January 29, 2020

3017 words 15 mins read

Paper Group ANR 540

An Automated Deep Learning Approach for Bacterial Image Classification. Embarrassingly parallel MCMC using deep invertible transformations. Region and Object based Panoptic Image Synthesis through Conditional GANs. To Tune or Not to Tune? Adapting Pretrained Representations to Diverse Tasks. 2SDR: Two Stage Dimension Reduction to Denoise Cryo-EM Im …

An Automated Deep Learning Approach for Bacterial Image Classification


Title	An Automated Deep Learning Approach for Bacterial Image Classification
Authors	Muhammed Talo
Abstract	Automated recognition and classification of bacteria species from microscopic images have significant importance in clinical microbiology. Bacteria classification is usually carried out manually by biologists using different shapes and morphologic characteristics of bacteria species. The manual taxonomy of bacteria types from microscopy images is time-consuming and a challenging task for even experienced biologists. In this study, an automated deep learning based classification approach has been proposed to classify bacterial images into different categories. The ResNet-50 pre-trained CNN architecture has been used to classify digital bacteria images into 33 categories. The transfer learning technique was employed to accelerate the training process of the network and improve the classification performance of the network. The proposed method achieved an average classification accuracy of 99.2%. The experimental results demonstrate that the proposed technique surpasses state-of-the-art methods in the literature and can be used for any type of bacteria classification tasks.
Tasks	Image Classification, Transfer Learning
Published	2019-12-04
URL	https://arxiv.org/abs/1912.08765v1
PDF	https://arxiv.org/pdf/1912.08765v1.pdf
PWC	https://paperswithcode.com/paper/an-automated-deep-learning-approach-for
Repo
Framework

Embarrassingly parallel MCMC using deep invertible transformations


Title	Embarrassingly parallel MCMC using deep invertible transformations
Authors	Diego Mesquita, Paul Blomstedt, Samuel Kaski
Abstract	While MCMC methods have become a main work-horse for Bayesian inference, scaling them to large distributed datasets is still a challenge. Embarrassingly parallel MCMC strategies take a divide-and-conquer stance to achieve this by writing the target posterior as a product of subposteriors, running MCMC for each of them in parallel and subsequently combining the results. The challenge then lies in devising efficient aggregation strategies. Current strategies trade-off between approximation quality, and costs of communication and computation. In this work, we introduce a novel method that addresses these issues simultaneously. Our key insight is to introduce a deep invertible transformation to approximate each of the subposteriors. These approximations can be made accurate even for complex distributions and serve as intermediate representations, keeping the total communication cost limited. Moreover, they enable us to sample from the product of the subposteriors using an efficient and stable importance sampling scheme. We demonstrate the approach outperforms available state-of-the-art methods in a range of challenging scenarios, including high-dimensional and heterogeneous subposteriors.
Tasks	Bayesian Inference
Published	2019-03-11
URL	http://arxiv.org/abs/1903.04556v1
PDF	http://arxiv.org/pdf/1903.04556v1.pdf
PWC	https://paperswithcode.com/paper/embarrassingly-parallel-mcmc-using-deep
Repo
Framework

Region and Object based Panoptic Image Synthesis through Conditional GANs


Title	Region and Object based Panoptic Image Synthesis through Conditional GANs
Authors	Heng Wang, Donghao Zhang, Yang Song, Heng Huang, Mei Chen, Weidong Cai
Abstract	Image-to-image translation is significant to many computer vision and machine learning tasks such as image synthesis and video synthesis. It has primary applications in the graphics editing and animation industries. With the development of generative adversarial networks, a lot of attention has been drawn to image-to-image translation tasks. In this paper, we propose and investigate a novel task named as panoptic-level image-to-image translation and a naive baseline of solving this task. Panoptic-level image translation extends the current image translation task to two separate objectives of semantic style translation (adjust the style of objects to that of different domains) and instance transfiguration (swap between different types of objects). The proposed task generates an image from a complete and detailed panoptic perspective which can enrich the context of real-world vision synthesis. Our contribution consists of the proposal of a significant task worth investigating and a naive baseline of solving it. The proposed baseline consists of the multiple instances sequential translation and semantic-level translation with domain-invariant content code.
Tasks	Image Generation, Image-to-Image Translation
Published	2019-12-14
URL	https://arxiv.org/abs/1912.06840v1
PDF	https://arxiv.org/pdf/1912.06840v1.pdf
PWC	https://paperswithcode.com/paper/region-and-object-based-panoptic-image
Repo
Framework

