January 25, 2020

3290 words 16 mins read

Paper Group ANR 1657

Semantic Example Guided Image-to-Image Translation. Shadow Transfer: Single Image Relighting For Urban Road Scenes. One-to-one Mapping for Unpaired Image-to-image Translation. Paired-Consistency: An Example-Based Model-Agnostic Approach to Fairness Regularization in Machine Learning. Characterizing the Variability in Face Recognition Accuracy Relat …

Semantic Example Guided Image-to-Image Translation


Title	Semantic Example Guided Image-to-Image Translation
Authors	Jialu Huang, Jing Liao, Tak Wu Sam Kwong
Abstract	Many image-to-image (I2I) translation problems are in nature of high diversity that a single input may have various counterparts. Prior works proposed the multi-modal network that can build a many-to-many mapping between two visual domains. However, most of them are guided by sampled noises. Some others encode the reference images into a latent vector, by which the semantic information of the reference image will be washed away. In this work, we aim to provide a solution to control the output based on references semantically. Given a reference image and an input in another domain, a semantic matching is first performed between the two visual contents and generates the auxiliary image, which is explicitly encouraged to preserve semantic characteristics of the reference. A deep network then is used for I2I translation and the final outputs are expected to be semantically similar to both the input and the reference; however, no such paired data can satisfy that dual-similarity in a supervised fashion, so we build up a self-supervised framework to serve the training purpose. We improve the quality and diversity of the outputs by employing non-local blocks and a multi-task architecture. We assess the proposed method through extensive qualitative and quantitative evaluations and also presented comparisons with several state-of-art models.
Tasks	Image-to-Image Translation
Published	2019-09-28
URL	https://arxiv.org/abs/1909.13028v2
PDF	https://arxiv.org/pdf/1909.13028v2.pdf
PWC	https://paperswithcode.com/paper/semantic-example-guided-image-to-image
Repo
Framework

Shadow Transfer: Single Image Relighting For Urban Road Scenes


Title	Shadow Transfer: Single Image Relighting For Urban Road Scenes
Authors	Alexandra Carlson, Ram Vasudevan, Matthew Johnson-Roberson
Abstract	Illumination effects in images, specifically cast shadows and shading, have been shown to decrease the performance of deep neural networks on a large number of vision-based detection, recognition and segmentation tasks in urban driving scenes. A key factor that contributes to this performance gap is the lack of `time-of-day’ diversity within real, labeled datasets. There have been impressive advances in the realm of image to image translation in transferring previously unseen visual effects into a dataset, specifically in day to night translation. However, it is not easy to constrain what visual effects, let alone illumination effects, are transferred from one dataset to another during the training process. To address this problem, we propose deep learning framework, called Shadow Transfer, that can relight complex outdoor scenes by transferring realistic shadow, shading, and other lighting effects onto a single image. The novelty of the proposed framework is that it is both self-supervised, and is designed to operate on sensor and label information that is easily available in autonomous vehicle datasets. We show the effectiveness of this method on both synthetic and real datasets, and we provide experiments that demonstrate that the proposed method produces images of higher visual quality than state of the art image to image translation methods. \|
Tasks	Image-to-Image Translation
Published	2019-09-23
URL	https://arxiv.org/abs/1909.10363v2
PDF	https://arxiv.org/pdf/1909.10363v2.pdf
PWC	https://paperswithcode.com/paper/190910363
Repo
Framework

One-to-one Mapping for Unpaired Image-to-image Translation


Title	One-to-one Mapping for Unpaired Image-to-image Translation
Authors	Zengming Shen, S. Kevin Zhou, Yifan Chen, Bogdan Georgescu, Xuqi Liu, Thomas S. Huang
Abstract	Recently image-to-image translation has attracted significant interests in the literature, starting from the successful use of the generative adversarial network (GAN), to the introduction of cyclic constraint, to extensions to multiple domains. However, in existing approaches, there is no guarantee that the mapping between two image domains is unique or one-to-one. Here we propose a self-inverse network learning approach for unpaired image-to-image translation. Building on top of CycleGAN, we learn a self-inverse function by simply augmenting the training samples by swapping inputs and outputs during training and with separated cycle consistency loss for each mapping direction. The outcome of such learning is a proven one-to-one mapping function. Our extensive experiments on a variety of datasets, including cross-modal medical image synthesis, object transfiguration, and semantic labeling, consistently demonstrate clear improvement over the CycleGAN method both qualitatively and quantitatively. Especially our proposed method reaches the state-of-the-art result on the cityscapes benchmark dataset for the label to photo unpaired directional image translation.
Tasks	Image Generation, Image-to-Image Translation
Published	2019-09-09
URL	https://arxiv.org/abs/1909.04110v6
PDF	https://arxiv.org/pdf/1909.04110v6.pdf
PWC	https://paperswithcode.com/paper/learning-a-self-inverse-network-for-unpaired
Repo
Framework

