January 25, 2020

3236 words 16 mins read

Paper Group ANR 1768

Scalable Bayesian Preference Learning for Crowds. Can We Trust You? On Calibration of a Probabilistic Object Detector for Autonomous Driving. A Structural Graph-Based Method for MRI Analysis. Deep learning Inversion of Seismic Data. Numerical Gaussian process Kalman filtering. Causality matters in medical imaging. Towards Pose-invariant Lip-Reading …

Scalable Bayesian Preference Learning for Crowds


Title	Scalable Bayesian Preference Learning for Crowds
Authors	Edwin Simpson, Iryna Gurevych
Abstract	We propose a scalable Bayesian preference learning method for jointly predicting the preferences of individuals as well as the consensus of a crowd from pairwise labels. Peoples’ opinions often differ greatly, making it difficult to predict their preferences from small amounts of personal data. Individual biases also make it harder to infer the consensus of a crowd when there are few labels per item. We address these challenges by combining matrix factorisation with Gaussian processes, using a Bayesian approach to account for uncertainty arising from noisy and sparse data. Our method exploits input features, such as text embeddings and user metadata, to predict preferences for new items and users that are not in the training set. As previous solutions based on Gaussian processes do not scale to large numbers of users, items or pairwise labels, we propose a stochastic variational inference approach that limits computational and memory costs. Our experiments on a recommendation task show that our method is competitive with previous approaches despite our scalable inference approximation. We demonstrate the method’s scalability on a natural language processing task with thousands of users and items, and show improvements over the state of the art on this task. We make our software publicly available for future work.
Tasks	Gaussian Processes
Published	2019-12-04
URL	https://arxiv.org/abs/1912.01987v2
PDF	https://arxiv.org/pdf/1912.01987v2.pdf
PWC	https://paperswithcode.com/paper/scalable-bayesian-preference-learning-for
Repo
Framework

Can We Trust You? On Calibration of a Probabilistic Object Detector for Autonomous Driving


Title	Can We Trust You? On Calibration of a Probabilistic Object Detector for Autonomous Driving
Authors	Di Feng, Lars Rosenbaum, Claudius Glaeser, Fabian Timm, Klaus Dietmayer
Abstract	Reliable uncertainty estimation is crucial for perception systems in safe autonomous driving. Recently, many methods have been proposed to model uncertainties in deep learning based object detectors. However, the estimated probabilities are often uncalibrated, which may lead to severe problems in safety critical scenarios. In this work, we identify such uncertainty miscalibration problems in a probabilistic LiDAR 3D object detection network, and propose three practical methods to significantly reduce errors in uncertainty calibration. Extensive experiments on several datasets show that our methods produce well-calibrated uncertainties, and generalize well between different datasets.
Tasks	3D Object Detection, Autonomous Driving, Calibration, Object Detection
Published	2019-09-26
URL	https://arxiv.org/abs/1909.12358v1
PDF	https://arxiv.org/pdf/1909.12358v1.pdf
PWC	https://paperswithcode.com/paper/can-we-trust-you-on-calibration-of-a
Repo
Framework

A Structural Graph-Based Method for MRI Analysis


Title	A Structural Graph-Based Method for MRI Analysis
Authors	Larissa de O. Penteado, Mateus Riva, Roberto M. Cesar Jr
Abstract	The importance of imaging exams, such as Magnetic Resonance Imaging (MRI), for the diagnostic and follow-up of pediatric pathologies and the assessment of anatomical structures’ development has been increasingly highlighted in recent times. Manual analysis of MRIs is time-consuming, subjective, and requires significant expertise. To mitigate this, automatic techniques are necessary. Most techniques focus on adult subjects, while pediatric MRI has specific challenges such as the ongoing anatomical and histological changes related to normal development of the organs, reduced signal-to-noise ratio due to the smaller bodies, motion artifacts and cooperation issues, especially in long exams, which can in many cases preclude common analysis methods developed for use in adults. Therefore, the development of a robust technique to aid in pediatric MRI analysis is necessary. This paper presents the current development of a new method based on the learning and matching of structural relational graphs (SRGs). The experiments were performed on liver MRI sequences of one patient from ICr-HC-FMUSP, and preliminary results showcased the viability of the project. Future experiments are expected to culminate with an application for pediatric liver substructure and brain tumor segmentation.
Tasks	Brain Tumor Segmentation
Published	2019-08-02
URL	https://arxiv.org/abs/1908.00778v1
PDF	https://arxiv.org/pdf/1908.00778v1.pdf
PWC	https://paperswithcode.com/paper/a-structural-graph-based-method-for-mri
Repo
Framework

