October 21, 2019

3255 words 16 mins read

Paper Group AWR 164

Adversarially Regularising Neural NLI Models to Integrate Logical Background Knowledge. Cluster-Based Learning from Weakly Labeled Bags in Digital Pathology. NeuralWarp: Time-Series Similarity with Warping Networks. Triplet-Center Loss for Multi-View 3D Object Retrieval. Constructing Fast Network through Deconstruction of Convolution. One-shot doma …

Adversarially Regularising Neural NLI Models to Integrate Logical Background Knowledge


Title	Adversarially Regularising Neural NLI Models to Integrate Logical Background Knowledge
Authors	Pasquale Minervini, Sebastian Riedel
Abstract	Adversarial examples are inputs to machine learning models designed to cause the model to make a mistake. They are useful for understanding the shortcomings of machine learning models, interpreting their results, and for regularisation. In NLP, however, most example generation strategies produce input text by using known, pre-specified semantic transformations, requiring significant manual effort and in-depth understanding of the problem and domain. In this paper, we investigate the problem of automatically generating adversarial examples that violate a set of given First-Order Logic constraints in Natural Language Inference (NLI). We reduce the problem of identifying such adversarial examples to a combinatorial optimisation problem, by maximising a quantity measuring the degree of violation of such constraints and by using a language model for generating linguistically-plausible examples. Furthermore, we propose a method for adversarially regularising neural NLI models for incorporating background knowledge. Our results show that, while the proposed method does not always improve results on the SNLI and MultiNLI datasets, it significantly and consistently increases the predictive accuracy on adversarially-crafted datasets – up to a 79.6% relative improvement – while drastically reducing the number of background knowledge violations. Furthermore, we show that adversarial examples transfer among model architectures, and that the proposed adversarial training procedure improves the robustness of NLI models to adversarial examples.
Tasks	Language Modelling, Natural Language Inference
Published	2018-08-26
URL	http://arxiv.org/abs/1808.08609v1
PDF	http://arxiv.org/pdf/1808.08609v1.pdf
PWC	https://paperswithcode.com/paper/adversarially-regularising-neural-nli-models
Repo	https://github.com/uclmr/adversarial-nli
Framework	tf

Cluster-Based Learning from Weakly Labeled Bags in Digital Pathology


Title	Cluster-Based Learning from Weakly Labeled Bags in Digital Pathology
Authors	Shazia Akbar, Anne L. Martel
Abstract	To alleviate the burden of gathering detailed expert annotations when training deep neural networks, we propose a weakly supervised learning approach to recognize metastases in microscopic images of breast lymph nodes. We describe an alternative training loss which clusters weakly labeled bags in latent space to inform relevance of patch-instances during training of a convolutional neural network. We evaluate our method on the Camelyon dataset which contains high-resolution digital slides of breast lymph nodes, where labels are provided at the image-level and only subsets of patches are made available during training.
Tasks
Published	2018-11-28
URL	http://arxiv.org/abs/1812.00884v1
PDF	http://arxiv.org/pdf/1812.00884v1.pdf
PWC	https://paperswithcode.com/paper/cluster-based-learning-from-weakly-labeled
Repo	https://github.com/shaziaakbar/cluster-mil
Framework	tf

NeuralWarp: Time-Series Similarity with Warping Networks


Title	NeuralWarp: Time-Series Similarity with Warping Networks
Authors	Josif Grabocka, Lars Schmidt-Thieme
Abstract	Research on time-series similarity measures has emphasized the need for elastic methods which align the indices of pairs of time series and a plethora of non-parametric have been proposed for the task. On the other hand, deep learning approaches are dominant in closely related domains, such as learning image and text sentence similarity. In this paper, we propose \textit{NeuralWarp}, a novel measure that models the alignment of time-series indices in a deep representation space, by modeling a warping function as an upper level neural network between deeply-encoded time series values. Experimental results demonstrate that \textit{NeuralWarp} outperforms both non-parametric and un-warped deep models on a range of diverse real-life datasets.
Tasks	Time Series
Published	2018-12-20
URL	http://arxiv.org/abs/1812.08306v1
PDF	http://arxiv.org/pdf/1812.08306v1.pdf
PWC	https://paperswithcode.com/paper/neuralwarp-time-series-similarity-with
Repo	https://github.com/josifgrabocka/neuralwarp
Framework	tf