Paired-Consistency: An Example-Based Model-Agnostic Approach to Fairness Regularization in Machine Learning


Title	Paired-Consistency: An Example-Based Model-Agnostic Approach to Fairness Regularization in Machine Learning
Authors	Yair Horesh, Noa Haas, Elhanan Mishraky, Yehezkel S. Resheff, Shir Meir Lador
Abstract	As AI systems develop in complexity it is becoming increasingly hard to ensure non-discrimination on the basis of protected attributes such as gender, age, and race. Many recent methods have been developed for dealing with this issue as long as the protected attribute is explicitly available for the algorithm. We address the setting where this is not the case (with either no explicit protected attribute, or a large set of them). Instead, we assume the existence of a fair domain expert capable of generating an extension to the labeled dataset - a small set of example pairs, each having a different value on a subset of protected variables, but judged to warrant a similar model response. We define a performance metric - paired consistency. Paired consistency measures how close the output (assigned by a classifier or a regressor) is on these carefully selected pairs of examples for which fairness dictates identical decisions. In some cases consistency can be embedded within the loss function during optimization and serve as a fairness regularizer, and in others it is a tool for fair model selection. We demonstrate our method using the well studied Income Census dataset.
Tasks	Model Selection
Published	2019-08-07
URL	https://arxiv.org/abs/1908.02641v2
PDF	https://arxiv.org/pdf/1908.02641v2.pdf
PWC	https://paperswithcode.com/paper/paired-consistency-an-example-based-model
Repo
Framework

Characterizing the Variability in Face Recognition Accuracy Relative to Race


Title	Characterizing the Variability in Face Recognition Accuracy Relative to Race
Authors	KS Krishnapriya, Kushal Vangara, Michael C. King, Vitor Albiero, Kevin Bowyer
Abstract	Many recent news headlines have labeled face recognition technology as biased or racist. We report on a methodical investigation into differences in face recognition accuracy between African-American and Caucasian image cohorts of the MORPH dataset. We find that, for all four matchers considered, the impostor and the genuine distributions are statistically significantly different between cohorts. For a fixed decision threshold, the African-American image cohort has a higher false match rate and a lower false non-match rate. ROC curves compare verification rates at the same false match rate, but the different cohorts achieve the same false match rate at different thresholds. This means that ROC comparisons are not relevant to operational scenarios that use a fixed decision threshold. We show that, for the ResNet matcher, the two cohorts have approximately equal separation of impostor and genuine distributions. Using ICAO compliance as a standard of image quality, we find that the initial image cohorts have unequal rates of good quality images. The ICAO-compliant subsets of the original image cohorts show improved accuracy, with the main effect being to reducing the low-similarity tail of the genuine distributions.
Tasks	Face Recognition
Published	2019-04-15
URL	https://arxiv.org/abs/1904.07325v3
PDF	https://arxiv.org/pdf/1904.07325v3.pdf
PWC	https://paperswithcode.com/paper/characterizing-the-variability-in-face
Repo
Framework

Polynomial Tensor Sketch for Element-wise Function of Low-Rank Matrix


Title	Polynomial Tensor Sketch for Element-wise Function of Low-Rank Matrix
Authors	Insu Han, Haim Avron, Jinwoo Shin
Abstract	This paper studies how to sketch element-wise functions of low-rank matrices. Formally, given low-rank matrix A = [Aij] and scalar non-linear function f, we aim for finding an approximated low-rank representation of the (possibly high-rank) matrix [f(Aij)]. To this end, we propose an efficient sketching-based algorithm whose complexity is significantly lower than the number of entries of A, i.e., it runs without accessing all entries of [f(Aij)] explicitly. The main idea underlying our method is to combine a polynomial approximation of f with the existing tensor sketch scheme for approximating monomials of entries of A. To balance the errors of the two approximation components in an optimal manner, we propose a novel regression formula to find polynomial coefficients given A and f. In particular, we utilize a coreset-based regression with a rigorous approximation guarantee. Finally, we demonstrate the applicability and superiority of the proposed scheme under various machine learning tasks.
Tasks
Published	2019-05-28
URL	https://arxiv.org/abs/1905.11616v2
PDF	https://arxiv.org/pdf/1905.11616v2.pdf
PWC	https://paperswithcode.com/paper/polynomial-tensor-sketch-for-element-wise
Repo
Framework