To Tune or Not to Tune? Adapting Pretrained Representations to Diverse Tasks


Title	To Tune or Not to Tune? Adapting Pretrained Representations to Diverse Tasks
Authors	Matthew E. Peters, Sebastian Ruder, Noah A. Smith
Abstract	While most previous work has focused on different pretraining objectives and architectures for transfer learning, we ask how to best adapt the pretrained model to a given target task. We focus on the two most common forms of adaptation, feature extraction (where the pretrained weights are frozen), and directly fine-tuning the pretrained model. Our empirical results across diverse NLP tasks with two state-of-the-art models show that the relative performance of fine-tuning vs. feature extraction depends on the similarity of the pretraining and target tasks. We explore possible explanations for this finding and provide a set of adaptation guidelines for the NLP practitioner.
Tasks	Transfer Learning
Published	2019-03-14
URL	https://arxiv.org/abs/1903.05987v2
PDF	https://arxiv.org/pdf/1903.05987v2.pdf
PWC	https://paperswithcode.com/paper/to-tune-or-not-to-tune-adapting-pretrained
Repo
Framework

2SDR: Two Stage Dimension Reduction to Denoise Cryo-EM Images


Title	2SDR: Two Stage Dimension Reduction to Denoise Cryo-EM Images
Authors	Szu-Chi Chung, Shao-Hsuan Wang, Po-Yao Niu, Su-Yun Huang, Wei-Hau Chang, I-Ping Tu
Abstract	Principal component analysis (PCA) is arguably the most widely used dimension reduction method for vector type data. When applied to a set of images, PCA demands that the images be vectorized. This demand consequentially introduced a weakness in the application: heavy computation due to solving the eigenvalue problem of a huge covariance matrix. In this paper, we propose a two stage dimension reduction (2SDR) method for images based on a statistical model with two layers of noise structures. 2SDR first applies multi-linear PCA (MPCA) to extract core scores from the images as well as to screen the first layer of noise, and then applies PCA on these scores to further reduce the second layer of noise. MPCA has computation advantages that it avoids image vectorization and applies the Kronecker product on column and row eigenvectors to model the image bases. In contrast, PCA can diagonalize the covariance matrix that its projected scores are guaranteed to be uncorrelated. Combining MPCA and PCA, 2SDR has two benefits that it inherits the computation advantage of MPCA and its projection scores are uncorrelated as those of PCA. Testing with two cryo-electron microscopy (cryo-EM) benchmark experimental datasets shows that 2SDR performs better than MPCA and PCA alone in terms of the computation efficiency and denoising performance. We further propose a rank selection method for 2SDR and prove that this method has the consistency property under some regular conditions.
Tasks	Denoising, Dimensionality Reduction
Published	2019-11-22
URL	https://arxiv.org/abs/1911.09816v2
PDF	https://arxiv.org/pdf/1911.09816v2.pdf
PWC	https://paperswithcode.com/paper/2sdr-applying-kronecker-envelope-pca-to
Repo
Framework

Improved Hyperspectral Unmixing With Endmember Variability Parametrized Using an Interpolated Scaling Tensor


Title	Improved Hyperspectral Unmixing With Endmember Variability Parametrized Using an Interpolated Scaling Tensor
Authors	Ricardo Augusto Borsoi, Tales Imbiriba, José Carlos Moreira Bermudez
Abstract	Endmember (EM) variability has an important impact on the performance of hyperspectral image (HI) analysis algorithms. Recently, extended linear mixing models have been proposed to account for EM variability in the spectral unmixing (SU) problem. The direct use of these models has led to severely ill-posed optimization problems. Different regularization strategies have been considered to deal with this issue, but none so far has consistently exploited the information provided by the existence of multiple pure pixels often present in HIs. In this work, we propose to break the SU problem into a sequence of two problems. First, we use pure pixel information to estimate an interpolated tensor of scaling factors representing spectral variability. This is done by considering the spectral variability to be a smooth function over the HI and confining the energy of the scaling tensor to a low-rank structure. Afterwards, we solve a matrix-factorization problem to estimate the fractional abundances using the variability scaling factors estimated in the previous step, what leads to a significantly more well-posed problem. Simulation swith synthetic and real data attest the effectiveness of the proposed strategy.
Tasks	Hyperspectral Unmixing
Published	2019-01-02
URL	http://arxiv.org/abs/1901.00463v1
PDF	http://arxiv.org/pdf/1901.00463v1.pdf
PWC	https://paperswithcode.com/paper/improved-hyperspectral-unmixing-with
Repo
Framework

