January 29, 2020

3152 words 15 mins read

Paper Group ANR 763

Deep learning assessment of breast terminal duct lobular unit involution: towards automated prediction of breast cancer risk. P-ODN: Prototype based Open Deep Network for Open Set Recognition. LATTE: Latent Type Modeling for Biomedical Entity Linking. YELM: End-to-End Contextualized Entity Linking. Object Detection in Specific Traffic Scenes using …

Deep learning assessment of breast terminal duct lobular unit involution: towards automated prediction of breast cancer risk


Title	Deep learning assessment of breast terminal duct lobular unit involution: towards automated prediction of breast cancer risk
Authors	Suzanne C Wetstein, Allison M Onken, Christina Luffman, Gabrielle M Baker, Michael E Pyle, Kevin H Kensler, Ying Liu, Bart Bakker, Ruud Vlutters, Marinus B van Leeuwen, Laura C Collins, Stuart J Schnitt, Josien PW Pluim, Rulla M Tamimi, Yujing J Heng, Mitko Veta
Abstract	Terminal ductal lobular unit (TDLU) involution is the regression of milk-producing structures in the breast. Women with less TDLU involution are more likely to develop breast cancer. A major bottleneck in studying TDLU involution in large cohort studies is the need for labor-intensive manual assessment of TDLUs. We developed a computational pathology solution to automatically capture TDLU involution measures. Whole slide images (WSIs) of benign breast biopsies were obtained from the Nurses’ Health Study (NHS). A first set of 92 WSIs was annotated for TDLUs, acini and adipose tissue to train deep convolutional neural network (CNN) models for detection of acini, and segmentation of TDLUs and adipose tissue. These networks were integrated into a single computational method to capture TDLU involution measures including number of TDLUs per tissue area, median TDLU span and median number of acini per TDLU. We validated our method on 40 additional WSIs by comparing with manually acquired measures. Our CNN models detected acini with an F1 score of 0.73$\pm$0.09, and segmented TDLUs and adipose tissue with Dice scores of 0.86$\pm$0.11 and 0.86$\pm$0.04, respectively. The inter-observer ICC scores for manual assessments on 40 WSIs of number of TDLUs per tissue area, median TDLU span, and median acini count per TDLU were 0.71, 95% CI [0.51, 0.83], 0.81, 95% CI [0.67, 0.90], and 0.73, 95% CI [0.54, 0.85], respectively. Intra-observer reliability was evaluated on 10/40 WSIs with ICC scores of >0.8. Inter-observer ICC scores between automated results and the mean of the two observers were: 0.80, 95% CI [0.63, 0.90] for number of TDLUs per tissue area, 0.57, 95% CI [0.19, 0.77] for median TDLU span, and 0.80, 95% CI [0.62, 0.89] for median acini count per TDLU. TDLU involution measures evaluated by manual and automated assessment were inversely associated with age and menopausal status.
Tasks
Published	2019-10-31
URL	https://arxiv.org/abs/1911.00036v1
PDF	https://arxiv.org/pdf/1911.00036v1.pdf
PWC	https://paperswithcode.com/paper/deep-learning-assessment-of-breast-terminal
Repo
Framework

P-ODN: Prototype based Open Deep Network for Open Set Recognition


Title	P-ODN: Prototype based Open Deep Network for Open Set Recognition
Authors	Yu Shu, Yemin Shi, Yaowei Wang, Tiejun Huang, Yonghong Tian
Abstract	Most of the existing recognition algorithms are proposed for closed set scenarios, where all categories are known beforehand. However, in practice, recognition is essentially an open set problem. There are categories we know called “knowns”, and there are more we do not know called “unknowns”. Enumerating all categories beforehand is never possible, consequently it is infeasible to prepare sufficient training samples for those unknowns. Applying closed set recognition methods will naturally lead to unseen-category errors. To address this problem, we propose the prototype based Open Deep Network (P-ODN) for open set recognition tasks. Specifically, we introduce prototype learning into open set recognition. Prototypes and prototype radiuses are trained jointly to guide a CNN network to derive more discriminative features. Then P-ODN detects the unknowns by applying a multi-class triplet thresholding method based on the distance metric between features and prototypes. Manual labeling the unknowns which are detected in the previous process as new categories. Predictors for new categories are added to the classification layer to “open” the deep neural networks to incorporate new categories dynamically. The weights of new predictors are initialized exquisitely by applying a distances based algorithm to transfer the learned knowledge. Consequently, this initialization method speed up the fine-tuning process and reduce the samples needed to train new predictors. Extensive experiments show that P-ODN can effectively detect unknowns and needs only few samples with human intervention to recognize a new category. In the real world scenarios, our method achieves state-of-the-art performance on the UCF11, UCF50, UCF101 and HMDB51 datasets.
Tasks	Open Set Learning
Published	2019-05-06
URL	https://arxiv.org/abs/1905.01851v2
PDF	https://arxiv.org/pdf/1905.01851v2.pdf
PWC	https://paperswithcode.com/paper/p-odn-prototype-based-open-deep-network-for
Repo
Framework