NormLime: A New Feature Importance Metric for Explaining Deep Neural Networks


Title	NormLime: A New Feature Importance Metric for Explaining Deep Neural Networks
Authors	Isaac Ahern, Adam Noack, Luis Guzman-Nateras, Dejing Dou, Boyang Li, Jun Huan
Abstract	The problem of explaining deep learning models, and model predictions generally, has attracted intensive interest recently. Many successful approaches forgo global approximations in order to provide more faithful local interpretations of the model’s behavior. LIME develops multiple interpretable models, each approximating a large neural network on a small region of the data manifold and SP-LIME aggregates the local models to form a global interpretation. Extending this line of research, we propose a simple yet effective method, NormLIME for aggregating local models into global and class-specific interpretations. A human user study strongly favored class-specific interpretations created by NormLIME to other feature importance metrics. Numerical experiments confirm that NormLIME is effective at recognizing important features.
Tasks	Feature Importance
Published	2019-09-10
URL	https://arxiv.org/abs/1909.04200v2
PDF	https://arxiv.org/pdf/1909.04200v2.pdf
PWC	https://paperswithcode.com/paper/normlime-a-new-feature-importance-metric-for
Repo
Framework

Learning Continuous 3D Reconstructions for Geometrically Aware Grasping


Title	Learning Continuous 3D Reconstructions for Geometrically Aware Grasping
Authors	Mark Van der Merwe, Qingkai Lu, Balakumar Sundaralingam, Martin Matak, Tucker Hermans
Abstract	Deep learning has enabled remarkable improvements in grasp synthesis for previously unseen objects from partial object views. However, existing approaches lack the ability to explicitly reason about the full 3D geometry of the object when selecting a grasp, relying on indirect geometric reasoning derived when learning grasp success networks. This abandons explicit geometric reasoning, such as avoiding undesired robot object collisions. We propose to utilize a novel, learned 3D reconstruction to enable geometric awareness in a grasping system. We leverage the structure of the reconstruction network to learn a grasp success classifier which serves as the objective function for a continuous grasp optimization. We additionally explicitly constrain the optimization to avoid undesired contact, directly using the reconstruction. We examine the role of geometry in grasping both in the training of grasp metrics and through 96 robot grasping trials. Our results can be found on https://sites.google.com/view/reconstruction-grasp/.
Tasks	3D Reconstruction, Common Sense Reasoning
Published	2019-10-02
URL	https://arxiv.org/abs/1910.00983v2
PDF	https://arxiv.org/pdf/1910.00983v2.pdf
PWC	https://paperswithcode.com/paper/learning-continuous-3d-reconstructions-for
Repo
Framework

Unsupervised Domain Adaptation of Contextual Embeddings for Low-Resource Duplicate Question Detection


Title	Unsupervised Domain Adaptation of Contextual Embeddings for Low-Resource Duplicate Question Detection
Authors	Alexandre Rochette, Yadollah Yaghoobzadeh, Timothy J. Hazen
Abstract	Answering questions is a primary goal of many conversational systems or search products. While most current systems have focused on answering questions against structured databases or curated knowledge graphs, on-line community forums or frequently asked questions (FAQ) lists offer an alternative source of information for question answering systems. Automatic duplicate question detection (DQD) is the key technology need for question answering systems to utilize existing online forums like StackExchange. Existing annotations of duplicate questions in such forums are community-driven, making them sparse or even completely missing for many domains. Therefore, it is important to transfer knowledge from related domains and tasks. Recently, contextual embedding models such as BERT have been outperforming many baselines by transferring self-supervised information to downstream tasks. In this paper, we apply BERT to DQD and advance it by unsupervised adaptation to StackExchange domains using self-supervised learning. We show the effectiveness of this adaptation for low-resource settings, where little or no training data is available from the target domain. Our analysis reveals that unsupervised BERT domain adaptation on even small amounts of data boosts the performance of BERT.
Tasks	Domain Adaptation, Knowledge Graphs, Question Answering, Unsupervised Domain Adaptation
Published	2019-11-06
URL	https://arxiv.org/abs/1911.02645v1
PDF	https://arxiv.org/pdf/1911.02645v1.pdf
PWC	https://paperswithcode.com/paper/unsupervised-domain-adaptation-of-contextual
Repo
Framework