Deep learning Inversion of Seismic Data


Title	Deep learning Inversion of Seismic Data
Authors	Shucai Li, Bin Liu, Yuxiao Ren, Yangkang Chen, Senlin Yang, Yunhai Wang, Peng Jiang
Abstract	In this paper, we propose a new method to tackle the mapping challenge from time-series data to spatial image in the field of seismic exploration, i.e., reconstructing the velocity model directly from seismic data by deep neural networks (DNNs). The conventional way to address this ill-posed seismic inversion problem is through iterative algorithms, which suffer from poor nonlinear mapping and strong non-uniqueness. Other attempts may either import human intervention errors or underuse seismic data. The challenge for DNNs mainly lies in the weak spatial correspondence, the uncertain reflection-reception relationship between seismic data and velocity model as well as the time-varying property of seismic data. To approach these challenges, we propose an end-to-end Seismic Inversion Networks (SeisInvNet for short) with novel components to make the best use of all seismic data. Specifically, we start with every seismic trace and enhance it with its neighborhood information, its observation setup and global context of its corresponding seismic profile. Then from enhanced seismic traces, the spatially aligned feature maps can be learned and further concatenated to reconstruct velocity model. In general, we let every seismic trace contribute to the reconstruction of the whole velocity model by finding spatial correspondence. The proposed SeisInvNet consistently produces improvements over the baselines and achieves promising performance on our proposed SeisInv dataset according to various evaluation metrics, and the inversion results are more consistent with the target from the aspects of velocity value, subsurface structure and geological interface. In addition to the superior performance, the mechanism is also carefully discussed, and some potential problems are identified for further study.
Tasks	Time Series
Published	2019-01-23
URL	http://arxiv.org/abs/1901.07733v1
PDF	http://arxiv.org/pdf/1901.07733v1.pdf
PWC	https://paperswithcode.com/paper/deep-learning-inversion-of-seismic-data
Repo
Framework

Numerical Gaussian process Kalman filtering


Title	Numerical Gaussian process Kalman filtering
Authors	Armin Küper, Steffen Waldherr
Abstract	Numerical Gaussian processes have recently been developed to handle spatiotemporal models. The contribution of this paper is to embed numerical Gaussian processes into the well established recursive Kalman filter equations. This enables us to do Kalman filtering for infinite-dimensional systems with Gaussian processes. This is possible because i) we are obtaining a linear model from numerical Gaussian processes, and ii) the states of which are by definition Gaussian distributed random variables. Convenient properties of the numerical GPKF are that no spatial discretization is necessary, and setting up of the Kalman filter, namely the process and measurement noise levels, need not be fine-tuned by hand, as they are hyper-parameters of the Gaussian process and learned online on the data stream. We showcase the capability of the numerical GPKF in a simulation study of a heterogeneous cell population displaying cell-to-cell variability in cell size.
Tasks	Gaussian Processes
Published	2019-12-03
URL	https://arxiv.org/abs/1912.01234v1
PDF	https://arxiv.org/pdf/1912.01234v1.pdf
PWC	https://paperswithcode.com/paper/numerical-gaussian-process-kalman-filtering
Repo
Framework

Causality matters in medical imaging


Title	Causality matters in medical imaging
Authors	Daniel C. Castro, Ian Walker, Ben Glocker
Abstract	This article discusses how the language of causality can shed new light on the major challenges in machine learning for medical imaging: 1) data scarcity, which is the limited availability of high-quality annotations, and 2) data mismatch, whereby a trained algorithm may fail to generalize in clinical practice. Looking at these challenges through the lens of causality allows decisions about data collection, annotation procedures, and learning strategies to be made (and scrutinized) more transparently. We discuss how causal relationships between images and annotations can not only have profound effects on the performance of predictive models, but may even dictate which learning strategies should be considered in the first place. For example, we conclude that semi-supervision may be unsuitable for image segmentation—one of the possibly surprising insights from our causal analysis, which is illustrated with representative real-world examples of computer-aided diagnosis (skin lesion classification in dermatology) and radiotherapy (automated contouring of tumours). We highlight that being aware of and accounting for the causal relationships in medical imaging data is important for the safe development of machine learning and essential for regulation and responsible reporting. To facilitate this we provide step-by-step recommendations for future studies.
Tasks	Semantic Segmentation, Skin Lesion Classification
Published	2019-12-17
URL	https://arxiv.org/abs/1912.08142v1
PDF	https://arxiv.org/pdf/1912.08142v1.pdf
PWC	https://paperswithcode.com/paper/causality-matters-in-medical-imaging
Repo
Framework