DeepACE: Automated Chromosome Enumeration in Metaphase Cell Images Using Deep Convolutional Neural Networks


Title	DeepACE: Automated Chromosome Enumeration in Metaphase Cell Images Using Deep Convolutional Neural Networks
Authors	Li Xiao, Chunlong Luo, Yufan Luo, Tianqi Yu, Chan Tian, Jie Qiao, Yi Zhao
Abstract	Chromosome enumeration is an important but tedious procedure in karyotyping analysis. In this paper, to automate the enumeration process, we developed a chromosome enumeration framework, DeepACE, based on the region based object detection scheme. Firstly, the ability of region proposal network is enhanced by a newly proposed Hard Negative Anchors Sampling to extract unapparent but important information about highly confusing partial chromosomes. Next, to alleviate serious occlusion problems, we novelly introduced a weakly-supervised mechanism by adding a Template Module into classification branch to heuristically separate overlapped chromosomes. The template features are further incorporated into the NMS procedure to further improve the detection of overlapping chromosomes. In the newly collected clinical dataset, the proposed method outperform all the previous method, yielding an mAP with respect to chromosomes as 99.45, and the error rate is about 2.4%.
Tasks	Object Detection
Published	2019-10-12
URL	https://arxiv.org/abs/1910.11091v1
PDF	https://arxiv.org/pdf/1910.11091v1.pdf
PWC	https://paperswithcode.com/paper/deepace-automated-chromosome-enumeration-in
Repo
Framework

Generalized Dirichlet-process-means for $f$-separable distortion measures


Title	Generalized Dirichlet-process-means for $f$-separable distortion measures
Authors	Masahiro Kobayashi, Kazuho Watanabe
Abstract	DP-means clustering was obtained as an extension of $K$-means clustering. While it is implemented with a simple and efficient algorithm, it can estimate the number of clusters simultaneously. However, DP-means is specifically designed for the average distortion measure. Therefore, it is vulnerable to outliers in data, and can cause large maximum distortion in clusters. In this work, we extend the objective function of the DP-means to $f$-separable distortion measures and propose a unified learning algorithm to overcome the above problems by selecting the function $f$. Further, the influence function of the estimated cluster center is analyzed to evaluate the robustness against outliers. We demonstrate the performance of the generalized method by numerical experiments using real datasets.
Tasks
Published	2019-01-31
URL	https://arxiv.org/abs/1901.11331v2
PDF	https://arxiv.org/pdf/1901.11331v2.pdf
PWC	https://paperswithcode.com/paper/generalized-dirichlet-process-means-for-f
Repo
Framework

Recursive Graphical Neural Networks for Text Classification


Title	Recursive Graphical Neural Networks for Text Classification
Authors	Wei Li, Shuheng Li, Shuming Ma, Yancheng He, Deli Chen, Xu Sun
Abstract	The complicated syntax structure of natural language is hard to be explicitly modeled by sequence-based models. Graph is a natural structure to describe the complicated relation between tokens. The recent advance in Graph Neural Networks (GNN) provides a powerful tool to model graph structure data, but simple graph models such as Graph Convolutional Networks (GCN) suffer from over-smoothing problem, that is, when stacking multiple layers, all nodes will converge to the same value. In this paper, we propose a novel Recursive Graphical Neural Networks model (ReGNN) to represent text organized in the form of graph. In our proposed model, LSTM is used to dynamically decide which part of the aggregated neighbor information should be transmitted to upper layers thus alleviating the over-smoothing problem. Furthermore, to encourage the exchange between the local and global information, a global graph-level node is designed. We conduct experiments on both single and multiple label text classification tasks. Experiment results show that our ReGNN model surpasses the strong baselines significantly in most of the datasets and greatly alleviates the over-smoothing problem.
Tasks	Text Classification
Published	2019-09-18
URL	https://arxiv.org/abs/1909.08166v1
PDF	https://arxiv.org/pdf/1909.08166v1.pdf
PWC	https://paperswithcode.com/paper/recursive-graphical-neural-networks-for-text
Repo
Framework