Triplet-Center Loss for Multi-View 3D Object Retrieval


Title	Triplet-Center Loss for Multi-View 3D Object Retrieval
Authors	Xinwei He, Yang Zhou, Zhichao Zhou, Song Bai, Xiang Bai
Abstract	Most existing 3D object recognition algorithms focus on leveraging the strong discriminative power of deep learning models with softmax loss for the classification of 3D data, while learning discriminative features with deep metric learning for 3D object retrieval is more or less neglected. In the paper, we study variants of deep metric learning losses for 3D object retrieval, which did not receive enough attention from this area. First , two kinds of representative losses, triplet loss and center loss, are introduced which could learn more discriminative features than traditional classification loss. Then, we propose a novel loss named triplet-center loss, which can further enhance the discriminative power of the features. The proposed triplet-center loss learns a center for each class and requires that the distances between samples and centers from the same class are closer than those from different classes. Extensive experimental results on two popular 3D object retrieval benchmarks and two widely-adopted sketch-based 3D shape retrieval benchmarks consistently demonstrate the effectiveness of our proposed loss, and significant improvements have been achieved compared with the state-of-the-arts.
Tasks	3D Object Recognition, 3D Object Retrieval, 3D Shape Retrieval, Metric Learning, Object Recognition
Published	2018-03-16
URL	http://arxiv.org/abs/1803.06189v1
PDF	http://arxiv.org/pdf/1803.06189v1.pdf
PWC	https://paperswithcode.com/paper/triplet-center-loss-for-multi-view-3d-object
Repo	https://github.com/popcornell/keras-triplet-center-loss
Framework	tf

Constructing Fast Network through Deconstruction of Convolution


Title	Constructing Fast Network through Deconstruction of Convolution
Authors	Yunho Jeon, Junmo Kim
Abstract	Convolutional neural networks have achieved great success in various vision tasks; however, they incur heavy resource costs. By using deeper and wider networks, network accuracy can be improved rapidly. However, in an environment with limited resources (e.g., mobile applications), heavy networks may not be usable. This study shows that naive convolution can be deconstructed into a shift operation and pointwise convolution. To cope with various convolutions, we propose a new shift operation called active shift layer (ASL) that formulates the amount of shift as a learnable function with shift parameters. This new layer can be optimized end-to-end through backpropagation and it can provide optimal shift values. Finally, we apply this layer to a light and fast network that surpasses existing state-of-the-art networks.
Tasks
Published	2018-05-28
URL	http://arxiv.org/abs/1806.07370v5
PDF	http://arxiv.org/pdf/1806.07370v5.pdf
PWC	https://paperswithcode.com/paper/constructing-fast-network-through
Repo	https://github.com/DeadAt0m/ActiveSparseShifts-PyTorch
Framework	pytorch

One-shot domain adaptation in multiple sclerosis lesion segmentation using convolutional neural networks