LATTE: Latent Type Modeling for Biomedical Entity Linking


Title	LATTE: Latent Type Modeling for Biomedical Entity Linking
Authors	Ming Zhu, Busra Celikkaya, Parminder Bhatia, Chandan K. Reddy
Abstract	Entity linking is the task of linking mentions of named entities in natural language text, to entities in a curated knowledge-base. This is of significant importance in the biomedical domain, where it could be used to semantically annotate a large volume of clinical records and biomedical literature, to standardized concepts described in an ontology such as Unified Medical Language System (UMLS). We observe that with precise type information, entity disambiguation becomes a straightforward task. However, fine-grained type information is usually not available in biomedical domain. Thus, we propose LATTE, a LATent Type Entity Linking model, that improves entity linking by modeling the latent fine-grained type information about mentions and entities. Unlike previous methods that perform entity linking directly between the mentions and the entities, LATTE jointly does entity disambiguation, and latent fine-grained type learning, without direct supervision. We evaluate our model on two biomedical datasets: MedMentions, a large scale public dataset annotated with UMLS concepts, and a de-identified corpus of dictated doctor’s notes that has been annotated with ICD concepts. Extensive experimental evaluation shows our model achieves significant performance improvements over several state-of-the-art techniques.
Tasks	Entity Disambiguation, Entity Linking
Published	2019-11-21
URL	https://arxiv.org/abs/1911.09787v2
PDF	https://arxiv.org/pdf/1911.09787v2.pdf
PWC	https://paperswithcode.com/paper/latte-latent-type-modeling-for-biomedical
Repo
Framework

YELM: End-to-End Contextualized Entity Linking


Title	YELM: End-to-End Contextualized Entity Linking
Authors	Haotian Chen, Sahil Wadhwa, Xi David Li, Andrej Zukov-Gregoric
Abstract	We propose yet another entity linking model (YELM) which links words to entities instead of spans. This overcomes any difficulties associated with the selection of good candidate mention spans and makes the joint training of mention detection (MD) and entity disambiguation (ED) easily possible. Our model is based on BERT and produces contextualized word embeddings which are trained against a joint MD and ED objective. We achieve state-of-the-art results on several standard entity linking (EL) datasets.
Tasks	Entity Disambiguation, Entity Linking, Word Embeddings
Published	2019-11-10
URL	https://arxiv.org/abs/1911.03834v1
PDF	https://arxiv.org/pdf/1911.03834v1.pdf
PWC	https://paperswithcode.com/paper/yelm-end-to-end-contextualized-entity-linking
Repo
Framework

Object Detection in Specific Traffic Scenes using YOLOv2


Title	Object Detection in Specific Traffic Scenes using YOLOv2
Authors	Shouyu Wang, Weitao Tang
Abstract	object detection framework plays crucial role in autonomous driving. In this paper, we introduce the real-time object detection framework called You Only Look Once (YOLOv1) and the related improvements of YOLOv2. We further explore the capability of YOLOv2 by implementing its pre-trained model to do the object detecting tasks in some specific traffic scenes. The four artificially designed traffic scenes include single-car, single-person, frontperson-rearcar and frontcar-rearperson.
Tasks	Autonomous Driving, Object Detection, Real-Time Object Detection
Published	2019-05-12
URL	https://arxiv.org/abs/1905.04740v1
PDF	https://arxiv.org/pdf/1905.04740v1.pdf
PWC	https://paperswithcode.com/paper/object-detection-in-specific-traffic-scenes
Repo
Framework

