February 1, 2020

2907 words 14 mins read

Paper Group AWR 90

X-ray and Visible Spectra Circular Motion Images Dataset. Dual Averaging Method for Online Graph-structured Sparsity. Deep Triplet Quantization. On Tractable Computation of Expected Predictions. Repairing without Retraining: Avoiding Disparate Impact with Counterfactual Distributions. An Introduction to Probabilistic Spiking Neural Networks: Probab …

X-ray and Visible Spectra Circular Motion Images Dataset


Title	X-ray and Visible Spectra Circular Motion Images Dataset
Authors	Mikhail Chekanov, Oleg Shipitko
Abstract	We present the collections of images of the same rotating plastic object made in X-ray and visible spectra. Both parts of the dataset contain 400 images. The images are maid every 0.5 degrees of the object axial rotation. The collection of images is designed for evaluation of the performance of circular motion estimation algorithms as well as for the study of X-ray nature influence on the image analysis algorithms such as keypoints detection and description. The dataset is available at https://github.com/Visillect/xvcm-dataset.
Tasks	Motion Estimation
Published	2019-09-30
URL	https://arxiv.org/abs/1909.13730v2
PDF	https://arxiv.org/pdf/1909.13730v2.pdf
PWC	https://paperswithcode.com/paper/x-ray-and-visible-spectra-circular-motion
Repo	https://github.com/Visillect/xvcm-dataset
Framework	none

Dual Averaging Method for Online Graph-structured Sparsity


Title	Dual Averaging Method for Online Graph-structured Sparsity
Authors	Baojian Zhou, Feng Chen, Yiming Ying
Abstract	Online learning algorithms update models via one sample per iteration, thus efficient to process large-scale datasets and useful to detect malicious events for social benefits, such as disease outbreak and traffic congestion on the fly. However, existing algorithms for graph-structured models focused on the offline setting and the least square loss, incapable for online setting, while methods designed for online setting cannot be directly applied to the problem of complex (usually non-convex) graph-structured sparsity model. To address these limitations, in this paper we propose a new algorithm for graph-structured sparsity constraint problems under online setting, which we call \textsc{GraphDA}. The key part in \textsc{GraphDA} is to project both averaging gradient (in dual space) and primal variables (in primal space) onto lower dimensional subspaces, thus capturing the graph-structured sparsity effectively. Furthermore, the objective functions assumed here are generally convex so as to handle different losses for online learning settings. To the best of our knowledge, \textsc{GraphDA} is the first online learning algorithm for graph-structure constrained optimization problems. To validate our method, we conduct extensive experiments on both benchmark graph and real-world graph datasets. Our experiment results show that, compared to other baseline methods, \textsc{GraphDA} not only improves classification performance, but also successfully captures graph-structured features more effectively, hence stronger interpretability.
Tasks
Published	2019-05-26
URL	https://arxiv.org/abs/1905.10714v1
PDF	https://arxiv.org/pdf/1905.10714v1.pdf
PWC	https://paperswithcode.com/paper/dual-averaging-method-for-online-graph
Repo	https://github.com/baojianzhou/graph-da
Framework	none

Deep Triplet Quantization


Title	Deep Triplet Quantization
Authors	Bin Liu, Yue Cao, Mingsheng Long, Jianmin Wang, Jingdong Wang
Abstract	Deep hashing establishes efficient and effective image retrieval by end-to-end learning of deep representations and hash codes from similarity data. We present a compact coding solution, focusing on deep learning to quantization approach that has shown superior performance over hashing solutions for similarity retrieval. We propose Deep Triplet Quantization (DTQ), a novel approach to learning deep quantization models from the similarity triplets. To enable more effective triplet training, we design a new triplet selection approach, Group Hard, that randomly selects hard triplets in each image group. To generate compact binary codes, we further apply a triplet quantization with weak orthogonality during triplet training. The quantization loss reduces the codebook redundancy and enhances the quantizability of deep representations through back-propagation. Extensive experiments demonstrate that DTQ can generate high-quality and compact binary codes, which yields state-of-the-art image retrieval performance on three benchmark datasets, NUS-WIDE, CIFAR-10, and MS-COCO.
Tasks	Image Retrieval, Quantization
Published	2019-02-01
URL	http://arxiv.org/abs/1902.00153v1
PDF	http://arxiv.org/pdf/1902.00153v1.pdf
PWC	https://paperswithcode.com/paper/deep-triplet-quantization
Repo	https://github.com/thulab/DeepHash
Framework	tf

