April 2, 2020

2939 words 14 mins read

Paper Group ANR 149

A Classification-Based Approach to Semi-Supervised Clustering with Pairwise Constraints. Learning to See Analogies: A Connectionist Exploration. Vox2Vox: 3D-GAN for Brain Tumour Segmentation. DeLTra: Deep Light Transport for Projector-Camera Systems. Stable variation in multidimensional competition. Submodular Rank Aggregation on Score-based Permut …

A Classification-Based Approach to Semi-Supervised Clustering with Pairwise Constraints


Title	A Classification-Based Approach to Semi-Supervised Clustering with Pairwise Constraints
Authors	Marek Śmieja, Łukasz Struski, Mário A. T. Figueiredo
Abstract	In this paper, we introduce a neural network framework for semi-supervised clustering (SSC) with pairwise (must-link or cannot-link) constraints. In contrast to existing approaches, we decompose SSC into two simpler classification tasks/stages: the first stage uses a pair of Siamese neural networks to label the unlabeled pairs of points as must-link or cannot-link; the second stage uses the fully pairwise-labeled dataset produced by the first stage in a supervised neural-network-based clustering method. The proposed approach, S3C2 (Semi-Supervised Siamese Classifiers for Clustering), is motivated by the observation that binary classification (such as assigning pairwise relations) is usually easier than multi-class clustering with partial supervision. On the other hand, being classification-based, our method solves only well-defined classification problems, rather than less well specified clustering tasks. Extensive experiments on various datasets demonstrate the high performance of the proposed method.
Tasks
Published	2020-01-18
URL	https://arxiv.org/abs/2001.06720v1
PDF	https://arxiv.org/pdf/2001.06720v1.pdf
PWC	https://paperswithcode.com/paper/a-classification-based-approach-to-semi
Repo
Framework

Learning to See Analogies: A Connectionist Exploration


Title	Learning to See Analogies: A Connectionist Exploration
Authors	Douglas S. Blank
Abstract	This dissertation explores the integration of learning and analogy-making through the development of a computer program, called Analogator, that learns to make analogies by example. By “seeing” many different analogy problems, along with possible solutions, Analogator gradually develops an ability to make new analogies. That is, it learns to make analogies by analogy. This approach stands in contrast to most existing research on analogy-making, in which typically the a priori existence of analogical mechanisms within a model is assumed. The present research extends standard connectionist methodologies by developing a specialized associative training procedure for a recurrent network architecture. The network is trained to divide input scenes (or situations) into appropriate figure and ground components. Seeing one scene in terms of a particular figure and ground provides the context for seeing another in an analogous fashion. After training, the model is able to make new analogies between novel situations. Analogator has much in common with lower-level perceptual models of categorization and recognition; it thus serves as a unifying framework encompassing both high-level analogical learning and low-level perception. This approach is compared and contrasted with other computational models of analogy-making. The model’s training and generalization performance is examined, and limitations are discussed.
Tasks
Published	2020-01-18
URL	https://arxiv.org/abs/2001.06668v1
PDF	https://arxiv.org/pdf/2001.06668v1.pdf
PWC	https://paperswithcode.com/paper/learning-to-see-analogies-a-connectionist
Repo
Framework

Vox2Vox: 3D-GAN for Brain Tumour Segmentation


Title	Vox2Vox: 3D-GAN for Brain Tumour Segmentation
Authors	Marco Domenico Cirillo, David Abramian, Anders Eklund
Abstract	We propose a 3D volume-to-volume Generative Adversarial Network (GAN) for segmentation of brain tumours. The proposed model, called Vox2Vox, generates segmentations from multi-channel 3D MR images. The best results are obtained when the generator loss (a 3D U-Net) is weighted 5 times higher compared to the discriminator loss (a 3D GAN). For the BraTS 2018 training set we obtain (after ensembling 5 models) the following dice scores and Hausdorff 95 percentile distances: 90.66%, 82.54%, 78.71%, and 4.04 mm, 6.07 mm, 5.00 mm, for whole tumour, core tumour and enhancing tumour respectively. The proposed model is shown to compare favorably to the winners of the BraTS 2018 challenge, but a direct comparison is not possible.
Tasks
Published	2020-03-19
URL	https://arxiv.org/abs/2003.13653v1
PDF	https://arxiv.org/pdf/2003.13653v1.pdf
PWC	https://paperswithcode.com/paper/vox2vox-3d-gan-for-brain-tumour-segmentation
Repo
Framework

