February 1, 2020

3222 words 16 mins read

Paper Group AWR 328

Perspective-consistent multifocus multiview 3D reconstruction of small objects. An End-to-End Joint Learning Scheme of Image Compression and Quality Enhancement with Improved Entropy Minimization. Multi-marginal Wasserstein GAN. Fine-grained Entity Recognition with Reduced False Negatives and Large Type Coverage. Automating Whole Brain Histology to …

Perspective-consistent multifocus multiview 3D reconstruction of small objects


Title	Perspective-consistent multifocus multiview 3D reconstruction of small objects
Authors	Hengjia Li, Chuong Nguyen
Abstract	Image-based 3D reconstruction or 3D photogrammetry of small-scale objects including insects and biological specimens is challenging due to the use of high magnification lens with inherent limited depth of field, and the object’s fine structures and complex surface properties. Due to these challenges, traditional 3D reconstruction techniques cannot be applied without suitable image pre-processings. One such preprocessing technique is multifocus stacking that combines a set of partially focused images captured from the same viewing angle to create a single in-focus image. Traditional multifocus image capture uses a camera on a macro rail. Furthermore, the scale and shift are not properly considered by multifocus stacking techniques. As a consequence, the resulting in-focus images contain artifacts that violate perspective image formation. A 3D reconstruction using such images will fail to produce an accurate 3D model of the object. This paper shows how this problem can be solved effectively by a new multifocus stacking procedure which includes a new Fixed-Lens Multifocus Capture and camera calibration for image scale and shift. Initial experimental results are presented to confirm our expectation and show that the camera poses of fixed-lens images are at least 3-times less noisy than those of conventional moving lens images.
Tasks	3D Reconstruction, Calibration
Published	2019-12-06
URL	https://arxiv.org/abs/1912.03005v1
PDF	https://arxiv.org/pdf/1912.03005v1.pdf
PWC	https://paperswithcode.com/paper/perspective-consistent-multifocus-multiview
Repo	https://github.com/natowi/meshroom_publications
Framework	none

An End-to-End Joint Learning Scheme of Image Compression and Quality Enhancement with Improved Entropy Minimization


Title	An End-to-End Joint Learning Scheme of Image Compression and Quality Enhancement with Improved Entropy Minimization
Authors	Jooyoung Lee, Seunghyun Cho, Munchurl Kim
Abstract	Recently, learned image compression methods have been actively studied. Among them, entropy-minimization based approaches have achieved superior results compared to conventional image codecs such as BPG and JPEG2000. However, the quality enhancement and rate-minimization are conflictively coupled in the process of image compression. That is, maintaining high image quality entails less compression and vice versa. However, by jointly training separate quality enhancement in conjunction with image compression, the coding efficiency can be improved. In this paper, we propose a novel joint learning scheme of image compression and quality enhancement, called JointIQ-Net, as well as entropy model improvement, thus achieving significantly improved coding efficiency against the previous methods. Our proposed JointIQ-Net combines an image compression sub-network and a quality enhancement sub-network in a cascade, both of which are end-to-end trained in a combined manner within the JointIQ-Net. Also the JointIQ-Net benefits from improved entropy-minimization that newly adopts a Gussian Mixture Model (GMM) and further exploits global context to estimate the probabilities of latent representations. In order to show the effectiveness of our proposed JointIQ-Net, extensive experiments have been performed, and showed that the JointIQ-Net achieves a remarkable performance improvement in coding efficiency in terms of both PSNR and MS-SSIM, compared to the previous learned image compression methods and the conventional codecs such as VVC Intra (VTM 7.1), BPG, and JPEG2000. To the best of our knowledge, this is the first end-to-end optimized image compression method that outperforms VTM 7.1 (Intra), the latest reference software of the VVC standard, in terms of the PSNR and MS-SSIM.
Tasks	Image Compression
Published	2019-12-30
URL	https://arxiv.org/abs/1912.12817v2
PDF	https://arxiv.org/pdf/1912.12817v2.pdf
PWC	https://paperswithcode.com/paper/a-hybrid-architecture-of-jointly-learning
Repo	https://github.com/JooyoungLeeETRI/CA_Entropy_Model
Framework	none

