October 21, 2019

2952 words 14 mins read

Paper Group AWR 104

Reliability and Learnability of Human Bandit Feedback for Sequence-to-Sequence Reinforcement Learning. Coherence Modeling of Asynchronous Conversations: A Neural Entity Grid Approach. Gradient target propagation. Deep End-to-end Fingerprint Denoising and Inpainting. Occupancy Networks: Learning 3D Reconstruction in Function Space. EANet: Enhancing …

Reliability and Learnability of Human Bandit Feedback for Sequence-to-Sequence Reinforcement Learning


Title	Reliability and Learnability of Human Bandit Feedback for Sequence-to-Sequence Reinforcement Learning
Authors	Julia Kreutzer, Joshua Uyheng, Stefan Riezler
Abstract	We present a study on reinforcement learning (RL) from human bandit feedback for sequence-to-sequence learning, exemplified by the task of bandit neural machine translation (NMT). We investigate the reliability of human bandit feedback, and analyze the influence of reliability on the learnability of a reward estimator, and the effect of the quality of reward estimates on the overall RL task. Our analysis of cardinal (5-point ratings) and ordinal (pairwise preferences) feedback shows that their intra- and inter-annotator $\alpha$-agreement is comparable. Best reliability is obtained for standardized cardinal feedback, and cardinal feedback is also easiest to learn and generalize from. Finally, improvements of over 1 BLEU can be obtained by integrating a regression-based reward estimator trained on cardinal feedback for 800 translations into RL for NMT. This shows that RL is possible even from small amounts of fairly reliable human feedback, pointing to a great potential for applications at larger scale.
Tasks	Machine Translation
Published	2018-05-27
URL	http://arxiv.org/abs/1805.10627v3
PDF	http://arxiv.org/pdf/1805.10627v3.pdf
PWC	https://paperswithcode.com/paper/reliability-and-learnability-of-human-bandit
Repo	https://github.com/juliakreutzer/bandit-neuralmonkey
Framework	tf

Coherence Modeling of Asynchronous Conversations: A Neural Entity Grid Approach


Title	Coherence Modeling of Asynchronous Conversations: A Neural Entity Grid Approach
Authors	Tasnim Mohiuddin, Shafiq Joty, Dat Tien Nguyen
Abstract	We propose a novel coherence model for written asynchronous conversations (e.g., forums, emails), and show its applications in coherence assessment and thread reconstruction tasks. We conduct our research in two steps. First, we propose improvements to the recently proposed neural entity grid model by lexicalizing its entity transitions. Then, we extend the model to asynchronous conversations by incorporating the underlying conversational structure in the entity grid representation and feature computation. Our model achieves state of the art results on standard coherence assessment tasks in monologue and conversations outperforming existing models. We also demonstrate its effectiveness in reconstructing thread structures.
Tasks
Published	2018-05-06
URL	http://arxiv.org/abs/1805.02275v1
PDF	http://arxiv.org/pdf/1805.02275v1.pdf
PWC	https://paperswithcode.com/paper/coherence-modeling-of-asynchronous
Repo	https://github.com/taasnim/conv-coherence
Framework	tf

Gradient target propagation


Title	Gradient target propagation
Authors	Tiago de Souza Farias, Jonas Maziero
Abstract	We report a learning rule for neural networks that computes how much each neuron should contribute to minimize a giving cost function via the estimation of its target value. By theoretical analysis, we show that this learning rule contains backpropagation, Hebian learning, and additional terms. We also give a general technique for weights initialization. Our results are at least as good as those obtained with backpropagation. The neural networks are trained and tested in three problems: MNIST, MNIST-Fashion, and CIFAR-10 datasets. The associated code is available at https://github.com/tiago939/target.
Tasks
Published	2018-10-19
URL	http://arxiv.org/abs/1810.09284v3
PDF	http://arxiv.org/pdf/1810.09284v3.pdf
PWC	https://paperswithcode.com/paper/gradient-target-propagation
Repo	https://github.com/tiago939/target
Framework	none