DeLTra: Deep Light Transport for Projector-Camera Systems


Title	DeLTra: Deep Light Transport for Projector-Camera Systems
Authors	Bingyao Huang, Haibin Ling
Abstract	In projector-camera systems, light transport models the propagation from projector emitted radiance to camera-captured irradiance. In this paper, we propose the first end-to-end trainable solution named Deep Light Transport (DeLTra) that estimates radiometrically uncalibrated projector-camera light transport. DeLTra is designed to have two modules: DepthToAtrribute and ShadingNet. DepthToAtrribute explicitly learns rays, depth and normal, and then estimates rough Phong illuminations. Afterwards, the CNN-based ShadingNet renders photorealistic camera-captured image using estimated shading attributes and rough Phong illuminations. A particular challenge addressed by DeLTra is occlusion, for which we exploit epipolar constraint and propose a novel differentiable direct light mask. Thus, it can be learned end-to-end along with the other DeLTra modules. Once trained, DeLTra can be applied simultaneously to three projector-camera tasks: image-based relighting, projector compensation and depth/normal reconstruction. In our experiments, DeLTra shows clear advantages over previous arts with promising quality and meanwhile being practically convenient.
Tasks
Published	2020-03-06
URL	https://arxiv.org/abs/2003.03040v1
PDF	https://arxiv.org/pdf/2003.03040v1.pdf
PWC	https://paperswithcode.com/paper/deltra-deep-light-transport-for-projector
Repo
Framework

Stable variation in multidimensional competition


Title	Stable variation in multidimensional competition
Authors	Henri Kauhanen
Abstract	The Fundamental Theorem of Language Change (Yang, 2000) implies the impossibility of stable variation in the Variational Learning framework, but only in the special case where two, and not more, grammatical variants compete. Introducing the notion of an advantage matrix, I generalize Variational Learning to situations where the learner receives input generated by more than two grammars, and show that diachronically stable variation is an intrinsic feature of several types of such multiple-grammar systems. This invites experimentalists to take the possibility of stable variation seriously and identifies one possible place where to look for it: situations of complex language contact.
Tasks
Published	2020-03-11
URL	https://arxiv.org/abs/2003.06265v1
PDF	https://arxiv.org/pdf/2003.06265v1.pdf
PWC	https://paperswithcode.com/paper/stable-variation-in-multidimensional
Repo
Framework

Submodular Rank Aggregation on Score-based Permutations for Distributed Automatic Speech Recognition


Title	Submodular Rank Aggregation on Score-based Permutations for Distributed Automatic Speech Recognition
Authors	Jun Qi, Chao-Han Huck Yang, Javier Tejedor
Abstract	Distributed automatic speech recognition (ASR) requires to aggregate outputs of distributed deep neural network (DNN)-based models. This work studies the use of submodular functions to design a rank aggregation on score-based permutations, which can be used for distributed ASR systems in both supervised and unsupervised modes. Specifically, we compose an aggregation rank function based on the Lovasz Bregman divergence for setting up linear structured convex and nested structured concave functions. The algorithm is based on stochastic gradient descent (SGD) and can obtain well-trained aggregation models. Our experiments on the distributed ASR system show that the submodular rank aggregation can obtain higher speech recognition accuracy than traditional aggregation methods like Adaboost. Code is available online~\footnote{https://github.com/uwjunqi/Subrank}.
Tasks	Speech Recognition
Published	2020-01-27
URL	https://arxiv.org/abs/2001.10529v1
PDF	https://arxiv.org/pdf/2001.10529v1.pdf
PWC	https://paperswithcode.com/paper/submodular-rank-aggregation-on-score-based
Repo
Framework