On Tractable Computation of Expected Predictions


Title	On Tractable Computation of Expected Predictions
Authors	Pasha Khosravi, YooJung Choi, Yitao Liang, Antonio Vergari, Guy Van den Broeck
Abstract	Computing expected predictions of discriminative models is a fundamental task in machine learning that appears in many interesting applications such as fairness, handling missing values, and data analysis. Unfortunately, computing expectations of a discriminative model with respect to a probability distribution defined by an arbitrary generative model has been proven to be hard in general. In fact, the task is intractable even for simple models such as logistic regression and a naive Bayes distribution. In this paper, we identify a pair of generative and discriminative models that enables tractable computation of expectations, as well as moments of any order, of the latter with respect to the former in case of regression. Specifically, we consider expressive probabilistic circuits with certain structural constraints that support tractable probabilistic inference. Moreover, we exploit the tractable computation of high-order moments to derive an algorithm to approximate the expectations for classification scenarios in which exact computations are intractable. Our framework to compute expected predictions allows for handling of missing data during prediction time in a principled and accurate way and enables reasoning about the behavior of discriminative models. We empirically show our algorithm to consistently outperform standard imputation techniques on a variety of datasets. Finally, we illustrate how our framework can be used for exploratory data analysis.
Tasks	Imputation
Published	2019-10-05
URL	https://arxiv.org/abs/1910.02182v2
PDF	https://arxiv.org/pdf/1910.02182v2.pdf
PWC	https://paperswithcode.com/paper/on-tractable-computation-of-expected
Repo	https://github.com/UCLA-StarAI/mc2
Framework	none

Repairing without Retraining: Avoiding Disparate Impact with Counterfactual Distributions


Title	Repairing without Retraining: Avoiding Disparate Impact with Counterfactual Distributions
Authors	Hao Wang, Berk Ustun, Flavio P. Calmon
Abstract	When the performance of a machine learning model varies over groups defined by sensitive attributes (e.g., gender or ethnicity), the performance disparity can be expressed in terms of the probability distributions of the input and output variables over each group. In this paper, we exploit this fact to reduce the disparate impact of a fixed classification model over a population of interest. Given a black-box classifier, we aim to eliminate the performance gap by perturbing the distribution of input variables for the disadvantaged group. We refer to the perturbed distribution as a counterfactual distribution, and characterize its properties for common fairness criteria. We introduce a descent algorithm to learn a counterfactual distribution from data. We then discuss how the estimated distribution can be used to build a data preprocessor that can reduce disparate impact without training a new model. We validate our approach through experiments on real-world datasets, showing that it can repair different forms of disparity without a significant drop in accuracy.
Tasks
Published	2019-01-29
URL	https://arxiv.org/abs/1901.10501v2
PDF	https://arxiv.org/pdf/1901.10501v2.pdf
PWC	https://paperswithcode.com/paper/repairing-without-retraining-avoiding
Repo	https://github.com/ustunb/ctfdist
Framework	none

An Introduction to Probabilistic Spiking Neural Networks: Probabilistic Models, Learning Rules, and Applications