Multi-marginal Wasserstein GAN


Title	Multi-marginal Wasserstein GAN
Authors	Jiezhang Cao, Langyuan Mo, Yifan Zhang, Kui Jia, Chunhua Shen, Mingkui Tan
Abstract	Multiple marginal matching problem aims at learning mappings to match a source domain to multiple target domains and it has attracted great attention in many applications, such as multi-domain image translation. However, addressing this problem has two critical challenges: (i) Measuring the multi-marginal distance among different domains is very intractable; (ii) It is very difficult to exploit cross-domain correlations to match the target domain distributions. In this paper, we propose a novel Multi-marginal Wasserstein GAN (MWGAN) to minimize Wasserstein distance among domains. Specifically, with the help of multi-marginal optimal transport theory, we develop a new adversarial objective function with inner- and inter-domain constraints to exploit cross-domain correlations. Moreover, we theoretically analyze the generalization performance of MWGAN, and empirically evaluate it on the balanced and imbalanced translation tasks. Extensive experiments on toy and real-world datasets demonstrate the effectiveness of MWGAN.
Tasks	Image Generation
Published	2019-11-03
URL	https://arxiv.org/abs/1911.00888v1
PDF	https://arxiv.org/pdf/1911.00888v1.pdf
PWC	https://paperswithcode.com/paper/multi-marginal-wasserstein-gan
Repo	https://github.com/caojiezhang/MWGAN
Framework	pytorch

Fine-grained Entity Recognition with Reduced False Negatives and Large Type Coverage


Title	Fine-grained Entity Recognition with Reduced False Negatives and Large Type Coverage
Authors	Abhishek Abhishek, Sanya Bathla Taneja, Garima Malik, Ashish Anand, Amit Awekar
Abstract	Fine-grained Entity Recognition (FgER) is the task of detecting and classifying entity mentions to a large set of types spanning diverse domains such as biomedical, finance and sports. We observe that when the type set spans several domains, detection of entity mention becomes a limitation for supervised learning models. The primary reason being lack of dataset where entity boundaries are properly annotated while covering a large spectrum of entity types. Our work directly addresses this issue. We propose Heuristics Allied with Distant Supervision (HAnDS) framework to automatically construct a quality dataset suitable for the FgER task. HAnDS framework exploits the high interlink among Wikipedia and Freebase in a pipelined manner, reducing annotation errors introduced by naively using distant supervision approach. Using HAnDS framework, we create two datasets, one suitable for building FgER systems recognizing up to 118 entity types based on the FIGER type hierarchy and another for up to 1115 entity types based on the TypeNet hierarchy. Our extensive empirical experimentation warrants the quality of the generated datasets. Along with this, we also provide a manually annotated dataset for benchmarking FgER systems.
Tasks
Published	2019-04-30
URL	http://arxiv.org/abs/1904.13178v1
PDF	http://arxiv.org/pdf/1904.13178v1.pdf
PWC	https://paperswithcode.com/paper/fine-grained-entity-recognition-with-reduced
Repo	https://github.com/abhipec/HAnDS
Framework	none

Automating Whole Brain Histology to MRI Registration: Implementation of a Computational Pipeline