Title	One-shot domain adaptation in multiple sclerosis lesion segmentation using convolutional neural networks
Authors	Sergi Valverde, Mostafa Salem, Mariano Cabezas, Deborah Pareto, Joan C. Vilanova, Lluís Ramió-Torrentà, Àlex Rovira, Joaquim Salvi, Arnau Oliver, Xavier Lladó
Abstract	In recent years, several convolutional neural network (CNN) methods have been proposed for the automated white matter lesion segmentation of multiple sclerosis (MS) patient images, due to their superior performance compared with those of other state-of-the-art methods. However, the accuracies of CNN methods tend to decrease significantly when evaluated on different image domains compared with those used for training, which demonstrates the lack of adaptability of CNNs to unseen imaging data. In this study, we analyzed the effect of intensity domain adaptation on our recently proposed CNN-based MS lesion segmentation method. Given a source model trained on two public MS datasets, we investigated the transferability of the CNN model when applied to other MRI scanners and protocols, evaluating the minimum number of annotated images needed from the new domain and the minimum number of layers needed to re-train to obtain comparable accuracy. Our analysis comprised MS patient data from both a clinical center and the public ISBI2015 challenge database, which permitted us to compare the domain adaptation capability of our model to that of other state-of-the-art methods. For the ISBI2015 challenge, our one-shot domain adaptation model trained using only a single image showed a performance similar to that of other CNN methods that were fully trained using the entire available training set, yielding a comparable human expert rater performance. We believe that our experiments will encourage the MS community to incorporate its use in different clinical settings with reduced amounts of annotated data. This approach could be meaningful not only in terms of the accuracy in delineating MS lesions but also in the related reductions in time and economic costs derived from manual lesion labeling.
Tasks	Domain Adaptation, Lesion Segmentation
Published	2018-05-31
URL	http://arxiv.org/abs/1805.12415v1
PDF	http://arxiv.org/pdf/1805.12415v1.pdf
PWC	https://paperswithcode.com/paper/one-shot-domain-adaptation-in-multiple
Repo	https://github.com/NIC-VICOROB/nicmslesions
Framework	tf

Automatic segmentation of the spinal cord and intramedullary multiple sclerosis lesions with convolutional neural networks


Title	Automatic segmentation of the spinal cord and intramedullary multiple sclerosis lesions with convolutional neural networks
Authors	Charley Gros, Benjamin De Leener, Atef Badji, Josefina Maranzano, Dominique Eden, Sara M. Dupont, Jason Talbott, Ren Zhuoquiong, Yaou Liu, Tobias Granberg, Russell Ouellette, Yasuhiko Tachibana, Masaaki Hori, Kouhei Kamiya, Lydia Chougar, Leszek Stawiarz, Jan Hillert, Elise Bannier, Anne Kerbrat, Gilles Edan, Pierre Labauge, Virginie Callot, Jean Pelletier, Bertrand Audoin, Henitsoa Rasoanandrianina, Jean-Christophe Brisset, Paola Valsasina, Maria A. Rocca, Massimo Filippi, Rohit Bakshi, Shahamat Tauhid, Ferran Prados, Marios Yiannakas, Hugh Kearney, Olga Ciccarelli, Seth Smith, Constantina Andrada Treaba, Caterina Mainero, Jennifer Lefeuvre, Daniel S. Reich, Govind Nair, Vincent Auclair, Donald G. McLaren, Allan R. Martin, Michael G. Fehlings, Shahabeddin Vahdat, Ali Khatibi, Julien Doyon, Timothy Shepherd, Erik Charlson, Sridar Narayanan, Julien Cohen-Adad
Abstract	The spinal cord is frequently affected by atrophy and/or lesions in multiple sclerosis (MS) patients. Segmentation of the spinal cord and lesions from MRI data provides measures of damage, which are key criteria for the diagnosis, prognosis, and longitudinal monitoring in MS. Automating this operation eliminates inter-rater variability and increases the efficiency of large-throughput analysis pipelines. Robust and reliable segmentation across multi-site spinal cord data is challenging because of the large variability related to acquisition parameters and image artifacts. The goal of this study was to develop a fully-automatic framework, robust to variability in both image parameters and clinical condition, for segmentation of the spinal cord and intramedullary MS lesions from conventional MRI data. Scans of 1,042 subjects (459 healthy controls, 471 MS patients, and 112 with other spinal pathologies) were included in this multi-site study (n=30). Data spanned three contrasts (T1-, T2-, and T2*-weighted) for a total of 1,943 volumes. The proposed cord and lesion automatic segmentation approach is based on a sequence of two Convolutional Neural Networks (CNNs). To deal with the very small proportion of spinal cord and/or lesion voxels compared to the rest of the volume, a first CNN with 2D dilated convolutions detects the spinal cord centerline, followed by a second CNN with 3D convolutions that segments the spinal cord and/or lesions. When compared against manual segmentation, our CNN-based approach showed a median Dice of 95% vs. 88% for PropSeg, a state-of-the-art spinal cord segmentation method. Regarding lesion segmentation on MS data, our framework provided a Dice of 60%, a relative volume difference of -15%, and a lesion-wise detection sensitivity and precision of 83% and 77%, respectively. The proposed framework is open-source and readily available in the Spinal Cord Toolbox.
Tasks	Lesion Segmentation
Published	2018-05-16
URL	http://arxiv.org/abs/1805.06349v2
PDF	http://arxiv.org/pdf/1805.06349v2.pdf
PWC	https://paperswithcode.com/paper/automatic-segmentation-of-the-spinal-cord-and
Repo	https://github.com/sct-pipeline/deepseg-training
Framework	none

