February 2, 2020

3163 words 15 mins read

Paper Group AWR 13

TERA: the Toxicological Effect and Risk Assessment Knowledge Graph. More About Covariance Descriptors for Image Set Coding: Log-Euclidean Framework based Kernel Matrix Representation. Ludii – The Ludemic General Game System. Improving Noise Tolerance of Mixed-Signal Neural Networks. Learning Configuration Space Belief Model from Collision Checks f …

TERA: the Toxicological Effect and Risk Assessment Knowledge Graph


Title	TERA: the Toxicological Effect and Risk Assessment Knowledge Graph
Authors	Erik Bryhn Myklebust, Ernesto Jimenez-Ruiz, Jiaoyan Chen, Raoul Wolf, Knut Erik Tollefsen
Abstract	Ecological risk assessment requires large amounts of chemical effect data from laboratory experiments. Due to experimental effort and animal welfare concerns it is desired to extrapolate data from existing sources. To cover the required chemical effect data several data sources need to be integrated to enable their interoperability. In this paper we introduce the Toxicological Effect and Risk Assessment (TERA) knowledge graph, which aims at providing such integrated view, and the data preparation and steps followed to construct this knowledge graph. We also present the applications of TERA for chemical effect prediction and the potential applications within the Semantic Web community.
Tasks
Published	2019-08-27
URL	https://arxiv.org/abs/1908.10128v5
PDF	https://arxiv.org/pdf/1908.10128v5.pdf
PWC	https://paperswithcode.com/paper/enabling-semantic-data-access-for
Repo	https://github.com/Erik-BM/NIVAUC
Framework	tf

More About Covariance Descriptors for Image Set Coding: Log-Euclidean Framework based Kernel Matrix Representation


Title	More About Covariance Descriptors for Image Set Coding: Log-Euclidean Framework based Kernel Matrix Representation
Authors	Kai-Xuan Chen, Xiao-Jun Wu, Jie-Yi Ren, Rui Wang, Josef Kittler
Abstract	We consider a family of structural descriptors for visual data, namely covariance descriptors (CovDs) that lie on a non-linear symmetric positive definite (SPD) manifold, a special type of Riemannian manifolds. We propose an improved version of CovDs for image set coding by extending the traditional CovDs from Euclidean space to the SPD manifold. Specifically, the manifold of SPD matrices is a complete inner product space with the operations of logarithmic multiplication and scalar logarithmic multiplication defined in the Log-Euclidean framework. In this framework, we characterise covariance structure in terms of the arc-cosine kernel which satisfies Mercer’s condition and propose the operation of mean centralization on SPD matrices. Furthermore, we combine arc-cosine kernels of different orders using mixing parameters learnt by kernel alignment in a supervised manner. Our proposed framework provides a lower-dimensional and more discriminative data representation for the task of image set classification. The experimental results demonstrate its superior performance, measured in terms of recognition accuracy, as compared with the state-of-the-art methods.
Tasks
Published	2019-09-16
URL	https://arxiv.org/abs/1909.07273v2
PDF	https://arxiv.org/pdf/1909.07273v2.pdf
PWC	https://paperswithcode.com/paper/more-about-covariance-descriptors-for-image
Repo	https://github.com/Kai-Xuan/iCovDs
Framework	none

Ludii – The Ludemic General Game System


Title	Ludii – The Ludemic General Game System
Authors	Éric Piette, Dennis J. N. J. Soemers, Matthew Stephenson, Chiara F. Sironi, Mark H. M. Winands, Cameron Browne
Abstract	While current General Game Playing (GGP) systems facilitate useful research in Artificial Intelligence (AI) for game-playing, they are often somewhat specialised and computationally inefficient. In this paper, we describe the “ludemic” general game system Ludii, which has the potential to provide an efficient tool for AI researchers as well as game designers, historians, educators and practitioners in related fields. Ludii defines games as structures of ludemes – high-level, easily understandable game concepts – which allows for concise and human-understandable game descriptions. We formally describe Ludii and outline its main benefits: generality, extensibility, understandability and efficiency. Experimentally, Ludii outperforms one of the most efficient Game Description Language (GDL) reasoners, based on a propositional network, in all games available in the Tiltyard GGP repository. Moreover, Ludii is also competitive in terms of performance with the more recently proposed Regular Boardgames (RBG) system, and has various advantages in qualitative aspects such as generality.
Tasks
Published	2019-05-13
URL	https://arxiv.org/abs/1905.05013v3
PDF	https://arxiv.org/pdf/1905.05013v3.pdf
PWC	https://paperswithcode.com/paper/ludii-the-ludemic-general-game-system
Repo	https://github.com/Ludeme/LudiiExampleAI
Framework	none