Deep End-to-end Fingerprint Denoising and Inpainting


Title	Deep End-to-end Fingerprint Denoising and Inpainting
Authors	Youness Mansar
Abstract	This work describes our winning solution for the Chalearn LAP In-painting Competition Track 3 - Fingerprint Denoising and In-painting. The objective of this competition is to reduce noise, remove the background pattern and replace missing parts of fingerprint images in order to simplify the verification made by humans or third-party software. In this paper, we use a U-Net like CNN model that performs all those steps end-to-end after being trained on the competition data in a fully supervised way. This architecture and training procedure achieved the best results on all three metrics of the competition.
Tasks	Denoising
Published	2018-07-31
URL	http://arxiv.org/abs/1807.11888v3
PDF	http://arxiv.org/pdf/1807.11888v3.pdf
PWC	https://paperswithcode.com/paper/deep-end-to-end-fingerprint-denoising-and
Repo	https://github.com/CVxTz/fingerprint_denoising
Framework	none

Occupancy Networks: Learning 3D Reconstruction in Function Space


Title	Occupancy Networks: Learning 3D Reconstruction in Function Space
Authors	Lars Mescheder, Michael Oechsle, Michael Niemeyer, Sebastian Nowozin, Andreas Geiger
Abstract	With the advent of deep neural networks, learning-based approaches for 3D reconstruction have gained popularity. However, unlike for images, in 3D there is no canonical representation which is both computationally and memory efficient yet allows for representing high-resolution geometry of arbitrary topology. Many of the state-of-the-art learning-based 3D reconstruction approaches can hence only represent very coarse 3D geometry or are limited to a restricted domain. In this paper, we propose Occupancy Networks, a new representation for learning-based 3D reconstruction methods. Occupancy networks implicitly represent the 3D surface as the continuous decision boundary of a deep neural network classifier. In contrast to existing approaches, our representation encodes a description of the 3D output at infinite resolution without excessive memory footprint. We validate that our representation can efficiently encode 3D structure and can be inferred from various kinds of input. Our experiments demonstrate competitive results, both qualitatively and quantitatively, for the challenging tasks of 3D reconstruction from single images, noisy point clouds and coarse discrete voxel grids. We believe that occupancy networks will become a useful tool in a wide variety of learning-based 3D tasks.
Tasks	3D Reconstruction, 3D Shape Representation
Published	2018-12-10
URL	http://arxiv.org/abs/1812.03828v2
PDF	http://arxiv.org/pdf/1812.03828v2.pdf
PWC	https://paperswithcode.com/paper/occupancy-networks-learning-3d-reconstruction
Repo	https://github.com/LMescheder/Occupancy-Networks
Framework	pytorch

EANet: Enhancing Alignment for Cross-Domain Person Re-identification


Title	EANet: Enhancing Alignment for Cross-Domain Person Re-identification
Authors	Houjing Huang, Wenjie Yang, Xiaotang Chen, Xin Zhao, Kaiqi Huang, Jinbin Lin, Guan Huang, Dalong Du
Abstract	Person re-identification (ReID) has achieved significant improvement under the single-domain setting. However, directly exploiting a model to new domains is always faced with huge performance drop, and adapting the model to new domains without target-domain identity labels is still challenging. In this paper, we address cross-domain ReID and make contributions for both model generalization and adaptation. First, we propose Part Aligned Pooling (PAP) that brings significant improvement for cross-domain testing. Second, we design a Part Segmentation (PS) constraint over ReID feature to enhance alignment and improve model generalization. Finally, we show that applying our PS constraint to unlabeled target domain images serves as effective domain adaptation. We conduct extensive experiments between three large datasets, Market1501, CUHK03 and DukeMTMC-reID. Our model achieves state-of-the-art performance under both source-domain and cross-domain settings. For completeness, we also demonstrate the complementarity of our model to existing domain adaptation methods. The code is available at https://github.com/huanghoujing/EANet.
Tasks	Domain Adaptation, Person Re-Identification
Published	2018-12-29
URL	http://arxiv.org/abs/1812.11369v1
PDF	http://arxiv.org/pdf/1812.11369v1.pdf
PWC	https://paperswithcode.com/paper/eanet-enhancing-alignment-for-cross-domain
Repo	https://github.com/huanghoujing/EANet
Framework	pytorch