Generalization error bounds for kernel matrix completion and extrapolation


Title	Generalization error bounds for kernel matrix completion and extrapolation
Authors	Pere Giménez-Febrer, Alba Pagès-Zamora, Georgios B. Giannakis
Abstract	Prior information can be incorporated in matrix completion to improve estimation accuracy and extrapolate the missing entries. Reproducing kernel Hilbert spaces provide tools to leverage the said prior information, and derive more reliable algorithms. This paper analyzes the generalization error of such approaches, and presents numerical tests confirming the theoretical results.
Tasks	Matrix Completion
Published	2019-06-20
URL	https://arxiv.org/abs/1906.08770v1
PDF	https://arxiv.org/pdf/1906.08770v1.pdf
PWC	https://paperswithcode.com/paper/generalization-error-bounds-for-kernel-matrix
Repo
Framework

Learning-based Single-step Quantitative Susceptibility Mapping Reconstruction Without Brain Extraction


Title	Learning-based Single-step Quantitative Susceptibility Mapping Reconstruction Without Brain Extraction
Authors	Hongjiang Wei, Steven Cao, Yuyao Zhang, Xiaojun Guan, Fuhua Yan, Kristen W. Yeom, Chunlei Liu
Abstract	Quantitative susceptibility mapping (QSM) estimates the underlying tissue magnetic susceptibility from MRI gradient-echo phase signal and typically requires several processing steps. These steps involve phase unwrapping, brain volume extraction, background phase removal and solving an ill-posed inverse problem. The resulting susceptibility map is known to suffer from inaccuracy near the edges of the brain tissues, in part due to imperfect brain extraction, edge erosion of the brain tissue and the lack of phase measurement outside the brain. This inaccuracy has thus hindered the application of QSM for measuring the susceptibility of tissues near the brain edges, e.g., quantifying cortical layers and generating superficial venography. To address these challenges, we propose a learning-based QSM reconstruction method that directly estimates the magnetic susceptibility from total phase images without the need for brain extraction and background phase removal, referred to as autoQSM. The neural network has a modified U-net structure and is trained using QSM maps computed by a two-step QSM method. 209 healthy subjects with ages ranging from 11 to 82 years were employed for patch-wise network training. The network was validated on data dissimilar to the training data, e.g. in vivo mouse brain data and brains with lesions, which suggests that the network has generalized and learned the underlying mathematical relationship between magnetic field perturbation and magnetic susceptibility. AutoQSM was able to recover magnetic susceptibility of anatomical structures near the edges of the brain including the veins covering the cortical surface, spinal cord and nerve tracts near the mouse brain boundaries. The advantages of high-quality maps, no need for brain volume extraction and high reconstruction speed demonstrate its potential for future applications.
Tasks
Published	2019-05-15
URL	https://arxiv.org/abs/1905.05953v1
PDF	https://arxiv.org/pdf/1905.05953v1.pdf
PWC	https://paperswithcode.com/paper/learning-based-single-step-quantitative
Repo
Framework

Errors-in-variables Modeling of Personalized Treatment-Response Trajectories


Title	Errors-in-variables Modeling of Personalized Treatment-Response Trajectories
Authors	Guangyi Zhang, Reza Ashrafi, Anne Juuti, Kirsi Pietiläinen, Pekka Marttinen
Abstract	Estimating the effect of a treatment on a given outcome, conditioned on a vector of covariates, is central in many applications. However, learning the impact of a treatment on a continuous temporal response, when the covariates suffer extensively from measurement error and even the timing of the treatments is uncertain, has not been addressed. We introduce a novel data-driven method that can estimate treatment-response trajectories in this challenging scenario. We model personalized treatment-response curves as a combination of parametric response functions, hierarchically sharing information across individuals, and a sparse Gaussian process for the baseline trend. Importantly, our model considers measurement error not only in treatment covariates, but also in treatment times, a problem which arises in practice for example when treatment information is based on self-reporting. In a challenging and timely problem of estimating the impact of diet on continuous blood glucose measurements, our model leads to significant improvements in estimation accuracy and prediction.
Tasks
Published	2019-06-10
URL	https://arxiv.org/abs/1906.03989v1
PDF	https://arxiv.org/pdf/1906.03989v1.pdf
PWC	https://paperswithcode.com/paper/errors-in-variables-modeling-of-personalized
Repo
Framework