Data Transformation Insights in Self-supervision with Clustering Tasks


Title	Data Transformation Insights in Self-supervision with Clustering Tasks
Authors	Abhimanu Kumar, Aniket Anand Deshmukh, Urun Dogan, Denis Charles, Eren Manavoglu
Abstract	Self-supervision is key to extending use of deep learning for label scarce domains. For most of self-supervised approaches data transformations play an important role. However, up until now the impact of transformations have not been studied. Furthermore, different transformations may have different impact on the system. We provide novel insights into the use of data transformation in self-supervised tasks, specially pertaining to clustering. We show theoretically and empirically that certain set of transformations are helpful in convergence of self-supervised clustering. We also show the cases when the transformations are not helpful or in some cases even harmful. We show faster convergence rate with valid transformations for convex as well as certain family of non-convex objectives along with the proof of convergence to the original set of optima. We have synthetic as well as real world data experiments. Empirically our results conform with the theoretical insights provided.
Tasks
Published	2020-02-18
URL	https://arxiv.org/abs/2002.07384v1
PDF	https://arxiv.org/pdf/2002.07384v1.pdf
PWC	https://paperswithcode.com/paper/data-transformation-insights-in-self
Repo
Framework

An Hybrid Method for the Estimation of the Breast Mechanical Parameters


Title	An Hybrid Method for the Estimation of the Breast Mechanical Parameters
Authors	Diogo Lopes, António Ramires Fernandes, Stéphane Clain
Abstract	There are several numerical models that describe real phenomena being used to solve complex problems. For example, an accurate numerical breast model can provide assistance to surgeons with visual information of the breast as a result of a surgery simulation. The process of finding the model parameters requires numeric inputs, either based in medical imaging techniques, or other measures. Inputs can be processed by iterative methods (inverse elasticity solvers). Such solvers are highly robust and provide solutions within the required degree of accuracy. However, their computational complexity is costly. On the other hand, machine learning based approaches provide outputs in real-time. Although high accuracy rates can be achieved, these methods are not exempt from producing solutions outside the required degree of accuracy. In the context of real life situations, a non accurate solution might present complications to the patient. We present an hybrid parameter estimation method to take advantage of the positive features of each of the aforementioned approaches. Our method preserves both the real-time performance of deep-learning methods, and the reliability of inverse elasticity solvers. The underlying reasoning behind our proposal is the fact that deep-learning methods, such as neural networks, can provide accurate results in the majority of cases and they just need a fail-safe system to ensure its reliability. Hence, we propose using a Multilayer Neural Networks (MNN) to get an estimation which is in turn validated by a iterative solver. In case the MNN provides an estimation not within the required accuracy range, the solver refines the estimation until the required accuracy is achieved. Based on our results we can conclude that the presented hybrid method is able to complement the computational performance of MNNs with the robustness of iterative solver approaches.
Tasks
Published	2020-03-09
URL	https://arxiv.org/abs/2003.07274v1
PDF	https://arxiv.org/pdf/2003.07274v1.pdf
PWC	https://paperswithcode.com/paper/an-hybrid-method-for-the-estimation-of-the
Repo
Framework

Machine Learning in Quantitative PET Imaging


Title	Machine Learning in Quantitative PET Imaging
Authors	Tonghe Wang, Yang Lei, Yabo Fu, Walter J. Curran, Tian Liu, Xiaofeng Yang
Abstract	This paper reviewed the machine learning-based studies for quantitative positron emission tomography (PET). Specifically, we summarized the recent developments of machine learning-based methods in PET attenuation correction and low-count PET reconstruction by listing and comparing the proposed methods, study designs and reported performances of the current published studies with brief discussion on representative studies. The contributions and challenges among the reviewed studies were summarized and highlighted in the discussion part followed by.
Tasks
Published	2020-01-18
URL	https://arxiv.org/abs/2001.06597v1
PDF	https://arxiv.org/pdf/2001.06597v1.pdf
PWC	https://paperswithcode.com/paper/machine-learning-in-quantitative-pet-imaging
Repo
Framework