An Intersectional Definition of Fairness


Title	An Intersectional Definition of Fairness
Authors	James Foulds, Rashidul Islam, Kamrun Naher Keya, Shimei Pan
Abstract	We propose definitions of fairness in machine learning and artificial intelligence systems that are informed by the framework of intersectionality, a critical lens arising from the Humanities literature which analyzes how interlocking systems of power and oppression affect individuals along overlapping dimensions including gender, race, sexual orientation, class, and disability. We show that our criteria behave sensibly for any subset of the set of protected attributes, and we prove economic, privacy, and generalization guarantees. We provide a learning algorithm which respects our intersectional fairness criteria. Case studies on census data and the COMPAS criminal recidivism dataset demonstrate the utility of our methods.
Tasks
Published	2018-07-22
URL	https://arxiv.org/abs/1807.08362v3
PDF	https://arxiv.org/pdf/1807.08362v3.pdf
PWC	https://paperswithcode.com/paper/an-intersectional-definition-of-fairness
Repo	https://github.com/rashid-islam/Differential_Fairness
Framework	none

Trainable Projected Gradient Detector for Massive Overloaded MIMO Channels: Data-driven Tuning Approach


Title	Trainable Projected Gradient Detector for Massive Overloaded MIMO Channels: Data-driven Tuning Approach
Authors	Satoshi Takabe, Masayuki Imanishi, Tadashi Wadayama, Ryo Hayakawa, Kazunori Hayashi
Abstract	This paper presents a deep learning-aided iterative detection algorithm for massive overloaded multiple-input multiple-output (MIMO) systems where the number of transmit antennas $n$ is larger than that of receive antennas $m$. Since the proposed algorithm is based on the projected gradient descent method with trainable parameters, it is named the trainable projected gradient-detector (TPG-detector). The trainable internal parameters, such as the step-size parameter, can be optimized with standard deep learning techniques, i.e., the back propagation and stochastic gradient descent algorithms. This approach is referred to as data-driven tuning, and ensures fast convergence during parameter estimation in the proposed scheme. The TPG-detector mainly consists of matrix-vector product operations whose computational cost is proportional to $m n$ for each iteration. In addition, the number of trainable parameters in the TPG-detector is independent of the number of antennas. These features of the TPG-detector result in a fast and stable training process and reasonable scalability for large systems. Numerical simulations show that the proposed detector achieves a comparable detection performance to those of existing algorithms for massive overloaded MIMO channels, e.g., the state-of-the-art IW-SOAV detector, with a lower computation cost.
Tasks
Published	2018-12-25
URL	https://arxiv.org/abs/1812.10044v2
PDF	https://arxiv.org/pdf/1812.10044v2.pdf
PWC	https://paperswithcode.com/paper/trainable-projected-gradient-detector-for
Repo	https://github.com/wadayama/overloaded_MIMO
Framework	pytorch