Principal Fairness: Removing Bias via Projections


Title	Principal Fairness: Removing Bias via Projections
Authors	Aris Anagnostopoulos, Luca Becchetti, Adriano Fazzone, Cristina Menghini, Chris Schwiegelshohn
Abstract	Reducing hidden bias in the data and ensuring fairness in algorithmic data analysis has recently received significant attention. We complement several recent papers in this line of research by introducing a general method to reduce bias in the data through random projections in a ``fair’’ subspace. We apply this method to densest subgraph problem. For densest subgraph, our approach based on fair projections allows to recover both theoretically and empirically an almost optimal, fair, dense subgraph hidden in the input data. We also show that, under the small set expansion hypothesis, approximating this problem beyond a factor of 2 is NP-hard and we show a polynomial time algorithm with a matching approximation bound. \|
Tasks
Published	2019-05-31
URL	https://arxiv.org/abs/1905.13651v2
PDF	https://arxiv.org/pdf/1905.13651v2.pdf
PWC	https://paperswithcode.com/paper/principal-fairness-removing-bias-via
Repo
Framework

Graph Few-shot Learning via Knowledge Transfer


Title	Graph Few-shot Learning via Knowledge Transfer
Authors	Huaxiu Yao, Chuxu Zhang, Ying Wei, Meng Jiang, Suhang Wang, Junzhou Huang, Nitesh V. Chawla, Zhenhui Li
Abstract	Towards the challenging problem of semi-supervised node classification, there have been extensive studies. As a frontier, Graph Neural Networks (GNNs) have aroused great interest recently, which update the representation of each node by aggregating information of its neighbors. However, most GNNs have shallow layers with a limited receptive field and may not achieve satisfactory performance especially when the number of labeled nodes is quite small. To address this challenge, we innovatively propose a graph few-shot learning (GFL) algorithm that incorporates prior knowledge learned from auxiliary graphs to improve classification accuracy on the target graph. Specifically, a transferable metric space characterized by a node embedding and a graph-specific prototype embedding function is shared between auxiliary graphs and the target, facilitating the transfer of structural knowledge. Extensive experiments and ablation studies on four real-world graph datasets demonstrate the effectiveness of our proposed model.
Tasks	Few-Shot Learning, Node Classification, Transfer Learning
Published	2019-10-07
URL	https://arxiv.org/abs/1910.03053v2
PDF	https://arxiv.org/pdf/1910.03053v2.pdf
PWC	https://paperswithcode.com/paper/graph-few-shot-learning-via-knowledge
Repo
Framework

Disentangling to Cluster: Gaussian Mixture Variational Ladder Autoencoders


Title	Disentangling to Cluster: Gaussian Mixture Variational Ladder Autoencoders
Authors	Matthew Willetts, Stephen Roberts, Chris Holmes
Abstract	In clustering we normally output one cluster variable for each datapoint. However it is not necessarily the case that there is only one way to partition a given dataset into cluster components. For example, one could cluster objects by their colour, or by their type. Different attributes form a hierarchy, and we could wish to cluster in any of them. By disentangling the learnt latent representations of some dataset into different layers for different attributes we can then cluster in those latent spaces. We call this “disentangled clustering”. Extending Variational Ladder Autoencoders (Zhao et al., 2017), we propose a clustering algorithm, VLAC, that outperforms a Gaussian Mixture DGM in cluster accuracy over digit identity on the test set of SVHN. We also demonstrate learning clusters jointly over numerous layers of the hierarchy of latent variables for the data, and show component-wise generation from this hierarchical model.
Tasks
Published	2019-09-25
URL	https://arxiv.org/abs/1909.11501v2
PDF	https://arxiv.org/pdf/1909.11501v2.pdf
PWC	https://paperswithcode.com/paper/disentangling-to-cluster-gaussian-mixture
Repo
Framework

Fast object detection in compressed JPEG Images


Title	Fast object detection in compressed JPEG Images
Authors	Benjamin Deguerre, Clément Chatelain, Gilles Gasso
Abstract	Object detection in still images has drawn a lot of attention over past few years, and with the advent of Deep Learning impressive performances have been achieved with numerous industrial applications. Most of these deep learning models rely on RGB images to localize and identify objects in the image. However in some application scenarii, images are compressed either for storage savings or fast transmission. Therefore a time consuming image decompression step is compulsory in order to apply the aforementioned deep models. To alleviate this drawback, we propose a fast deep architecture for object detection in JPEG images, one of the most widespread compression format. We train a neural network to detect objects based on the blockwise DCT (discrete cosine transform) coefficients {issued from} the JPEG compression algorithm. We modify the well-known Single Shot multibox Detector (SSD) by replacing its first layers with one convolutional layer dedicated to process the DCT inputs. Experimental evaluations on PASCAL VOC and industrial dataset comprising images of road traffic surveillance show that the model is about $2\times$ faster than regular SSD with promising detection performances. To the best of our knowledge, this paper is the first to address detection in compressed JPEG images.
Tasks	Object Detection, Real-Time Object Detection
Published	2019-04-16
URL	http://arxiv.org/abs/1904.08408v1
PDF	http://arxiv.org/pdf/1904.08408v1.pdf
PWC	https://paperswithcode.com/paper/fast-object-detection-in-compressed-jpeg
Repo
Framework