Collaborative Inference for Efficient Remote Monitoring


Title	Collaborative Inference for Efficient Remote Monitoring
Authors	Chi Zhang, Yong Sheng Soh, Ling Feng, Tianyi Zhou, Qianxiao Li
Abstract	While current machine learning models have impressive performance over a wide range of applications, their large size and complexity render them unsuitable for tasks such as remote monitoring on edge devices with limited storage and computational power. A naive approach to resolve this on the model level is to use simpler architectures, but this sacrifices prediction accuracy and is unsuitable for monitoring applications requiring accurate detection of the onset of adverse events. In this paper, we propose an alternative solution to this problem by decomposing the predictive model as the sum of a simple function which serves as a local monitoring tool, and a complex correction term to be evaluated on the server. A sign requirement is imposed on the latter to ensure that the local monitoring function is safe, in the sense that it can effectively serve as an early warning system. Our analysis quantifies the trade-offs between model complexity and performance, and serves as a guidance for architecture design. We validate our proposed framework on a series of monitoring experiments, where we succeed at learning monitoring models with significantly reduced complexity that minimally violate the safety requirement. More broadly, our framework is useful for learning classifiers in applications where false negatives are significantly more costly compared to false positives.
Tasks
Published	2020-02-12
URL	https://arxiv.org/abs/2002.04759v1
PDF	https://arxiv.org/pdf/2002.04759v1.pdf
PWC	https://paperswithcode.com/paper/collaborative-inference-for-efficient-remote
Repo
Framework

Triplet Online Instance Matching Loss for Person Re-identification


Title	Triplet Online Instance Matching Loss for Person Re-identification
Authors	Ye Li, Guangqiang Yin, Chunhui Liu, Xiaoyu Yang, Zhiguo Wang
Abstract	Mining the shared features of same identity in different scene, and the unique features of different identity in same scene, are most significant challenges in the field of person re-identification (ReID). Online Instance Matching (OIM) loss function and Triplet loss function are main methods for person ReID. Unfortunately, both of them have drawbacks. OIM loss treats all samples equally and puts no emphasis on hard samples. Triplet loss processes batch construction in a complicated and fussy way and converges slowly. For these problems, we propose a Triplet Online Instance Matching (TOIM) loss function, which lays emphasis on the hard samples and improves the accuracy of person ReID effectively. It combines the advantages of OIM loss and Triplet loss and simplifies the process of batch construction, which leads to a more rapid convergence. It can be trained on-line when handle the joint detection and identification task. To validate our loss function, we collect and annotate a large-scale benchmark dataset (UESTC-PR) based on images taken from surveillance cameras, which contains 499 identities and 60,437 images. We evaluated our proposed loss function on Duke, Marker-1501 and UESTC-PR using ResNet-50, and the result shows that our proposed loss function outperforms the baseline methods by a maximum of 21.7%, including Softmax loss, OIM loss and Triplet loss.
Tasks	Person Re-Identification
Published	2020-02-24
URL	https://arxiv.org/abs/2002.10560v1
PDF	https://arxiv.org/pdf/2002.10560v1.pdf
PWC	https://paperswithcode.com/paper/triplet-online-instance-matching-loss-for
Repo
Framework

A Convolutional Baseline for Person Re-Identification Using Vision and Language Descriptions


Title	A Convolutional Baseline for Person Re-Identification Using Vision and Language Descriptions
Authors	Ammarah Farooq, Muhammad Awais, Fei Yan, Josef Kittler, Ali Akbari, Syed Safwan Khalid
Abstract	Classical person re-identification approaches assume that a person of interest has appeared across different cameras and can be queried by one of the existing images. However, in real-world surveillance scenarios, frequently no visual information will be available about the queried person. In such scenarios, a natural language description of the person by a witness will provide the only source of information for retrieval. In this work, person re-identification using both vision and language information is addressed under all possible gallery and query scenarios. A two stream deep convolutional neural network framework supervised by cross entropy loss is presented. The weights connecting the second last layer to the last layer with class probabilities, i.e., logits of softmax layer are shared in both networks. Canonical Correlation Analysis is performed to enhance the correlation between the two modalities in a joint latent embedding space. To investigate the benefits of the proposed approach, a new testing protocol under a multi modal ReID setting is proposed for the test split of the CUHK-PEDES and CUHK-SYSU benchmarks. The experimental results verify the merits of the proposed system. The learnt visual representations are more robust and perform 22% better during retrieval as compared to a single modality system. The retrieval with a multi modal query greatly enhances the re-identification capability of the system quantitatively as well as qualitatively.
Tasks	Person Re-Identification
Published	2020-02-20
URL	https://arxiv.org/abs/2003.00808v1
PDF	https://arxiv.org/pdf/2003.00808v1.pdf
PWC	https://paperswithcode.com/paper/a-convolutional-baseline-for-person-re
Repo
Framework