Towards Pose-invariant Lip-Reading


Title	Towards Pose-invariant Lip-Reading
Authors	Shiyang Cheng, Pingchuan Ma, Georgios Tzimiropoulos, Stavros Petridis, Adrian Bulat, Jie Shen, Maja Pantic
Abstract	Lip-reading models have been significantly improved recently thanks to powerful deep learning architectures. However, most works focused on frontal or near frontal views of the mouth. As a consequence, lip-reading performance seriously deteriorates in non-frontal mouth views. In this work, we present a framework for training pose-invariant lip-reading models on synthetic data instead of collecting and annotating non-frontal data which is costly and tedious. The proposed model significantly outperforms previous approaches on non-frontal views while retaining the superior performance on frontal and near frontal mouth views. Specifically, we propose to use a 3D Morphable Model (3DMM) to augment LRW, an existing large-scale but mostly frontal dataset, by generating synthetic facial data in arbitrary poses. The newly derived dataset, is used to train a state-of-the-art neural network for lip-reading. We conducted a cross-database experiment for isolated word recognition on the LRS2 dataset, and reported an absolute improvement of 2.55%. The benefit of the proposed approach becomes clearer in extreme poses where an absolute improvement of up to 20.64% over the baseline is achieved.
Tasks
Published	2019-11-14
URL	https://arxiv.org/abs/1911.06095v1
PDF	https://arxiv.org/pdf/1911.06095v1.pdf
PWC	https://paperswithcode.com/paper/towards-pose-invariant-lip-reading
Repo
Framework

An Active Learning Approach for Reducing Annotation Cost in Skin Lesion Analysis


Title	An Active Learning Approach for Reducing Annotation Cost in Skin Lesion Analysis
Authors	Xueying Shi, Qi Dou, Cheng Xue, Jing Qin, Hao Chen, Pheng-Ann Heng
Abstract	Automated skin lesion analysis is very crucial in clinical practice, as skin cancer is among the most common human malignancy. Existing approaches with deep learning have achieved remarkable performance on this challenging task, however, heavily relying on large-scale labelled datasets. In this paper, we present a novel active learning framework for cost-effective skin lesion analysis. The goal is to effectively select and utilize much fewer labelled samples, while the network can still achieve state-of-the-art performance. Our sample selection criteria complementarily consider both informativeness and representativeness, derived from decoupled aspects of measuring model certainty and covering sample diversity. To make wise use of the selected samples, we further design a simple yet effective strategy to aggregate intra-class images in pixel space, as a new form of data augmentation. We validate our proposed method on data of ISIC 2017 Skin Lesion Classification Challenge for two tasks. Using only up to 50% of samples, our approach can achieve state-of-the-art performances on both tasks, which are comparable or exceeding the accuracies with full-data training, and outperform other well-known active learning methods by a large margin.
Tasks	Active Learning, Data Augmentation, Skin Lesion Classification
Published	2019-09-05
URL	https://arxiv.org/abs/1909.02344v1
PDF	https://arxiv.org/pdf/1909.02344v1.pdf
PWC	https://paperswithcode.com/paper/an-active-learning-approach-for-reducing
Repo
Framework

Ship classification from overhead imagery using synthetic data and domain adaptation


Title	Ship classification from overhead imagery using synthetic data and domain adaptation
Authors	Chris M. Ward, Josh Harguess, Cameron Hilton
Abstract	In this paper, we revisit the problem of classifying ships (maritime vessels) detected from overhead imagery. Despite the last decade of research on this very important and pertinent problem, it remains largely unsolved. One of the major issues with the detection and classification of ships and other objects in the maritime domain is the lack of substantial ground truth data needed to train state-of-the-art machine learning algorithms. We address this issue by building a large (200k) synthetic image dataset using the Unity gaming engine and 3D ship models. We demonstrate that with the use of synthetic data, classification performance increases dramatically, particularly when there are very few annotated images used in training.
Tasks	Domain Adaptation
Published	2019-05-10
URL	https://arxiv.org/abs/1905.03894v1
PDF	https://arxiv.org/pdf/1905.03894v1.pdf
PWC	https://paperswithcode.com/paper/ship-classification-from-overhead-imagery
Repo
Framework