Physics-Based Rendering for Improving Robustness to Rain


Title	Physics-Based Rendering for Improving Robustness to Rain
Authors	Shirsendu Sukanta Halder, Jean-François Lalonde, Raoul de Charette
Abstract	To improve the robustness to rain, we present a physically-based rain rendering pipeline for realistically inserting rain into clear weather images. Our rendering relies on a physical particle simulator, an estimation of the scene lighting and an accurate rain photometric modeling to augment images with arbitrary amount of realistic rain or fog. We validate our rendering with a user study, proving our rain is judged 40% more realistic that state-of-the-art. Using our generated weather augmented Kitti and Cityscapes dataset, we conduct a thorough evaluation of deep object detection and semantic segmentation algorithms and show that their performance decreases in degraded weather, on the order of 15% for object detection and 60% for semantic segmentation. Furthermore, we show refining existing networks with our augmented images improves the robustness of both object detection and semantic segmentation algorithms. We experiment on nuScenes and measure an improvement of 15% for object detection and 35% for semantic segmentation compared to original rainy performance. Augmented databases and code are available on the project page.
Tasks	Object Detection, Semantic Segmentation
Published	2019-08-27
URL	https://arxiv.org/abs/1908.10335v1
PDF	https://arxiv.org/pdf/1908.10335v1.pdf
PWC	https://paperswithcode.com/paper/physics-based-rendering-for-improving
Repo
Framework

ERNet Family: Hardware-Oriented CNN Models for Computational Imaging Using Block-Based Inference


Title	ERNet Family: Hardware-Oriented CNN Models for Computational Imaging Using Block-Based Inference
Authors	Chao-Tsung Huang
Abstract	Convolutional neural networks (CNNs) demand huge DRAM bandwidth for computational imaging tasks, and block-based processing has recently been applied to greatly reduce the bandwidth. However, the induced additional computation for feature recomputing or the large SRAM for feature reusing will degrade the performance or even forbid the usage of state-of-the-art models. In this paper, we address these issues by considering the overheads and hardware constraints in advance when constructing CNNs. We investigate a novel model family—ERNet—which includes temporary layer expansion as another means for increasing model capacity. We analyze three ERNet variants in terms of hardware requirement and introduce a hardware-aware model optimization procedure. Evaluations on Full HD and 4K UHD applications will be given to show the effectiveness in terms of image quality, pixel throughput, and SRAM usage. The results also show that, for block-based inference, ERNet can outperform the state-of-the-art FFDNet and EDSR-baseline models for image denoising and super-resolution respectively.
Tasks	Denoising, Image Denoising, Super-Resolution
Published	2019-10-13
URL	https://arxiv.org/abs/1910.05787v2
PDF	https://arxiv.org/pdf/1910.05787v2.pdf
PWC	https://paperswithcode.com/paper/ernet-family-hardware-oriented-cnn-models-for
Repo
Framework

A unifying representer theorem for inverse problems and machine learning


Title	A unifying representer theorem for inverse problems and machine learning
Authors	Michael Unser
Abstract	The standard approach for dealing with the ill-posedness of the training problem in machine learning and/or the reconstruction of a signal from a limited number of measurements is regularization. The method is applicable whenever the problem is formulated as an optimization task. The standard strategy consists in augmenting the original cost functional by an energy that penalizes solutions with undesirable behavior. The effect of regularization is very well understood when the penalty involves a Hilbertian norm. Another popular configuration is the use of an $\ell_1$-norm (or some variant thereof) that favors sparse solutions. In this paper, we propose a higher-level formulation of regularization within the context of Banach spaces. We present a general representer theorem that characterizes the solutions of a remarkably broad class of optimization problems. We then use our theorem to retrieve a number of known results in the literature—e.g., the celebrated representer theorem of machine leaning for RKHS, Tikhonov regularization, representer theorems for sparsity promoting functionals, the recovery of spikes—as well as a few new ones.
Tasks
Published	2019-03-02
URL	https://arxiv.org/abs/1903.00687v2
PDF	https://arxiv.org/pdf/1903.00687v2.pdf
PWC	https://paperswithcode.com/paper/a-unifying-representer-theorem-for-inverse
Repo
Framework