MAGSAC: marginalizing sample consensus


Title	MAGSAC: marginalizing sample consensus
Authors	Daniel Barath, Jana Noskova, Jiri Matas
Abstract	A method called, sigma-consensus, is proposed to eliminate the need for a user-defined inlier-outlier threshold in RANSAC. Instead of estimating the noise sigma, it is marginalized over a range of noise scales. The optimized model is obtained by weighted least-squares fitting where the weights come from the marginalization over sigma of the point likelihoods of being inliers. A new quality function is proposed not requiring sigma and, thus, a set of inliers to determine the model quality. Also, a new termination criterion for RANSAC is built on the proposed marginalization approach. Applying sigma-consensus, MAGSAC is proposed with no need for a user-defined sigma and improving the accuracy of robust estimation significantly. It is superior to the state-of-the-art in terms of geometric accuracy on publicly available real-world datasets for epipolar geometry (F and E) and homography estimation. In addition, applying sigma-consensus only once as a post-processing step to the RANSAC output always improved the model quality on a wide range of vision problems without noticeable deterioration in processing time, adding a few milliseconds. The source code is at https://github.com/danini/magsac.
Tasks	Homography Estimation
Published	2018-03-20
URL	https://arxiv.org/abs/1803.07469v2
PDF	https://arxiv.org/pdf/1803.07469v2.pdf
PWC	https://paperswithcode.com/paper/magsac-marginalizing-sample-consensus
Repo	https://github.com/danini/magsac
Framework	none

Sparse, Collaborative, or Nonnegative Representation: Which Helps Pattern Classification?


Title	Sparse, Collaborative, or Nonnegative Representation: Which Helps Pattern Classification?
Authors	Jun Xu, Wangpeng An, Lei Zhang, David Zhang
Abstract	The use of sparse representation (SR) and collaborative representation (CR) for pattern classification has been widely studied in tasks such as face recognition and object categorization. Despite the success of SR/CR based classifiers, it is still arguable whether it is the $\ell_{1}$-norm sparsity or the $\ell_{2}$-norm collaborative property that brings the success of SR/CR based classification. In this paper, we investigate the use of nonnegative representation (NR) for pattern classification, which is largely ignored by previous work. Our analyses reveal that NR can boost the representation power of homogeneous samples while limiting the representation power of heterogeneous samples, making the representation sparse and discriminative simultaneously and thus providing a more effective solution to representation based classification than SR/CR. Our experiments demonstrate that the proposed NR based classifier (NRC) outperforms previous representation based classifiers. With deep features as inputs, it also achieves state-of-the-art performance on various visual classification tasks.
Tasks	Face Recognition
Published	2018-06-12
URL	http://arxiv.org/abs/1806.04329v2
PDF	http://arxiv.org/pdf/1806.04329v2.pdf
PWC	https://paperswithcode.com/paper/sparse-collaborative-or-nonnegative
Repo	https://github.com/The-Shuai/Visual-Classifier-Baselines
Framework	none

Improving Robustness of Neural Dialog Systems in a Data-Efficient Way with Turn Dropout


Title	Improving Robustness of Neural Dialog Systems in a Data-Efficient Way with Turn Dropout
Authors	Igor Shalyminov, Sungjin Lee
Abstract	Neural network-based dialog models often lack robustness to anomalous, out-of-domain (OOD) user input which leads to unexpected dialog behavior and thus considerably limits such models’ usage in mission-critical production environments. The problem is especially relevant in the setting of dialog system bootstrapping with limited training data and no access to OOD examples. In this paper, we explore the problem of robustness of such systems to anomalous input and the associated to it trade-off in accuracies on seen and unseen data. We present a new dataset for studying the robustness of dialog systems to OOD input, which is bAbI Dialog Task 6 augmented with OOD content in a controlled way. We then present turn dropout, a simple yet efficient negative sampling-based technique for improving robustness of neural dialog models. We demonstrate its effectiveness applied to Hybrid Code Network-family models (HCNs) which reach state-of-the-art results on our OOD-augmented dataset as well as the original one. Specifically, an HCN trained with turn dropout achieves state-of-the-art performance of more than 75% per-utterance accuracy on the augmented dataset’s OOD turns and 74% F1-score as an OOD detector. Furthermore, we introduce a Variational HCN enhanced with turn dropout which achieves more than 56.5% accuracy on the original bAbI Task 6 dataset, thus outperforming the initially reported HCN’s result.
Tasks
Published	2018-11-29
URL	http://arxiv.org/abs/1811.12148v1
PDF	http://arxiv.org/pdf/1811.12148v1.pdf
PWC	https://paperswithcode.com/paper/improving-robustness-of-neural-dialog-systems
Repo	https://github.com/ishalyminov/ood_robust_hcn
Framework	tf