Simultaneous Transformation and Rounding (STAR) Models for Integer-Valued Data


Title	Simultaneous Transformation and Rounding (STAR) Models for Integer-Valued Data
Authors	Daniel R. Kowal, Antonio Canale
Abstract	We propose a simple yet powerful framework for modeling integer-valued data, such as counts, scores, and rounded data. The data-generating process is defined by Simultaneously Transforming and Rounding (STAR) a continuous-valued process, which produces a flexible family of integer-valued distributions capable of modeling zero-inflation, bounded or censored data, and over- or underdispersion. The transformation is modeled as unknown for greater distributional flexibility, while the rounding operation ensures a coherent integer-valued data-generating process. An efficient MCMC algorithm is developed for posterior inference and provides a mechanism for adaptation of successful Bayesian models and algorithms for continuous data to the integer-valued data setting. Using the STAR framework, we design a new Bayesian Additive Regression Tree (BART) model for integer-valued data, which demonstrates impressive predictive distribution accuracy for both synthetic data and a large healthcare utilization dataset. For interpretable regression-based inference, we develop a STAR additive model, which offers greater flexibility and scalability than existing integer-valued models. The STAR additive model is applied to study the recent decline in Amazon river dolphins.
Tasks
Published	2019-06-27
URL	https://arxiv.org/abs/1906.11653v2
PDF	https://arxiv.org/pdf/1906.11653v2.pdf
PWC	https://paperswithcode.com/paper/a-simultaneous-transformation-and-rounding
Repo
Framework

Semantically Aligned Bias Reducing Zero Shot Learning


Title	Semantically Aligned Bias Reducing Zero Shot Learning
Authors	Akanksha Paul, Narayanan C. Krishnan, Prateek Munjal
Abstract	Zero shot learning (ZSL) aims to recognize unseen classes by exploiting semantic relationships between seen and unseen classes. Two major problems faced by ZSL algorithms are the hubness problem and the bias towards the seen classes. Existing ZSL methods focus on only one of these problems in the conventional and generalized ZSL setting. In this work, we propose a novel approach, Semantically Aligned Bias Reducing (SABR) ZSL, which focuses on solving both the problems. It overcomes the hubness problem by learning a latent space that preserves the semantic relationship between the labels while encoding the discriminating information about the classes. Further, we also propose ways to reduce the bias of the seen classes through a simple cross-validation process in the inductive setting and a novel weak transfer constraint in the transductive setting. Extensive experiments on three benchmark datasets suggest that the proposed model significantly outperforms existing state-of-the-art algorithms by ~1.5-9% in the conventional ZSL setting and by ~2-14% in the generalized ZSL for both the inductive and transductive settings.
Tasks	Zero-Shot Learning
Published	2019-04-16
URL	http://arxiv.org/abs/1904.07659v1
PDF	http://arxiv.org/pdf/1904.07659v1.pdf
PWC	https://paperswithcode.com/paper/semantically-aligned-bias-reducing-zero-shot
Repo
Framework

Adaptive Adjustment with Semantic Feature Space for Zero-Shot Recognition


Title	Adaptive Adjustment with Semantic Feature Space for Zero-Shot Recognition
Authors	Jingcai Guo, Song Guo
Abstract	In most recent years, zero-shot recognition (ZSR) has gained increasing attention in machine learning and image processing fields. It aims at recognizing unseen class instances with knowledge transferred from seen classes. This is typically achieved by exploiting a pre-defined semantic feature space (FS), i.e., semantic attributes or word vectors, as a bridge to transfer knowledge between seen and unseen classes. However, due to the absence of unseen classes during training, the conventional ZSR easily suffers from domain shift and hubness problems. In this paper, we propose a novel ZSR learning framework that can handle these two issues well by adaptively adjusting semantic FS. To the best of our knowledge, our work is the first to consider the adaptive adjustment of semantic FS in ZSR. Moreover, our solution can be formulated to a more efficient framework that significantly boosts the training. Extensive experiments show the remarkable performance improvement of our model compared with other existing methods.
Tasks	Zero-Shot Learning
Published	2019-03-30
URL	http://arxiv.org/abs/1904.00170v1
PDF	http://arxiv.org/pdf/1904.00170v1.pdf
PWC	https://paperswithcode.com/paper/adaptive-adjustment-with-semantic-feature
Repo
Framework