Long-Term Feature Banks for Detailed Video Understanding


Title	Long-Term Feature Banks for Detailed Video Understanding
Authors	Chao-Yuan Wu, Christoph Feichtenhofer, Haoqi Fan, Kaiming He, Philipp Krähenbühl, Ross Girshick
Abstract	To understand the world, we humans constantly need to relate the present to the past, and put events in context. In this paper, we enable existing video models to do the same. We propose a long-term feature bank—supportive information extracted over the entire span of a video—to augment state-of-the-art video models that otherwise would only view short clips of 2-5 seconds. Our experiments demonstrate that augmenting 3D convolutional networks with a long-term feature bank yields state-of-the-art results on three challenging video datasets: AVA, EPIC-Kitchens, and Charades.
Tasks	Action Classification, Action Recognition In Videos, Video Understanding
Published	2018-12-12
URL	http://arxiv.org/abs/1812.05038v2
PDF	http://arxiv.org/pdf/1812.05038v2.pdf
PWC	https://paperswithcode.com/paper/long-term-feature-banks-for-detailed-video
Repo	https://github.com/facebookresearch/video-long-term-feature-banks
Framework	none

Weakly Supervised Localisation for Fetal Ultrasound Images


Title	Weakly Supervised Localisation for Fetal Ultrasound Images
Authors	Nicolas Toussaint, Bishesh Khanal, Matthew Sinclair, Alberto Gomez, Emily Skelton, Jacqueline Matthew, Julia A. Schnabel
Abstract	This paper addresses the task of detecting and localising fetal anatomical regions in 2D ultrasound images, where only image-level labels are present at training, i.e. without any localisation or segmentation information. We examine the use of convolutional neural network architectures coupled with soft proposal layers. The resulting network simultaneously performs anatomical region detection (classification) and localisation tasks. We generate a proposal map describing the attention of the network for a particular class. The network is trained on 85,500 2D fetal Ultrasound images and their associated labels. Labels correspond to six anatomical regions: head, spine, thorax, abdomen, limbs, and placenta. Detection achieves an average accuracy of 90% on individual regions, and show that the proposal maps correlate well with relevant anatomical structures. This work presents itself as a powerful and essential step towards subsequent tasks such as fetal position and pose estimation, organ-specific segmentation, or image-guided navigation. Code and additional material is available at https://ntoussaint.github.io/fetalnav.
Tasks	Pose Estimation
Published	2018-08-02
URL	http://arxiv.org/abs/1808.00793v1
PDF	http://arxiv.org/pdf/1808.00793v1.pdf
PWC	https://paperswithcode.com/paper/weakly-supervised-localisation-for-fetal
Repo	https://github.com/ntoussaint/qmedbrowser
Framework	none

Projecting Embeddings for Domain Adaptation: Joint Modeling of Sentiment Analysis in Diverse Domains


Title	Projecting Embeddings for Domain Adaptation: Joint Modeling of Sentiment Analysis in Diverse Domains
Authors	Jeremy Barnes, Roman Klinger, Sabine Schulte im Walde
Abstract	Domain adaptation for sentiment analysis is challenging due to the fact that supervised classifiers are very sensitive to changes in domain. The two most prominent approaches to this problem are structural correspondence learning and autoencoders. However, they either require long training times or suffer greatly on highly divergent domains. Inspired by recent advances in cross-lingual sentiment analysis, we provide a novel perspective and cast the domain adaptation problem as an embedding projection task. Our model takes as input two mono-domain embedding spaces and learns to project them to a bi-domain space, which is jointly optimized to (1) project across domains and to (2) predict sentiment. We perform domain adaptation experiments on 20 source-target domain pairs for sentiment classification and report novel state-of-the-art results on 11 domain pairs, including the Amazon domain adaptation datasets and SemEval 2013 and 2016 datasets. Our analysis shows that our model performs comparably to state-of-the-art approaches on domains that are similar, while performing significantly better on highly divergent domains. Our code is available at https://github.com/jbarnesspain/domain_blse
Tasks	Domain Adaptation, Sentiment Analysis
Published	2018-06-12
URL	http://arxiv.org/abs/1806.04381v2
PDF	http://arxiv.org/pdf/1806.04381v2.pdf
PWC	https://paperswithcode.com/paper/projecting-embeddings-for-domain-adaptation
Repo	https://github.com/jbarnesspain/domain_blse
Framework	pytorch