Title	Automating Whole Brain Histology to MRI Registration: Implementation of a Computational Pipeline
Authors	Maryana Alegro, Eduardo J. L. Alho, Maria da Graca Morais Martin, Lea Teneholz Grinberg, Helmut Heinsen, Roseli de Deus Lopes, Edson Amaro-Jr, Lilla Zöllei
Abstract	Although the latest advances in MRI technology have allowed the acquisition of higher resolution images, reliable delineation of cytoarchitectural or subcortical nuclei boundaries is not possible. As a result, histological images are still required to identify the exact limits of neuroanatomical structures. However, histological processing is associated with tissue distortion and fixation artifacts, which prevent a direct comparison between the two modalities. Our group has previously proposed a histological procedure based on celloidin embedding that reduces the amount of artifacts and yields high quality whole brain histological slices. Celloidin embedded tissue, nevertheless, still bears distortions that must be corrected. We propose a computational pipeline designed to semi-automatically process the celloidin embedded histology and register them to their MRI counterparts. In this paper we report the accuracy of our pipeline in two whole brain volumes from the Brain Bank of the Brazilian Aging Brain Study Group (BBBABSG). Results were assessed by comparison of manual segmentations from two experts in both MRIs and the registered histological volumes. The two whole brain histology/MRI datasets were successfully registered using minimal user interaction. We also point to possible improvements based on recent implementations that could be added to this pipeline, potentially allowing for higher precision and further performance gains.
Tasks
Published	2019-05-22
URL	https://arxiv.org/abs/1905.09339v1
PDF	https://arxiv.org/pdf/1905.09339v1.pdf
PWC	https://paperswithcode.com/paper/automating-whole-brain-histology-to-mri
Repo	https://github.com/mary-alegro/WholeBrainRegistration
Framework	none

MassFace: an efficient implementation using triplet loss for face recognition


Title	MassFace: an efficient implementation using triplet loss for face recognition
Authors	Yule Li
Abstract	In this paper we present an efficient implementation using triplet loss for face recognition. We conduct the practical experiment to analyze the factors that influence the training of triplet loss. All models are trained on CASIA-Webface dataset and tested on LFW. We analyze the experiment results and give some insights to help others balance the factors when they apply triplet loss to their own problem especially for face recognition task. Code has been released in https://github.com/yule-li/MassFace.
Tasks	Face Recognition
Published	2019-02-28
URL	http://arxiv.org/abs/1902.11007v1
PDF	http://arxiv.org/pdf/1902.11007v1.pdf
PWC	https://paperswithcode.com/paper/massface-an-efficient-implementation-using
Repo	https://github.com/yule-li/MassFace
Framework	tf

NAS-Bench-101: Towards Reproducible Neural Architecture Search


Title	NAS-Bench-101: Towards Reproducible Neural Architecture Search
Authors	Chris Ying, Aaron Klein, Esteban Real, Eric Christiansen, Kevin Murphy, Frank Hutter
Abstract	Recent advances in neural architecture search (NAS) demand tremendous computational resources, which makes it difficult to reproduce experiments and imposes a barrier-to-entry to researchers without access to large-scale computation. We aim to ameliorate these problems by introducing NAS-Bench-101, the first public architecture dataset for NAS research. To build NAS-Bench-101, we carefully constructed a compact, yet expressive, search space, exploiting graph isomorphisms to identify 423k unique convolutional architectures. We trained and evaluated all of these architectures multiple times on CIFAR-10 and compiled the results into a large dataset of over 5 million trained models. This allows researchers to evaluate the quality of a diverse range of models in milliseconds by querying the pre-computed dataset. We demonstrate its utility by analyzing the dataset as a whole and by benchmarking a range of architecture optimization algorithms.
Tasks	Neural Architecture Search
Published	2019-02-25
URL	https://arxiv.org/abs/1902.09635v2
PDF	https://arxiv.org/pdf/1902.09635v2.pdf
PWC	https://paperswithcode.com/paper/nas-bench-101-towards-reproducible-neural
Repo	https://github.com/keuperj/DeToL
Framework	none

Communication-Efficient Distributed Optimization in Networks with Gradient Tracking and Variance Reduction