Title	Unsupervised training of a deep clustering model for multichannel blind source separation
Authors	Lukas Drude, Daniel Hasenklever, Reinhold Haeb-Umbach
Abstract	We propose a training scheme to train neural network-based source separation algorithms from scratch when parallel clean data is unavailable. In particular, we demonstrate that an unsupervised spatial clustering algorithm is sufficient to guide the training of a deep clustering system. We argue that previous work on deep clustering requires strong supervision and elaborate on why this is a limitation. We demonstrate that (a) the single-channel deep clustering system trained according to the proposed scheme alone is able to achieve a similar performance as the multi-channel teacher in terms of word error rates and (b) initializing the spatial clustering approach with the deep clustering result yields a relative word error rate reduction of 26 % over the unsupervised teacher.
Tasks	Unsupervised Spatial Clustering
Published	2019-04-02
URL	http://arxiv.org/abs/1904.01340v1
PDF	http://arxiv.org/pdf/1904.01340v1.pdf
PWC	https://paperswithcode.com/paper/unsupervised-training-of-a-deep-clustering
Repo
Framework

Difficulty-aware Meta-Learning for Rare Disease Diagnosis


Title	Difficulty-aware Meta-Learning for Rare Disease Diagnosis
Authors	Xiaomeng Li, Lequan Yu, Chi-Wing Fu, Pheng-Ann Heng
Abstract	Rare diseases have extremely low-data regimes, unlike common diseases with large amount of available labeled data. Hence, to train a neural network to classify rare diseases with a few per-class data samples is very challenging, and so far, catches very little attention. In this paper, we present a difficulty-aware meta-learning method to address rare disease classifications and demonstrate its capability to classify dermoscopy images. Our key approach is to first train and construct a meta-learning model from data of common diseases, then adapt the model to perform rare disease classification.To achieve this, we develop the difficulty-aware meta-learning method that dynamically monitors the importance of learning tasks during the meta-optimization stage. To evaluate our method, we use the recent ISIC 2018 skin lesion classification dataset, and show that with only five samples per class, our model can quickly adapt to classify unseen classes by a high AUC of 83.3%. Also, we evaluated several rare disease classification results in the public Dermofit Image Library to demonstrate the potential of our method for real clinical practice.
Tasks	Meta-Learning, Skin Lesion Classification
Published	2019-06-30
URL	https://arxiv.org/abs/1907.00354v1
PDF	https://arxiv.org/pdf/1907.00354v1.pdf
PWC	https://paperswithcode.com/paper/difficulty-aware-meta-learning-for-rare
Repo
Framework

From complex to simple : hierarchical free-energy landscape renormalized in deep neural networks


Title	From complex to simple : hierarchical free-energy landscape renormalized in deep neural networks
Authors	Hajime Yoshino
Abstract	We develop a statistical mechanical approach based on the replica method to study the design space of deep and wide neural networks constrained to meet a large number of training data. Specifically, we analyze the configuration space of the synaptic weights and neurons in the hidden layers in a simple feed-forward perceptron network for two scenarios: a setting with random inputs/outputs and a teacher-student setting. By increasing the strength of constraints,~i.e. increasing the number of training data, successive 2nd order glass transition (random inputs/outputs) or 2nd order crystalline transition (teacher-student setting) take place layer-by-layer starting next to the inputs/outputs boundaries going deeper into the bulk with the thickness of the solid phase growing logarithmically with the data size. This implies the typical storage capacity of the network grows exponentially fast with the depth. In a deep enough network, the central part remains in the liquid phase. We argue that in systems of finite width N, the weak bias field can remain in the center and plays the role of a symmetry-breaking field that connects the opposite sides of the system. The successive glass transitions bring about a hierarchical free-energy landscape with ultrametricity, which evolves in space: it is most complex close to the boundaries but becomes renormalized into progressively simpler ones in deeper layers. These observations provide clues to understand why deep neural networks operate efficiently. Finally, we present some numerical simulations of learning which reveal spatially heterogeneous glassy dynamics truncated by a finite width $N$ effect.
Tasks
Published	2019-10-22
URL	https://arxiv.org/abs/1910.09918v3
PDF	https://arxiv.org/pdf/1910.09918v3.pdf
PWC	https://paperswithcode.com/paper/from-complex-to-simple-hierarchical-free
Repo
Framework