A Transfer-Learnable Natural Language Interface for Databases


Title	A Transfer-Learnable Natural Language Interface for Databases
Authors	Wenlu Wang, Yingtao Tian, Hongyu Xiong, Haixun Wang, Wei-Shinn Ku
Abstract	Relational database management systems (RDBMSs) are powerful because they are able to optimize and answer queries against any relational database. A natural language interface (NLI) for a database, on the other hand, is tailored to support that specific database. In this work, we introduce a general purpose transfer-learnable NLI with the goal of learning one model that can be used as NLI for any relational database. We adopt the data management principle of separating data and its schema, but with the additional support for the idiosyncrasy and complexity of natural languages. Specifically, we introduce an automatic annotation mechanism that separates the schema and the data, where the schema also covers knowledge about natural language. Furthermore, we propose a customized sequence model that translates annotated natural language queries to SQL statements. We show in experiments that our approach outperforms previous NLI methods on the WikiSQL dataset and the model we learned can be applied to another benchmark dataset OVERNIGHT without retraining.
Tasks
Published	2018-09-07
URL	http://arxiv.org/abs/1809.02649v1
PDF	http://arxiv.org/pdf/1809.02649v1.pdf
PWC	https://paperswithcode.com/paper/a-transfer-learnable-natural-language
Repo	https://github.com/VV123/NLIDB
Framework	tf

Probabilistic Semantic Inpainting with Pixel Constrained CNNs


Title	Probabilistic Semantic Inpainting with Pixel Constrained CNNs
Authors	Emilien Dupont, Suhas Suresha
Abstract	Semantic inpainting is the task of inferring missing pixels in an image given surrounding pixels and high level image semantics. Most semantic inpainting algorithms are deterministic: given an image with missing regions, a single inpainted image is generated. However, there are often several plausible inpaintings for a given missing region. In this paper, we propose a method to perform probabilistic semantic inpainting by building a model, based on PixelCNNs, that learns a distribution of images conditioned on a subset of visible pixels. Experiments on the MNIST and CelebA datasets show that our method produces diverse and realistic inpaintings.
Tasks
Published	2018-10-08
URL	http://arxiv.org/abs/1810.03728v2
PDF	http://arxiv.org/pdf/1810.03728v2.pdf
PWC	https://paperswithcode.com/paper/probabilistic-semantic-inpainting-with-pixel
Repo	https://github.com/Schlumberger/pixel-constrained-cnn-tf
Framework	tf

DeSIGN: Design Inspiration from Generative Networks


Title	DeSIGN: Design Inspiration from Generative Networks
Authors	Othman Sbai, Mohamed Elhoseiny, Antoine Bordes, Yann LeCun, Camille Couprie
Abstract	Can an algorithm create original and compelling fashion designs to serve as an inspirational assistant? To help answer this question, we design and investigate different image generation models associated with different loss functions to boost creativity in fashion generation. The dimensions of our explorations include: (i) different Generative Adversarial Networks architectures that start from noise vectors to generate fashion items, (ii) novel loss functions that encourage novelty, inspired from Sharma-Mittal divergence, a generalized mutual information measure for the widely used relative entropies such as Kullback-Leibler, and (iii) a generation process following the key elements of fashion design (disentangling shape and texture components). A key challenge of this study is the evaluation of generated designs and the retrieval of best ones, hence we put together an evaluation protocol associating automatic metrics and human experimental studies that we hope will help ease future research. We show that our proposed creativity criterion yield better overall appreciation than the one employed in Creative Adversarial Networks. In the end, about 61% of our images are thought to be created by human designers rather than by a computer while also being considered original per our human subject experiments, and our proposed loss scores the highest compared to existing losses in both novelty and likability.
Tasks	Image Generation
Published	2018-04-03
URL	http://arxiv.org/abs/1804.00921v2
PDF	http://arxiv.org/pdf/1804.00921v2.pdf
PWC	https://paperswithcode.com/paper/design-design-inspiration-from-generative
Repo	https://github.com/blufzzz/Design-Inspiration-from-Generative-Networks
Framework	pytorch