Title	Communication-Efficient Distributed Optimization in Networks with Gradient Tracking and Variance Reduction
Authors	Boyue Li, Shicong Cen, Yuxin Chen, Yuejie Chi
Abstract	There is growing interest in large-scale machine learning and optimization over decentralized networks, e.g. in the context of multi-agent learning and federated learning. Due to the imminent need to alleviate the communication burden, the investigation of communication-efficient distributed optimization algorithms - particularly for empirical risk minimization - has flourished in recent years. A large fraction of these algorithms have been developed for the master/slave setting, relying on a central parameter server that can communicate with all agents. This paper focuses on distributed optimization over networks, or decentralized optimization, where each agent is only allowed to aggregate information from its neighbors. By properly adjusting the global gradient estimate via local averaging in conjunction with proper correction, we develop a communication-efficient approximate Newton-type method Network-DANE, which generalizes DANE to the decentralized scenarios. Our key ideas can be applied in a systematic manner to obtain decentralized versions of other master/slave distributed algorithms. A notable development is Network-SVRG/SARAH, which employs variance reduction to further accelerate local computation. We establish linear convergence of Network-DANE and Network-SVRG for strongly convex losses, and Network-SARAH for quadratic losses, which shed light on the impacts of data homogeneity, network connectivity, and local averaging upon the rate of convergence. We further extend Network-DANE to composite optimization by allowing a nonsmooth penalty term. Numerical evidence is provided to demonstrate the appealing performance of our algorithms over competitive baselines, in terms of both communication and computation efficiency. Our work suggests that performing a certain amount of local communications and computations per iteration can substantially improve the overall efficiency.
Tasks	Distributed Optimization
Published	2019-09-12
URL	https://arxiv.org/abs/1909.05844v2
PDF	https://arxiv.org/pdf/1909.05844v2.pdf
PWC	https://paperswithcode.com/paper/communication-efficient-distributed-5
Repo	https://github.com/liboyue/Network-Distributed-Algorithm
Framework	none

Robust Learning from Untrusted Sources


Title	Robust Learning from Untrusted Sources
Authors	Nikola Konstantinov, Christoph Lampert
Abstract	Modern machine learning methods often require more data for training than a single expert can provide. Therefore, it has become a standard procedure to collect data from external sources, e.g. via crowdsourcing. Unfortunately, the quality of these sources is not always guaranteed. As additional complications, the data might be stored in a distributed way, or might even have to remain private. In this work, we address the question of how to learn robustly in such scenarios. Studying the problem through the lens of statistical learning theory, we derive a procedure that allows for learning from all available sources, yet automatically suppresses irrelevant or corrupted data. We show by extensive experiments that our method provides significant improvements over alternative approaches from robust statistics and distributed optimization.
Tasks	Distributed Optimization
Published	2019-01-29
URL	https://arxiv.org/abs/1901.10310v2
PDF	https://arxiv.org/pdf/1901.10310v2.pdf
PWC	https://paperswithcode.com/paper/robust-learning-from-untrusted-sources
Repo	https://github.com/NikolaKon1994/Robust-Learning-from-Untrusted-Sources
Framework	tf

Prior specification via prior predictive matching: Poisson matrix factorization and beyond


Title	Prior specification via prior predictive matching: Poisson matrix factorization and beyond
Authors	Eliezer de Souza da Silva, Tomasz Kuśmierczyk, Marcelo Hartmann, Arto Klami
Abstract	Hyperparameter optimization for machine learning models is typically carried out by some sort of cross-validation procedure or global optimization, both of which require running the learning algorithm numerous times. We show that for Bayesian hierarchical models there is an appealing alternative that allows selecting good hyperparameters without learning the model parameters during the process at all, facilitated by the prior predictive distribution that marginalizes out the model parameters. We propose an approach that matches suitable statistics of the prior predictive distribution with ones provided by an expert and apply the general concept for matrix factorization models. For some Poisson matrix factorization models we can analytically obtain exact hyperparameters, including the number of factors, and for more complex models we propose a model-independent optimization procedure.
Tasks	Hyperparameter Optimization
Published	2019-10-27
URL	https://arxiv.org/abs/1910.12263v1
PDF	https://arxiv.org/pdf/1910.12263v1.pdf
PWC	https://paperswithcode.com/paper/prior-specification-via-prior-predictive
Repo	https://github.com/tkusmierczyk/bayesian_hyperparameters_matching
Framework	tf

Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Network


Title	Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Network
Authors	Chen Li, Gim Hee Lee
Abstract	3D human pose estimation from a monocular image or 2D joints is an ill-posed problem because of depth ambiguity and occluded joints. We argue that 3D human pose estimation from a monocular input is an inverse problem where multiple feasible solutions can exist. In this paper, we propose a novel approach to generate multiple feasible hypotheses of the 3D pose from 2D joints.In contrast to existing deep learning approaches which minimize a mean square error based on an unimodal Gaussian distribution, our method is able to generate multiple feasible hypotheses of 3D pose based on a multimodal mixture density networks. Our experiments show that the 3D poses estimated by our approach from an input of 2D joints are consistent in 2D reprojections, which supports our argument that multiple solutions exist for the 2D-to-3D inverse problem. Furthermore, we show state-of-the-art performance on the Human3.6M dataset in both best hypothesis and multi-view settings, and we demonstrate the generalization capacity of our model by testing on the MPII and MPI-INF-3DHP datasets. Our code is available at the project website.
Tasks	3D Human Pose Estimation, Pose Estimation
Published	2019-04-11
URL	http://arxiv.org/abs/1904.05547v1
PDF	http://arxiv.org/pdf/1904.05547v1.pdf
PWC	https://paperswithcode.com/paper/generating-multiple-hypotheses-for-3d-human
Repo	https://github.com/vnmr/JointVideoPose3D
Framework	pytorch

Absolute Human Pose Estimation with Depth Prediction Network


Title	Absolute Human Pose Estimation with Depth Prediction Network
Authors	Márton Véges, András Lőrincz
Abstract	The common approach to 3D human pose estimation is predicting the body joint coordinates relative to the hip. This works well for a single person but is insufficient in the case of multiple interacting people. Methods predicting absolute coordinates first estimate a root-relative pose then calculate the translation via a secondary optimization task. We propose a neural network that predicts joints in a camera centered coordinate system instead of a root-relative one. Unlike previous methods, our network works in a single step without any post-processing. Our network beats previous methods on the MuPoTS-3D dataset and achieves state-of-the-art results.
Tasks	3D Human Pose Estimation, Depth Estimation, Pose Estimation
Published	2019-04-11
URL	http://arxiv.org/abs/1904.05947v1
PDF	http://arxiv.org/pdf/1904.05947v1.pdf
PWC	https://paperswithcode.com/paper/absolute-human-pose-estimation-with-depth
Repo	https://github.com/vegesm/depthpose
Framework	pytorch

Adapt or Get Left Behind: Domain Adaptation through BERT Language Model Finetuning for Aspect-Target Sentiment Classification


Title	Adapt or Get Left Behind: Domain Adaptation through BERT Language Model Finetuning for Aspect-Target Sentiment Classification
Authors	Alexander Rietzler, Sebastian Stabinger, Paul Opitz, Stefan Engl
Abstract	Aspect-Target Sentiment Classification (ATSC) is a subtask of Aspect-Based Sentiment Analysis (ABSA), which has many applications e.g. in e-commerce, where data and insights from reviews can be leveraged to create value for businesses and customers. Recently, deep transfer-learning methods have been applied successfully to a myriad of Natural Language Processing (NLP) tasks, including ATSC. Building on top of the prominent BERT language model, we approach ATSC using a two-step procedure: self-supervised domain-specific BERT language model finetuning, followed by supervised task-specific finetuning. Our findings on how to best exploit domain-specific language model finetuning enable us to produce new state-of-the-art performance on the SemEval 2014 Task 4 restaurants dataset. In addition, to explore the real-world robustness of our models, we perform cross-domain evaluation. We show that a cross-domain adapted BERT language model performs significantly better than strong baseline models like vanilla BERT-base and XLNet-base. Finally, we conduct a case study to interpret model prediction errors.
Tasks	Aspect-Based Sentiment Analysis, Domain Adaptation, Language Modelling, Sentiment Analysis, Transfer Learning
Published	2019-08-30
URL	https://arxiv.org/abs/1908.11860v2
PDF	https://arxiv.org/pdf/1908.11860v2.pdf
PWC	https://paperswithcode.com/paper/adapt-or-get-left-behind-domain-adaptation
Repo	https://github.com/deepopinion/domain-adapted-atsc
Framework	pytorch