Improving Noise Tolerance of Mixed-Signal Neural Networks


Title	Improving Noise Tolerance of Mixed-Signal Neural Networks
Authors	Michael Klachko, Mohammad Reza Mahmoodi, Dmitri B. Strukov
Abstract	Mixed-signal hardware accelerators for deep learning achieve orders of magnitude better power efficiency than their digital counterparts. In the ultra-low power consumption regime, limited signal precision inherent to analog computation becomes a challenge. We perform a case study of a 6-layer convolutional neural network running on a mixed-signal accelerator and evaluate its sensitivity to hardware specific noise. We apply various methods to improve noise robustness of the network and demonstrate an effective way to optimize useful signal ranges through adaptive signal clipping. The resulting model is robust enough to achieve 80.2% classification accuracy on CIFAR-10 dataset with just 1.4 mW power budget, while 6 mW budget allows us to achieve 87.1% accuracy, which is within 1% of the software baseline. For comparison, the unoptimized version of the same model achieves only 67.7% accuracy at 1.4 mW and 78.6% at 6 mW.
Tasks
Published	2019-04-02
URL	http://arxiv.org/abs/1904.01705v1
PDF	http://arxiv.org/pdf/1904.01705v1.pdf
PWC	https://paperswithcode.com/paper/improving-noise-tolerance-of-mixed-signal
Repo	https://github.com/michaelklachko/noisynet
Framework	pytorch

Learning Configuration Space Belief Model from Collision Checks for Motion Planning


Title	Learning Configuration Space Belief Model from Collision Checks for Motion Planning
Authors	Sumit Kumar, Shushman Choudhary, Siddhartha Srinivasa
Abstract	For motion planning in high dimensional configuration spaces, a significant computational bottleneck is collision detection. Our aim is to reduce the expected number of collision checks by creating a belief model of the configuration space using results from collision tests. We assume the robot’s configuration space to be a continuous ambient space whereby neighbouring points tend to share the same collision state. This enables us to formulate a probabilistic model that assigns to unevaluated configurations a belief estimate of being collision-free. We have presented a detailed comparative analysis of various kNN methods and distance metrics used to evaluate C-space belief. We have also proposed a weighting matrix in C-space to improve the performance of kNN methods. Moreover, we have proposed a topological method that exploits the higher order structure of the C-space to generate a belief model. Our results indicate that our proposed topological method outperforms kNN methods by achieving higher model accuracy while being computationally efficient.
Tasks	Motion Planning
Published	2019-01-22
URL	http://arxiv.org/abs/1901.07646v2
PDF	http://arxiv.org/pdf/1901.07646v2.pdf
PWC	https://paperswithcode.com/paper/learning-configuration-space-belief-model
Repo	https://github.com/sumitsk/cspace_belief
Framework	none

Understanding and Improving Transformer From a Multi-Particle Dynamic System Point of View


Title	Understanding and Improving Transformer From a Multi-Particle Dynamic System Point of View
Authors	Yiping Lu, Zhuohan Li, Di He, Zhiqing Sun, Bin Dong, Tao Qin, Liwei Wang, Tie-Yan Liu
Abstract	The Transformer architecture is widely used in natural language processing. Despite its success, the design principle of the Transformer remains elusive. In this paper, we provide a novel perspective towards understanding the architecture: we show that the Transformer can be mathematically interpreted as a numerical Ordinary Differential Equation (ODE) solver for a convection-diffusion equation in a multi-particle dynamic system. In particular, how words in a sentence are abstracted into contexts by passing through the layers of the Transformer can be interpreted as approximating multiple particles’ movement in the space using the Lie-Trotter splitting scheme and the Euler’s method. Given this ODE’s perspective, the rich literature of numerical analysis can be brought to guide us in designing effective structures beyond the Transformer. As an example, we propose to replace the Lie-Trotter splitting scheme by the Strang-Marchuk splitting scheme, a scheme that is more commonly used and with much lower local truncation errors. The Strang-Marchuk splitting scheme suggests that the self-attention and position-wise feed-forward network (FFN) sub-layers should not be treated equally. Instead, in each layer, two position-wise FFN sub-layers should be used, and the self-attention sub-layer is placed in between. This leads to a brand new architecture. Such an FFN-attention-FFN layer is “Macaron-like”, and thus we call the network with this new architecture the Macaron Net. Through extensive experiments, we show that the Macaron Net is superior to the Transformer on both supervised and unsupervised learning tasks. The reproducible codes and pretrained models can be found at https://github.com/zhuohan123/macaron-net
Tasks
Published	2019-06-06
URL	https://arxiv.org/abs/1906.02762v1
PDF	https://arxiv.org/pdf/1906.02762v1.pdf
PWC	https://paperswithcode.com/paper/understanding-and-improving-transformer-from
Repo	https://github.com/zhuohan123/macaron-net
Framework	pytorch