A CNN-based methodology for breast cancer diagnosis using thermal images


Title	A CNN-based methodology for breast cancer diagnosis using thermal images
Authors	Juan Zuluaga-Gomez, Zeina Al Masry, Khaled Benaggoune, Safa Meraghni, Noureddine Zerhouni
Abstract	Micro Abstract: A recent study from GLOBOCAN disclosed that during 2018 two million women worldwide had been diagnosed from breast cancer. This study presents a computer-aided diagnosis system based on convolutional neural networks as an alternative diagnosis methodology for breast cancer diagnosis with thermal images. Experimental results showed that lower false-positives and false-negatives classification rates are obtained when data pre-processing and data augmentation techniques are implemented in these thermal images. Background: There are many types of breast cancer screening techniques such as, mammography, magnetic resonance imaging, ultrasound and blood sample tests, which require either, expensive devices or personal qualified. Currently, some countries still lack access to these main screening techniques due to economic, social or cultural issues. The objective of this study is to demonstrate that computer-aided diagnosis(CAD) systems based on convolutional neural networks (CNN) are faster, reliable and robust than other techniques. Methods: We performed a study of the influence of data pre-processing, data augmentation and database size versus a proposed set of CNN models. Furthermore, we developed a CNN hyper-parameters fine-tuning optimization algorithm using a tree parzen estimator. Results: Among the 57 patients database, our CNN models obtained a higher accuracy (92%) and F1-score (92%) that outperforms several state-of-the-art architectures such as ResNet50, SeResNet50 and Inception. Also, we demonstrated that a CNN model that implements data-augmentation techniques reach identical performance metrics in comparison with a CNN that uses a database up to 50% bigger. Conclusion: This study highlights the benefits of data augmentation and CNNs in thermal breast images. Also, it measures the influence of the database size in the performance of CNNs.
Tasks	Data Augmentation
Published	2019-10-30
URL	https://arxiv.org/abs/1910.13757v1
PDF	https://arxiv.org/pdf/1910.13757v1.pdf
PWC	https://paperswithcode.com/paper/a-cnn-based-methodology-for-breast-cancer
Repo
Framework

Implicit Context-aware Learning and Discovery for Streaming Data Analytics


Title	Implicit Context-aware Learning and Discovery for Streaming Data Analytics
Authors	Kin Gwn Lore, Kishore K. Reddy
Abstract	The performance of machine learning model can be further improved if contextual cues are provided as input along with base features that are directly related to an inference task. In offline learning, one can inspect historical training data to identify contextual clusters either through feature clustering, or hand-crafting additional features to describe a context. While offline training enjoys the privilege of learning reliable models based on already-defined contextual features, online training for streaming data may be more challenging – the data is streamed through time, and the underlying context during a data generation process may change. Furthermore, the problem is exacerbated when the number of possible context is not known. In this study, we propose an online-learning algorithm involving the use of a neural network-based autoencoder to identify contextual changes during training, then compares the currently-inferred context to a knowledge base of learned contexts as training advances. Results show that classifier-training benefits from the automatically discovered contexts which demonstrates quicker learning convergence during contextual changes compared to current methods.
Tasks
Published	2019-10-18
URL	https://arxiv.org/abs/1910.08438v1
PDF	https://arxiv.org/pdf/1910.08438v1.pdf
PWC	https://paperswithcode.com/paper/implicit-context-aware-learning-and-discovery
Repo
Framework