On the Stability and Generalization of Learning with Kernel Activation Functions


Title	On the Stability and Generalization of Learning with Kernel Activation Functions
Authors	Michele Cirillo, Simone Scardapane, Steven Van Vaerenbergh, Aurelio Uncini
Abstract	In this brief we investigate the generalization properties of a recently-proposed class of non-parametric activation functions, the kernel activation functions (KAFs). KAFs introduce additional parameters in the learning process in order to adapt nonlinearities individually on a per-neuron basis, exploiting a cheap kernel expansion of every activation value. While this increase in flexibility has been shown to provide significant improvements in practice, a theoretical proof for its generalization capability has not been addressed yet in the literature. Here, we leverage recent literature on the stability properties of non-convex models trained via stochastic gradient descent (SGD). By indirectly proving two key smoothness properties of the models under consideration, we prove that neural networks endowed with KAFs generalize well when trained with SGD for a finite number of steps. Interestingly, our analysis provides a guideline for selecting one of the hyper-parameters of the model, the bandwidth of the scalar Gaussian kernel. A short experimental evaluation validates the proof.
Tasks
Published	2019-03-28
URL	http://arxiv.org/abs/1903.11990v1
PDF	http://arxiv.org/pdf/1903.11990v1.pdf
PWC	https://paperswithcode.com/paper/on-the-stability-and-generalization-of
Repo
Framework

Network Transfer Learning via Adversarial Domain Adaptation with Graph Convolution


Title	Network Transfer Learning via Adversarial Domain Adaptation with Graph Convolution
Authors	Quanyu Dai, Xiao Shen, Xiao-Ming Wu, Dan Wang
Abstract	This paper studies the problem of cross-network node classification to overcome the insufficiency of labeled data in a single network. It aims to leverage the label information in a partially labeled source network to assist node classification in a completely unlabeled or partially labeled target network. Existing methods for single network learning cannot solve this problem due to the domain shift across networks. Some multi-network learning methods heavily rely on the existence of cross-network connections, thus are inapplicable for this problem. To tackle this problem, we propose a novel network transfer learning framework AdaGCN by leveraging the techniques of adversarial domain adaptation and graph convolution. It consists of two components: a semi-supervised learning component and an adversarial domain adaptation component. The former aims to learn class discriminative node representations with given label information of the source and target networks, while the latter contributes to mitigating the distribution divergence between the source and target domains to facilitate knowledge transfer. Extensive empirical evaluations on real-world datasets show that AdaGCN can successfully transfer class information with a low label rate on the source network and a substantial divergence between the source and target domains. Codes will be released upon acceptance.
Tasks	Domain Adaptation, Node Classification, Transfer Learning
Published	2019-09-04
URL	https://arxiv.org/abs/1909.01541v1
PDF	https://arxiv.org/pdf/1909.01541v1.pdf
PWC	https://paperswithcode.com/paper/network-transfer-learning-via-adversarial
Repo
Framework

Long-Bone Fracture Detection using Artificial Neural Networks based on Contour Features of X-ray Images


Title	Long-Bone Fracture Detection using Artificial Neural Networks based on Contour Features of X-ray Images
Authors	Alice Yi Yang, Ling Cheng
Abstract	The following paper proposes two contour-based fracture detection schemes. The development of the contour-based fracture is based on the line-based fracture detection schemes proposed in arXiv:1902.07458. Existing Computer Aided Diagnosis (CAD) systems commonly employs Convolutional Neural Networks (CNN), although the cost to obtain a high accuracy is the amount of training data required. The purpose of the proposed schemes is to obtain a high classification accuracy with a reduced number of training data through the use of detected contours in X-ray images. There are two contour-based fracture detection schemes. The first is the Standard Contour Histogram Feature-Based (CHFB) and the second is the improved CHFB scheme. The difference between the two schemes is the removal of the surrounding detected flesh contours from the leg region in the improved CHFB scheme. The flesh contours are automatically classified as non-fractures. The contours are further refined to give a precise representation of the image edge objects. A total of 19 features are extracted from each refined contour. 8 out of the 19 features are based on the number of occurrences for particular detected gradients in the contour. Moreover, the occurrence of the 0-degree gradient in the contours are employed for the separation of the knee, leg and foot region. The features are a summary representation of the contour, in which it is used as inputs into the Artificial Neural Network (ANN). Both Standard CHFB and improved CHFB schemes are evaluated with the same experimental set-ups. The average system accuracy for the Standard CHFB scheme is 80.7%, whilst the improved CHFB scheme has an average accuracy of 82.98%. Additionally, the hierarchical clustering technique is adopted to highlight the fractured region within the X-ray image, using extracted 0-degree gradients from fractured contours.
Tasks
Published	2019-02-21
URL	http://arxiv.org/abs/1902.07897v1
PDF	http://arxiv.org/pdf/1902.07897v1.pdf
PWC	https://paperswithcode.com/paper/long-bone-fracture-detection-using-artificial-1
Repo
Framework