Unsupervised Person Image Generation with Semantic Parsing Transformation


Title	Unsupervised Person Image Generation with Semantic Parsing Transformation
Authors	Sijie Song, Wei Zhang, Jiaying Liu, Tao Mei
Abstract	In this paper, we address unsupervised pose-guided person image generation, which is known challenging due to non-rigid deformation. Unlike previous methods learning a rock-hard direct mapping between human bodies, we propose a new pathway to decompose the hard mapping into two more accessible subtasks, namely, semantic parsing transformation and appearance generation. Firstly, a semantic generative network is proposed to transform between semantic parsing maps, in order to simplify the non-rigid deformation learning. Secondly, an appearance generative network learns to synthesize semantic-aware textures. Thirdly, we demonstrate that training our framework in an end-to-end manner further refines the semantic maps and final results accordingly. Our method is generalizable to other semantic-aware person image generation tasks, eg, clothing texture transfer and controlled image manipulation. Experimental results demonstrate the superiority of our method on DeepFashion and Market-1501 datasets, especially in keeping the clothing attributes and better body shapes.
Tasks	Image Generation, Semantic Parsing
Published	2019-04-06
URL	http://arxiv.org/abs/1904.03379v2
PDF	http://arxiv.org/pdf/1904.03379v2.pdf
PWC	https://paperswithcode.com/paper/unsupervised-person-image-generation-with
Repo	https://github.com/SijieSong/person_generation_spt
Framework	pytorch

Self-Supervised Learning for Contextualized Extractive Summarization


Title	Self-Supervised Learning for Contextualized Extractive Summarization
Authors	Hong Wang, Xin Wang, Wenhan Xiong, Mo Yu, Xiaoxiao Guo, Shiyu Chang, William Yang Wang
Abstract	Existing models for extractive summarization are usually trained from scratch with a cross-entropy loss, which does not explicitly capture the global context at the document level. In this paper, we aim to improve this task by introducing three auxiliary pre-training tasks that learn to capture the document-level context in a self-supervised fashion. Experiments on the widely-used CNN/DM dataset validate the effectiveness of the proposed auxiliary tasks. Furthermore, we show that after pre-training, a clean model with simple building blocks is able to outperform previous state-of-the-art that are carefully designed.
Tasks
Published	2019-06-11
URL	https://arxiv.org/abs/1906.04466v1
PDF	https://arxiv.org/pdf/1906.04466v1.pdf
PWC	https://paperswithcode.com/paper/self-supervised-learning-for-contextualized
Repo	https://github.com/hongwang600/Summarization
Framework	pytorch

ULDor: A Universal Lesion Detector for CT Scans with Pseudo Masks and Hard Negative Example Mining


Title	ULDor: A Universal Lesion Detector for CT Scans with Pseudo Masks and Hard Negative Example Mining
Authors	Youbao Tang, Ke Yan, Yuxing Tang, Jiamin Liu, Jing Xiao, Ronald M. Summers
Abstract	Automatic lesion detection from computed tomography (CT) scans is an important task in medical imaging analysis. It is still very challenging due to similar appearances (e.g. intensity and texture) between lesions and other tissues, making it especially difficult to develop a universal lesion detector. Instead of developing a specific-type lesion detector, this work builds a Universal Lesion Detector (ULDor) based on Mask R-CNN, which is able to detect all different kinds of lesions from whole body parts. As a state-of-the-art object detector, Mask R-CNN adds a branch for predicting segmentation masks on each Region of Interest (RoI) to improve the detection performance. However, it is almost impossible to manually annotate a large-scale dataset with pixel-level lesion masks to train the Mask R-CNN for lesion detection. To address this problem, this work constructs a pseudo mask for each lesion region that can be considered as a surrogate of the real mask, based on which the Mask R-CNN is employed for lesion detection. On the other hand, this work proposes a hard negative example mining strategy to reduce the false positives for improving the detection performance. Experimental results on the NIH DeepLesion dataset demonstrate that the ULDor is enhanced using pseudo masks and the proposed hard negative example mining strategy and achieves a sensitivity of 86.21% with five false positives per image.
Tasks	Computed Tomography (CT)
Published	2019-01-18
URL	http://arxiv.org/abs/1901.06359v1
PDF	http://arxiv.org/pdf/1901.06359v1.pdf
PWC	https://paperswithcode.com/paper/uldor-a-universal-lesion-detector-for-ct
Repo	https://github.com/fsafe/Capstone
Framework	pytorch