Learning Implicit Generative Models by Matching Perceptual Features


Title	Learning Implicit Generative Models by Matching Perceptual Features
Authors	Cicero Nogueira dos Santos, Youssef Mroueh, Inkit Padhi, Pierre Dognin
Abstract	Perceptual features (PFs) have been used with great success in tasks such as transfer learning, style transfer, and super-resolution. However, the efficacy of PFs as key source of information for learning generative models is not well studied. We investigate here the use of PFs in the context of learning implicit generative models through moment matching (MM). More specifically, we propose a new effective MM approach that learns implicit generative models by performing mean and covariance matching of features extracted from pretrained ConvNets. Our proposed approach improves upon existing MM methods by: (1) breaking away from the problematic min/max game of adversarial learning; (2) avoiding online learning of kernel functions; and (3) being efficient with respect to both number of used moments and required minibatch size. Our experimental results demonstrate that, due to the expressiveness of PFs from pretrained deep ConvNets, our method achieves state-of-the-art results for challenging benchmarks.
Tasks	Style Transfer, Super-Resolution, Transfer Learning
Published	2019-04-04
URL	http://arxiv.org/abs/1904.02762v1
PDF	http://arxiv.org/pdf/1904.02762v1.pdf
PWC	https://paperswithcode.com/paper/learning-implicit-generative-models-by-2
Repo
Framework

Neural Architecture Search for Joint Optimization of Predictive Power and Biological Knowledge


Title	Neural Architecture Search for Joint Optimization of Predictive Power and Biological Knowledge
Authors	Zijun Zhang, Linqi Zhou, Liangke Gou, Ying Nian Wu
Abstract	We report a neural architecture search framework, BioNAS, that is tailored for biomedical researchers to easily build, evaluate, and uncover novel knowledge from interpretable deep learning models. The introduction of knowledge dissimilarity functions in BioNAS enables the joint optimization of predictive power and biological knowledge through searching architectures in a model space. By optimizing the consistency with existing knowledge, we demonstrate that BioNAS optimal models reveal novel knowledge in both simulated data and in real data of functional genomics. BioNAS provides a useful tool for domain experts to inject their prior belief into automated machine learning and therefore making deep learning easily accessible to practitioners. BioNAS is available at https://github.com/zj-zhang/BioNAS-pub.
Tasks	Neural Architecture Search
Published	2019-09-01
URL	https://arxiv.org/abs/1909.00337v1
PDF	https://arxiv.org/pdf/1909.00337v1.pdf
PWC	https://paperswithcode.com/paper/neural-architecture-search-for-joint
Repo
Framework

Fluid Flow Mass Transport for Generative Networks


Title	Fluid Flow Mass Transport for Generative Networks
Authors	Jingrong Lin, Keegan Lensink, Eldad Haber
Abstract	Generative Adversarial Networks have been shown to be powerful in generating content. To this end, they have been studied intensively in the last few years. Nonetheless, training these networks requires solving a saddle point problem that is difficult to solve and slowly converging. Motivated from techniques in the registration of point clouds and by the fluid flow formulation of mass transport, we investigate a new formulation that is based on strict minimization, without the need for the maximization. The formulation views the problem as a matching problem rather than an adversarial one and thus allows us to quickly converge and obtain meaningful metrics in the optimization path.
Tasks
Published	2019-10-03
URL	https://arxiv.org/abs/1910.01694v2
PDF	https://arxiv.org/pdf/1910.01694v2.pdf
PWC	https://paperswithcode.com/paper/fluid-flow-mass-transport-for-generative
Repo
Framework

RotationOut as a Regularization Method for Neural Network


Title	RotationOut as a Regularization Method for Neural Network
Authors	Kai Hu, Barnabas Poczos
Abstract	In this paper, we propose a novel regularization method, RotationOut, for neural networks. Different from Dropout that handles each neuron/channel independently, RotationOut regards its input layer as an entire vector and introduces regularization by randomly rotating the vector. RotationOut can also be used in convolutional layers and recurrent layers with small modifications. We further use a noise analysis method to interpret the difference between RotationOut and Dropout in co-adaptation reduction. Using this method, we also show how to use RotationOut/Dropout together with Batch Normalization. Extensive experiments in vision and language tasks are conducted to show the effectiveness of the proposed method. Codes are available at \url{https://github.com/RotationOut/RotationOut}.
Tasks
Published	2019-11-18
URL	https://arxiv.org/abs/1911.07427v1
PDF	https://arxiv.org/pdf/1911.07427v1.pdf
PWC	https://paperswithcode.com/paper/rotationout-as-a-regularization-method-for-1
Repo
Framework