Lifted Hybrid Variational Inference


Title	Lifted Hybrid Variational Inference
Authors	Yuqiao Chen, Yibo Yang, Sriraam Natarajan, Nicholas Ruozzi
Abstract	A variety of lifted inference algorithms, which exploit model symmetry to reduce computational cost, have been proposed to render inference tractable in probabilistic relational models. Most existing lifted inference algorithms operate only over discrete domains or continuous domains with restricted potential functions, e.g., Gaussian. We investigate two approximate lifted variational approaches that are applicable to hybrid domains and expressive enough to capture multi-modality. We demonstrate that the proposed variational methods are both scalable and can take advantage of approximate model symmetries, even in the presence of a large amount of continuous evidence. We demonstrate that our approach compares favorably against existing message-passing based approaches in a variety of settings. Finally, we present a sufficient condition for the Bethe approximation to yield a non-trivial estimate over the marginal polytope.
Tasks
Published	2020-01-08
URL	https://arxiv.org/abs/2001.02773v2
PDF	https://arxiv.org/pdf/2001.02773v2.pdf
PWC	https://paperswithcode.com/paper/lifted-hybrid-variational-inference
Repo
Framework

OoDAnalyzer: Interactive Analysis of Out-of-Distribution Samples


Title	OoDAnalyzer: Interactive Analysis of Out-of-Distribution Samples
Authors	Changjian Chen, Jun Yuan, Yafeng Lu, Yang Liu, Hang Su, Songtao Yuan, Shixia Liu
Abstract	One major cause of performance degradation in predictive models is that the test samples are not well covered by the training data. Such not well-represented samples are called OoD samples. In this paper, we propose OoDAnalyzer, a visual analysis approach for interactively identifying OoD samples and explaining them in context. Our approach integrates an ensemble OoD detection method and a grid-based visualization. The detection method is improved from deep ensembles by combining more features with algorithms in the same family. To better analyze and understand the OoD samples in context, we have developed a novel kNN-based grid layout algorithm motivated by Hall’s theorem. The algorithm approximates the optimal layout and has $O(kN^2)$ time complexity, faster than the grid layout algorithm with overall best performance but $O(N^3)$ time complexity. Quantitative evaluation and case studies were performed on several datasets to demonstrate the effectiveness and usefulness of OoDAnalyzer.
Tasks
Published	2020-02-08
URL	https://arxiv.org/abs/2002.03103v1
PDF	https://arxiv.org/pdf/2002.03103v1.pdf
PWC	https://paperswithcode.com/paper/oodanalyzer-interactive-analysis-of-out-of
Repo
Framework

Modeling Contrary-to-Duty with CP-nets


Title	Modeling Contrary-to-Duty with CP-nets
Authors	Roberta Calegari, Andrea Loreggia, Emiliano Lorini, Francesca Rossi, Giovanni Sartor
Abstract	In a ceteris-paribus semantics for deontic logic, a state of affairs where a larger set of prescriptions is respected is preferable to a state of affairs where some of them are violated. Conditional preference nets (CP-nets) are a compact formalism to express and analyse ceteris paribus preferences, which nice computational properties. This paper shows how deontic concepts can be captured through conditional preference models. A restricted deontic logic will be defined, and mapped into conditional preference nets. We shall also show how to model contrary to duties obligations in CP-nets and how to capture in this formalism the distinction between strong and weak permission.
Tasks
Published	2020-03-23
URL	https://arxiv.org/abs/2003.10480v1
PDF	https://arxiv.org/pdf/2003.10480v1.pdf
PWC	https://paperswithcode.com/paper/modeling-contrary-to-duty-with-cp-nets
Repo
Framework