Are We Modeling the Task or the Annotator? An Investigation of Annotator Bias in Natural Language Understanding Datasets


Title	Are We Modeling the Task or the Annotator? An Investigation of Annotator Bias in Natural Language Understanding Datasets
Authors	Mor Geva, Yoav Goldberg, Jonathan Berant
Abstract	Crowdsourcing has been the prevalent paradigm for creating natural language understanding datasets in recent years. A common crowdsourcing practice is to recruit a small number of high-quality workers, and have them massively generate examples. Having only a few workers generate the majority of examples raises concerns about data diversity, especially when workers freely generate sentences. In this paper, we perform a series of experiments showing these concerns are evident in three recent NLP datasets. We show that model performance improves when training with annotator identifiers as features, and that models are able to recognize the most productive annotators. Moreover, we show that often models do not generalize well to examples from annotators that did not contribute to the training set. Our findings suggest that annotator bias should be monitored during dataset creation, and that test set annotators should be disjoint from training set annotators.
Tasks
Published	2019-08-21
URL	https://arxiv.org/abs/1908.07898v2
PDF	https://arxiv.org/pdf/1908.07898v2.pdf
PWC	https://paperswithcode.com/paper/190807898
Repo	https://github.com/mega002/annotator_bias
Framework	tf

All Graphs Lead to Rome: Learning Geometric and Cycle-Consistent Representations with Graph Convolutional Networks


Title	All Graphs Lead to Rome: Learning Geometric and Cycle-Consistent Representations with Graph Convolutional Networks
Authors	Stephen Phillips, Kostas Daniilidis
Abstract	Image feature matching is a fundamental part of many geometric computer vision applications, and using multiple images can improve performance. In this work, we formulate multi-image matching as a graph embedding problem then use a Graph Convolutional Network to learn an appropriate embedding function for aligning image features. We use cycle consistency to train our network in an unsupervised fashion, since ground truth correspondence is difficult or expensive to aquire. In addition, geometric consistency losses can be added at training time, even if the information is not available in the test set, unlike previous approaches that optimize cycle consistency directly. To the best of our knowledge, no other works have used learning for multi-image feature matching. Our experiments show that our method is competitive with other optimization based approaches.
Tasks	Graph Embedding
Published	2019-01-07
URL	http://arxiv.org/abs/1901.02078v1
PDF	http://arxiv.org/pdf/1901.02078v1.pdf
PWC	https://paperswithcode.com/paper/all-graphs-lead-to-rome-learning-geometric
Repo	https://github.com/daniilidis-group/all-graphs-lead-to-rome
Framework	tf

Barycenters of Natural Images – Constrained Wasserstein Barycenters for Image Morphing


Title	Barycenters of Natural Images – Constrained Wasserstein Barycenters for Image Morphing
Authors	Dror Simon, Aviad Aberdam
Abstract	Image interpolation, or image morphing, refers to a visual transition between two (or more) input images. For such a transition to look visually appealing, its desirable properties are (i) to be smooth; (ii) to apply the minimal required change in the image; and (iii) to seem “real”, avoiding unnatural artifacts in each image in the transition. To obtain a smooth and straightforward transition, one may adopt the well-known Wasserstein Barycenter Problem (WBP). While this approach guarantees minimal changes under the Wasserstein metric, the resulting images might seem unnatural. In this work, we propose a novel approach for image morphing that possesses all three desired properties. To this end, we define a constrained variant of the WBP that enforces the intermediate images to satisfy an image prior. We describe an algorithm that solves this problem and demonstrate it using the sparse prior and generative adversarial networks.
Tasks	Image Morphing
Published	2019-12-24
URL	https://arxiv.org/abs/1912.11545v1
PDF	https://arxiv.org/pdf/1912.11545v1.pdf
PWC	https://paperswithcode.com/paper/barycenters-of-natural-images-constrained
Repo	https://github.com/drorsimon/image_barycenters
Framework	pytorch