Modeling Sentiment Dependencies with Graph Convolutional Networks for Aspect-level Sentiment Classification


Title	Modeling Sentiment Dependencies with Graph Convolutional Networks for Aspect-level Sentiment Classification
Authors	Pinlong Zhaoa, Linlin Houb, Ou Wua
Abstract	Aspect-level sentiment classification aims to distinguish the sentiment polarities over one or more aspect terms in a sentence. Existing approaches mostly model different aspects in one sentence independently, which ignore the sentiment dependencies between different aspects. However, we find such dependency information between different aspects can bring additional valuable information. In this paper, we propose a novel aspect-level sentiment classification model based on graph convolutional networks (GCN) which can effectively capture the sentiment dependencies between multi-aspects in one sentence. Our model firstly introduces bidirectional attention mechanism with position encoding to model aspect-specific representations between each aspect and its context words, then employs GCN over the attention mechanism to capture the sentiment dependencies between different aspects in one sentence. We evaluate the proposed approach on the SemEval 2014 datasets. Experiments show that our model outperforms the state-of-the-art methods. We also conduct experiments to evaluate the effectiveness of GCN module, which indicates that the dependencies between different aspects is highly helpful in aspect-level sentiment classification.
Tasks	Aspect-Based Sentiment Analysis, Sentiment Analysis
Published	2019-06-11
URL	https://arxiv.org/abs/1906.04501v1
PDF	https://arxiv.org/pdf/1906.04501v1.pdf
PWC	https://paperswithcode.com/paper/modeling-sentiment-dependencies-with-graph
Repo	https://github.com/Pinlong-Zhao/SDGCN
Framework	tf

Nanoscale Microscopy Images Colorization Using Neural Networks


Title	Nanoscale Microscopy Images Colorization Using Neural Networks
Authors	Israel Goytom, Qin Wang, Tianxiang Yu, Kunjie Dai, Kris Sankaran, Xinfei Zhou, Dongdong Lin
Abstract	Microscopy images are powerful tools and widely used in the majority of research areas, such as biology, chemistry, physics and materials fields by various microscopies (scanning electron microscope (SEM), atomic force microscope (AFM) and the optical microscope, et al.). However, most of the microscopy images are colorless due to the unique imaging mechanism. Though investigating on some popular solutions proposed recently about colorizing images, we notice the process of those methods are usually tedious, complicated, and time-consuming. In this paper, inspired by the achievement of machine learning algorithms on different science fields, we introduce two artificial neural networks for gray microscopy image colorization: An end-to-end convolutional neural network (CNN) with a pre-trained model for feature extraction and a pixel-to-pixel neural style transfer convolutional neural network (NST-CNN), which can colorize gray microscopy images with semantic information learned from a user-provided colorful image at inference time. The results demonstrate that our algorithm not only can colorize the microscopy images under complex circumstances precisely but also make the color naturally according to the training of a massive number of nature images with proper hue and saturation.
Tasks	Colorization, Style Transfer
Published	2019-12-17
URL	https://arxiv.org/abs/1912.07964v2
PDF	https://arxiv.org/pdf/1912.07964v2.pdf
PWC	https://paperswithcode.com/paper/nanoscale-microscopy-images-colourisation
Repo	https://github.com/isrugeek/semcolour
Framework	none