWC | https://paperswithcode.com/paper/dianed-time-aware-named-entity-disambiguation |
| Repo | |
| Framework | |
Systematic Study of Long Tail Phenomena in Entity Linking
| Title | Systematic Study of Long Tail Phenomena in Entity Linking |
| Authors | Filip Ilievski, Piek Vossen, Stefan Schlobach |
| Abstract | State-of-the-art entity linkers achieve high accuracy scores with probabilistic methods. However, these scores should be considered in relation to the properties of the datasets they are evaluated on. Until now, there has not been a systematic investigation of the properties of entity linking datasets and their impact on system performance. In this paper we report on a series of hypotheses regarding the long tail phenomena in entity linking datasets, their interaction, and their impact on system performance. Our systematic study of these hypotheses shows that evaluation datasets mainly capture head entities and only incidentally cover data from the tail, thus encouraging systems to overfit to popular/frequent and non-ambiguous cases. We find the most difficult cases of entity linking among the infrequent candidates of ambiguous forms. With our findings, we hope to inspire future designs of both entity linking systems and evaluation datasets. To support this goal, we provide a list of recommended actions for better inclusion of tail cases. |
| Tasks | Entity Linking |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1056/ |
| https://www.aclweb.org/anthology/C18-1056 | |
| PWC | https://paperswithcode.com/paper/systematic-study-of-long-tail-phenomena-in |
| Repo | |
| Framework | |
A dynamic game approach to training robust deep policies
| Title | A dynamic game approach to training robust deep policies |
| Authors | Olalekan Ogunmolu |
| Abstract | We present a method for evaluating the sensitivity of deep reinforcement learning (RL) policies. We also formulate a zero-sum dynamic game for designing robust deep reinforcement learning policies. Our approach mitigates the brittleness of policies when agents are trained in a simulated environment and are later exposed to the real world where it is hazardous to employ RL policies. This framework for training deep RL policies involve a zero-sum dynamic game against an adversarial agent, where the goal is to drive the system dynamics to a saddle region. Using a variant of the guided policy search algorithm, our agent learns to adopt robust policies that require less samples for learning the dynamics and performs better than the GPS algorithm. Without loss of generality, we demonstrate that deep RL policies trained in this fashion will be maximally robust to a ``worst” possible adversarial disturbances. | |
| Tasks | |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=rkc_hGb0Z |
| https://openreview.net/pdf?id=rkc_hGb0Z | |
| PWC | https://paperswithcode.com/paper/a-dynamic-game-approach-to-training-robust |
| Repo | |
| Framework | |
Dual Fixed-Size Ordinally Forgetting Encoding (FOFE) for Competitive Neural Language Models
| Title | Dual Fixed-Size Ordinally Forgetting Encoding (FOFE) for Competitive Neural Language Models |
| Authors | Sedtawut Watcharawittayakul, Mingbin Xu, Hui Jiang |
| Abstract | In this paper, we propose a new approach to employ the fixed-size ordinally-forgetting encoding (FOFE) (Zhang et al., 2015b) in neural languages modelling, called dual-FOFE. The main idea of dual-FOFE is that it allows to use two different forgetting factors so that it can avoid the trade-off in choosing either a small or large values for the single forgetting factor. In our experiments, we have compared the dual-FOFE based neural network language models (NNLM) against the original FOFE counterparts and various traditional NNLMs. Our results on the challenging Google Billion word corpus show that both FOFE and dual FOFE yield very strong performance while significantly reducing the computational complexity over other NNLMs. Furthermore, the proposed dual-FOFE method further gives over 10{%} improvement in perplexity over the original FOFE model. |
| Tasks | Language Modelling, Machine Translation, Speech Recognition, Text Summarization |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1502/ |
| https://www.aclweb.org/anthology/D18-1502 | |
| PWC | https://paperswithcode.com/paper/dual-fixed-size-ordinally-forgetting-encoding |
| Repo | |
| Framework | |
Exact natural gradient in deep linear networks and its application to the nonlinear case
| Title | Exact natural gradient in deep linear networks and its application to the nonlinear case |
| Authors | Alberto Bernacchia, Mate Lengyel, Guillaume Hennequin |
| Abstract | Stochastic gradient descent (SGD) remains the method of choice for deep learning, despite the limitations arising for ill-behaved objective functions. In cases where it could be estimated, the natural gradient has proven very effective at mitigating the catastrophic effects of pathological curvature in the objective function, but little is known theoretically about its convergence properties, and it has yet to find a practical implementation that would scale to very deep and large networks. Here, we derive an exact expression for the natural gradient in deep linear networks, which exhibit pathological curvature similar to the nonlinear case. We provide for the first time an analytical solution for its convergence rate, showing that the loss decreases exponentially to the global minimum in parameter space. Our expression for the natural gradient is surprisingly simple, computationally tractable, and explains why some approximations proposed previously work well in practice. This opens new avenues for approximating the natural gradient in the nonlinear case, and we show in preliminary experiments that our online natural gradient descent outperforms SGD on MNIST autoencoding while sharing its computational simplicity. |
| Tasks | |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7834-exact-natural-gradient-in-deep-linear-networks-and-its-application-to-the-nonlinear-case |
| http://papers.nips.cc/paper/7834-exact-natural-gradient-in-deep-linear-networks-and-its-application-to-the-nonlinear-case.pdf | |
| PWC | https://paperswithcode.com/paper/exact-natural-gradient-in-deep-linear |
| Repo | |
| Framework | |
Spotlight: Optimizing Device Placement for Training Deep Neural Networks
| Title | Spotlight: Optimizing Device Placement for Training Deep Neural Networks |
| Authors | Yuanxiang Gao, Li Chen, Baochun Li |
| Abstract | Training deep neural networks (DNNs) requires an increasing amount of computation resources, and it becomes typical to use a mixture of GPU and CPU devices. Due to the heterogeneity of these devices, a recent challenge is how each operation in a neural network can be optimally placed on these devices, so that the training process can take the shortest amount of time possible. The current state-of-the-art solution uses reinforcement learning based on the policy gradient method, and it suffers from suboptimal training times. In this paper, we propose Spotlight, a new reinforcement learning algorithm based on proximal policy optimization, designed specifically for finding an optimal device placement for training DNNs. The design of our new algorithm relies upon a new model of the device placement problem: by modeling it as a Markov decision process with multiple stages, we are able to prove that Spotlight achieves a theoretical guarantee on performance improvements. We have implemented Spotlight in the CIFAR-10 benchmark and deployed it on the Google Cloud platform. Extensive experiments have demonstrated that the training time with placements recommended by Spotlight is 60.9% of that recommended by the policy gradient method. |
| Tasks | |
| Published | 2018-07-01 |
| URL | https://icml.cc/Conferences/2018/Schedule?showEvent=2032 |
| http://proceedings.mlr.press/v80/gao18a/gao18a.pdf | |
| PWC | https://paperswithcode.com/paper/spotlight-optimizing-device-placement-for |
| Repo | |
| Framework | |