Dense Intrinsic Appearance Flow for Human Pose Transfer


Title	Dense Intrinsic Appearance Flow for Human Pose Transfer
Authors	Yining Li, Chen Huang, Chen Change Loy
Abstract	We present a novel approach for the task of human pose transfer, which aims at synthesizing a new image of a person from an input image of that person and a target pose. We address the issues of limited correspondences identified between keypoints only and invisible pixels due to self-occlusion. Unlike existing methods, we propose to estimate dense and intrinsic 3D appearance flow to better guide the transfer of pixels between poses. In particular, we wish to generate the 3D flow from just the reference and target poses. Training a network for this purpose is non-trivial, especially when the annotations for 3D appearance flow are scarce by nature. We address this problem through a flow synthesis stage. This is achieved by fitting a 3D model to the given pose pair and project them back to the 2D plane to compute the dense appearance flow for training. The synthesized ground-truths are then used to train a feedforward network for efficient mapping from the input and target skeleton poses to the 3D appearance flow. With the appearance flow, we perform feature warping on the input image and generate a photorealistic image of the target pose. Extensive results on DeepFashion and Market-1501 datasets demonstrate the effectiveness of our approach over existing methods. Our code is available at http://mmlab.ie.cuhk.edu.hk/projects/pose-transfer
Tasks	Pose Transfer
Published	2019-03-27
URL	http://arxiv.org/abs/1903.11326v1
PDF	http://arxiv.org/pdf/1903.11326v1.pdf
PWC	https://paperswithcode.com/paper/dense-intrinsic-appearance-flow-for-human
Repo	https://github.com/ly015/intrinsic_flow
Framework	pytorch

Exemplar Guided Face Image Super-Resolution without Facial Landmarks


Title	Exemplar Guided Face Image Super-Resolution without Facial Landmarks
Authors	Berk Dogan, Shuhang Gu, Radu Timofte
Abstract	Nowadays, due to the ubiquitous visual media there are vast amounts of already available high-resolution (HR) face images. Therefore, for super-resolving a given very low-resolution (LR) face image of a person it is very likely to find another HR face image of the same person which can be used to guide the process. In this paper, we propose a convolutional neural network (CNN)-based solution, namely GWAInet, which applies super-resolution (SR) by a factor 8x on face images guided by another unconstrained HR face image of the same person with possible differences in age, expression, pose or size. GWAInet is trained in an adversarial generative manner to produce the desired high quality perceptual image results. The utilization of the HR guiding image is realized via the use of a warper subnetwork that aligns its contents to the input image and the use of a feature fusion chain for the extracted features from the warped guiding image and the input image. In training, the identity loss further helps in preserving the identity related features by minimizing the distance between the embedding vectors of SR and HR ground truth images. Contrary to the current state-of-the-art in face super-resolution, our method does not require facial landmark points for its training, which helps its robustness and allows it to produce fine details also for the surrounding face region in a uniform manner. Our method GWAInet produces photo-realistic images in upscaling factor 8x and outperforms state-of-the-art in quantitative terms and perceptual quality.
Tasks	Image Super-Resolution, Super-Resolution
Published	2019-06-17
URL	https://arxiv.org/abs/1906.07078v1
PDF	https://arxiv.org/pdf/1906.07078v1.pdf
PWC	https://paperswithcode.com/paper/exemplar-guided-face-image-super-resolution
Repo	https://github.com/berkdogan2/GWAInet
Framework	tf

Procedural Content Generation through Quality Diversity


Title	Procedural Content Generation through Quality Diversity
Authors	Daniele Gravina, Ahmed Khalifa, Antonios Liapis, Julian Togelius, Georgios N. Yannakakis
Abstract	Quality-diversity (QD) algorithms search for a set of good solutions which cover a space as defined by behavior metrics. This simultaneous focus on quality and diversity with explicit metrics sets QD algorithms apart from standard single- and multi-objective evolutionary algorithms, as well as from diversity preservation approaches such as niching. These properties open up new avenues for artificial intelligence in games, in particular for procedural content generation. Creating multiple systematically varying solutions allows new approaches to creative human-AI interaction as well as adaptivity. In the last few years, a handful of applications of QD to procedural content generation and game playing have been proposed; we discuss these and propose challenges for future work.
Tasks
Published	2019-07-09
URL	https://arxiv.org/abs/1907.04053v1
PDF	https://arxiv.org/pdf/1907.04053v1.pdf
PWC	https://paperswithcode.com/paper/procedural-content-generation-through-quality
Repo	https://github.com/aadharna/UntouchableThunder
Framework	pytorch