Efficient Non-parametric Bayesian Hawkes Processes


Title	Efficient Non-parametric Bayesian Hawkes Processes
Authors	Rui Zhang, Christian Walder, Marian-Andrei Rizoiu, Lexing Xie
Abstract	In this paper, we develop an efficient nonparametric Bayesian estimation of the kernel function of Hawkes processes. The non-parametric Bayesian approach is important because it provides flexible Hawkes kernels and quantifies their uncertainty. Our method is based on the cluster representation of Hawkes processes. Utilizing the stationarity of the Hawkes process, we efficiently sample random branching structures and thus, we split the Hawkes process into clusters of Poisson processes. We derive two algorithms – a block Gibbs sampler and a maximum a posteriori estimator based on expectation maximization – and we show that our methods have a linear time complexity, both theoretically and empirically. On synthetic data, we show our methods to be able to infer flexible Hawkes triggering kernels. On two large-scale Twitter diffusion datasets, we show that our methods outperform the current state-of-the-art in goodness-of-fit and that the time complexity is linear in the size of the dataset. We also observe that on diffusions related to online videos, the learned kernels reflect the perceived longevity for different content types such as music or pets videos.
Tasks
Published	2018-10-08
URL	https://arxiv.org/abs/1810.03730v3
PDF	https://arxiv.org/pdf/1810.03730v3.pdf
PWC	https://paperswithcode.com/paper/efficient-non-parametric-bayesian-hawkes
Repo	https://github.com/RuiZhang2016/Efficient-Nonparametric-Bayesian-Hawkes-Processes
Framework	none

Style Transfer Through Back-Translation


Title	Style Transfer Through Back-Translation
Authors	Shrimai Prabhumoye, Yulia Tsvetkov, Ruslan Salakhutdinov, Alan W Black
Abstract	Style transfer is the task of rephrasing the text to contain specific stylistic properties without changing the intent or affect within the context. This paper introduces a new method for automatic style transfer. We first learn a latent representation of the input sentence which is grounded in a language translation model in order to better preserve the meaning of the sentence while reducing stylistic properties. Then adversarial generation techniques are used to make the output match the desired style. We evaluate this technique on three different style transformations: sentiment, gender and political slant. Compared to two state-of-the-art style transfer modeling techniques we show improvements both in automatic evaluation of style transfer and in manual evaluation of meaning preservation and fluency.
Tasks	Style Transfer, Text Style Transfer
Published	2018-04-24
URL	http://arxiv.org/abs/1804.09000v3
PDF	http://arxiv.org/pdf/1804.09000v3.pdf
PWC	https://paperswithcode.com/paper/style-transfer-through-back-translation
Repo	https://github.com/avshalomc/subtract
Framework	pytorch

Exploring Correlations in Multiple Facial Attributes through Graph Attention Network


Title	Exploring Correlations in Multiple Facial Attributes through Graph Attention Network
Authors	Yan Zhang, Li Sun
Abstract	Estimating multiple attributes from a single facial image gives comprehensive descriptions on the high level semantics of the face. It is naturally regarded as a multi-task supervised learning problem with a single deep CNN, in which lower layers are shared, and higher ones are task-dependent with the multi-branch structure. Within the traditional deep multi-task learning (DMTL) framework, this paper intends to fully exploit the correlations among different attributes by constructing a graph. The node in graph represents the feature vector from a particular branch for a given attribute, and the edge can be defined by either the prior knowledge or the similarity between two nodes in the embedding with a fully data-driven manner. We analyze that the attention mechanism actually takes effect in the latter case, and utilize the Graph Attention Layer (GAL) for exploring on the most relevant attribute feature and refining the task-dependant feature by considering other attributes. Experiments show that by mining the correlations among attributes, our method can improve the recognition accuracy on CelebA and LFWA dataset. And it also achieves competitive performance.
Tasks	Multi-Task Learning
Published	2018-10-22
URL	http://arxiv.org/abs/1810.09162v1
PDF	http://arxiv.org/pdf/1810.09162v1.pdf
PWC	https://paperswithcode.com/paper/exploring-correlations-in-multiple-facial
Repo	https://github.com/crazydemo/facial-attribute-classification-with-graph
Framework	tf