Unsupervised Segmentation of Hyperspectral Images Using 3D Convolutional Autoencoders


Title	Unsupervised Segmentation of Hyperspectral Images Using 3D Convolutional Autoencoders
Authors	Jakub Nalepa, Michal Myller, Yasuteru Imai, Ken-ichi Honda, Tomomi Takeda, Marek Antoniak
Abstract	Hyperspectral image analysis has become an important topic widely researched by the remote sensing community. Classification and segmentation of such imagery help understand the underlying materials within a scanned scene, since hyperspectral images convey a detailed information captured in a number of spectral bands. Although deep learning has established the state of the art in the field, it still remains challenging to train well-generalizing models due to the lack of ground-truth data. In this letter, we tackle this problem and propose an end-to-end approach to segment hyperspectral images in a fully unsupervised way. We introduce a new deep architecture which couples 3D convolutional autoencoders with clustering. Our multi-faceted experimental study—performed over benchmark and real-life data—revealed that our approach delivers high-quality segmentation without any prior class labels.
Tasks
Published	2019-07-20
URL	https://arxiv.org/abs/1907.08870v1
PDF	https://arxiv.org/pdf/1907.08870v1.pdf
PWC	https://paperswithcode.com/paper/unsupervised-segmentation-of-hyperspectral
Repo
Framework

Topic Spotting using Hierarchical Networks with Self Attention


Title	Topic Spotting using Hierarchical Networks with Self Attention
Authors	Pooja Chitkara, Ashutosh Modi, Pravalika Avvaru, Sepehr Janghorbani, Mubbasir Kapadia
Abstract	Success of deep learning techniques have renewed the interest in development of dialogue systems. However, current systems struggle to have consistent long term conversations with the users and fail to build rapport. Topic spotting, the task of automatically inferring the topic of a conversation, has been shown to be helpful in making a dialog system more engaging and efficient. We propose a hierarchical model with self attention for topic spotting. Experiments on the Switchboard corpus show the superior performance of our model over previously proposed techniques for topic spotting and deep models for text classification. Additionally, in contrast to offline processing of dialog, we also analyze the performance of our model in a more realistic setting i.e. in an online setting where the topic is identified in real time as the dialog progresses. Results show that our model is able to generalize even with limited information in the online setting.
Tasks	Text Classification
Published	2019-04-04
URL	http://arxiv.org/abs/1904.02815v1
PDF	http://arxiv.org/pdf/1904.02815v1.pdf
PWC	https://paperswithcode.com/paper/topic-spotting-using-hierarchical-networks
Repo
Framework

Greedy inference with layers of lazy maps


Title	Greedy inference with layers of lazy maps
Authors	Daniele Bigoni, Olivier Zahm, Alessio Spantini, Youssef Marzouk
Abstract	We propose a framework for the greedy approximation of high-dimensional Bayesian inference problems, through the composition of multiple \emph{low-dimensional} transport maps or flows. Our framework operates recursively on a sequence of ``residual’’ distributions, given by pulling back the posterior through the previously computed transport maps. The action of each map is confined to a low-dimensional subspace that we identify by minimizing an error bound. At each step, our approach thus identifies (i) a relevant subspace of the residual distribution, and (ii) a low-dimensional transformation between a restriction of the residual onto this subspace and a standard Gaussian. We prove weak convergence of the approach to the posterior distribution, and we demonstrate the algorithm on a range of challenging inference problems in differential equations and spatial statistics. \|
Tasks	Bayesian Inference
Published	2019-05-31
URL	https://arxiv.org/abs/1906.00031v1
PDF	https://arxiv.org/pdf/1906.00031v1.pdf
PWC	https://paperswithcode.com/paper/190600031
Repo
Framework