HOPF: Higher Order Propagation Framework for Deep Collective Classification


Title	HOPF: Higher Order Propagation Framework for Deep Collective Classification
Authors	Priyesh Vijayan, Yash Chandak, Mitesh M. Khapra, Srinivasan Parthasarathy, Balaraman Ravindran
Abstract	Given a graph where every node has certain attributes associated with it and some nodes have labels associated with them, Collective Classification (CC) is the task of assigning labels to every unlabeled node using information from the node as well as its neighbors. It is often the case that a node is not only influenced by its immediate neighbors but also by higher order neighbors, multiple hops away. Recent state-of-the-art models for CC learn end-to-end differentiable variations of Weisfeiler-Lehman (WL) kernels to aggregate multi-hop neighborhood information. In this work, we propose a Higher Order Propagation Framework, HOPF, which provides an iterative inference mechanism for these powerful differentiable kernels. Such a combination of classical iterative inference mechanism with recent differentiable kernels allows the framework to learn graph convolutional filters that simultaneously exploit the attribute and label information available in the neighborhood. Further, these iterative differentiable kernels can scale to larger hops beyond the memory limitations of existing differentiable kernels. We also show that existing WL kernel-based models suffer from the problem of Node Information Morphing where the information of the node is morphed or overwhelmed by the information of its neighbors when considering multiple hops. To address this, we propose a specific instantiation of HOPF, called the NIP models, which preserves the node information at every propagation step. The iterative formulation of NIP models further helps in incorporating distant hop information concisely as summaries of the inferred labels. We do an extensive evaluation across 11 datasets from different domains. We show that existing CC models do not provide consistent performance across datasets, while the proposed NIP model with iterative inference is more robust.
Tasks
Published	2018-05-31
URL	http://arxiv.org/abs/1805.12421v6
PDF	http://arxiv.org/pdf/1805.12421v6.pdf
PWC	https://paperswithcode.com/paper/hopf-higher-order-propagation-framework-for
Repo	https://github.com/PriyeshV/HOPF
Framework	tf

Transfer and Multi-Task Learning for Noun-Noun Compound Interpretation


Title	Transfer and Multi-Task Learning for Noun-Noun Compound Interpretation
Authors	Murhaf Fares, Stephan Oepen, Erik Velldal
Abstract	In this paper, we empirically evaluate the utility of transfer and multi-task learning on a challenging semantic classification task: semantic interpretation of noun–noun compounds. Through a comprehensive series of experiments and in-depth error analysis, we show that transfer learning via parameter initialization and multi-task learning via parameter sharing can help a neural classification model generalize over a highly skewed distribution of relations. Further, we demonstrate how dual annotation with two distinct sets of relations over the same set of compounds can be exploited to improve the overall accuracy of a neural classifier and its F1 scores on the less frequent, but more difficult relations.
Tasks	Multi-Task Learning, Transfer Learning
Published	2018-09-18
URL	http://arxiv.org/abs/1809.06748v1
PDF	http://arxiv.org/pdf/1809.06748v1.pdf
PWC	https://paperswithcode.com/paper/transfer-and-multi-task-learning-for-noun
Repo	https://github.com/ltgoslo/fun-nom
Framework	none

Learning Implicit Fields for Generative Shape Modeling


Title	Learning Implicit Fields for Generative Shape Modeling
Authors	Zhiqin Chen, Hao Zhang
Abstract	We advocate the use of implicit fields for learning generative models of shapes and introduce an implicit field decoder, called IM-NET, for shape generation, aimed at improving the visual quality of the generated shapes. An implicit field assigns a value to each point in 3D space, so that a shape can be extracted as an iso-surface. IM-NET is trained to perform this assignment by means of a binary classifier. Specifically, it takes a point coordinate, along with a feature vector encoding a shape, and outputs a value which indicates whether the point is outside the shape or not. By replacing conventional decoders by our implicit decoder for representation learning (via IM-AE) and shape generation (via IM-GAN), we demonstrate superior results for tasks such as generative shape modeling, interpolation, and single-view 3D reconstruction, particularly in terms of visual quality. Code and supplementary material are available at https://github.com/czq142857/implicit-decoder.
Tasks	3D Reconstruction, 3D Shape Representation, Representation Learning, Single-View 3D Reconstruction
Published	2018-12-06
URL	https://arxiv.org/abs/1812.02822v5
PDF	https://arxiv.org/pdf/1812.02822v5.pdf
PWC	https://paperswithcode.com/paper/learning-implicit-fields-for-generative-shape
Repo	https://github.com/czq142857/implicit-decoder
Framework	tf