Title	An Introduction to Probabilistic Spiking Neural Networks: Probabilistic Models, Learning Rules, and Applications
Authors	Hyeryung Jang, Osvaldo Simeone, Brian Gardner, André Grüning
Abstract	Spiking neural networks (SNNs) are distributed trainable systems whose computing elements, or neurons, are characterized by internal analog dynamics and by digital and sparse synaptic communications. The sparsity of the synaptic spiking inputs and the corresponding event-driven nature of neural processing can be leveraged by energy-efficient hardware implementations, which can offer significant energy reductions as compared to conventional artificial neural networks (ANNs). The design of training algorithms lags behind the hardware implementations. Most existing training algorithms for SNNs have been designed either for biological plausibility or through conversion from pretrained ANNs via rate encoding. This article provides an introduction to SNNs by focusing on a probabilistic signal processing methodology that enables the direct derivation of learning rules by leveraging the unique time-encoding capabilities of SNNs. We adopt discrete-time probabilistic models for networked spiking neurons and derive supervised and unsupervised learning rules from first principles via variational inference. Examples and open research problems are also provided.
Tasks
Published	2019-10-02
URL	https://arxiv.org/abs/1910.01059v2
PDF	https://arxiv.org/pdf/1910.01059v2.pdf
PWC	https://paperswithcode.com/paper/an-introduction-to-probabilistic-spiking
Repo	https://github.com/ajovanov95/probabilistic-spiking-neural-networks
Framework	none

Fair k-Center Clustering for Data Summarization


Title	Fair k-Center Clustering for Data Summarization
Authors	Matthäus Kleindessner, Pranjal Awasthi, Jamie Morgenstern
Abstract	In data summarization we want to choose $k$ prototypes in order to summarize a data set. We study a setting where the data set comprises several demographic groups and we are restricted to choose $k_i$ prototypes belonging to group $i$. A common approach to the problem without the fairness constraint is to optimize a centroid-based clustering objective such as $k$-center. A natural extension then is to incorporate the fairness constraint into the clustering problem. Existing algorithms for doing so run in time super-quadratic in the size of the data set, which is in contrast to the standard $k$-center problem being approximable in linear time. In this paper, we resolve this gap by providing a simple approximation algorithm for the $k$-center problem under the fairness constraint with running time linear in the size of the data set and $k$. If the number of demographic groups is small, the approximation guarantee of our algorithm only incurs a constant-factor overhead.
Tasks	Data Summarization
Published	2019-01-24
URL	https://arxiv.org/abs/1901.08628v2
PDF	https://arxiv.org/pdf/1901.08628v2.pdf
PWC	https://paperswithcode.com/paper/fair-k-center-clustering-for-data
Repo	https://github.com/matthklein/fair_k_center_clustering
Framework	none

A General Framework for Structured Learning of Mechanical Systems


Title	A General Framework for Structured Learning of Mechanical Systems
Authors	Jayesh K. Gupta, Kunal Menda, Zachary Manchester, Mykel J. Kochenderfer
Abstract	Learning accurate dynamics models is necessary for optimal, compliant control of robotic systems. Current approaches to white-box modeling using analytic parameterizations, or black-box modeling using neural networks, can suffer from high bias or high variance. We address the need for a flexible, gray-box model of mechanical systems that can seamlessly incorporate prior knowledge where it is available, and train expressive function approximators where it is not. We propose to parameterize a mechanical system using neural networks to model its Lagrangian and the generalized forces that act on it. We test our method on a simulated, actuated double pendulum. We show that our method outperforms a naive, black-box model in terms of data-efficiency, as well as performance in model-based reinforcement learning. We also conduct a systematic study of our method’s ability to incorporate available prior knowledge about the system to improve data efficiency.
Tasks
Published	2019-02-22
URL	http://arxiv.org/abs/1902.08705v2
PDF	http://arxiv.org/pdf/1902.08705v2.pdf
PWC	https://paperswithcode.com/paper/a-general-framework-for-structured-learning
Repo	https://github.com/sisl/mechamodlearn
Framework	pytorch

TileGAN: Synthesis of Large-Scale Non-Homogeneous Textures


Title	TileGAN: Synthesis of Large-Scale Non-Homogeneous Textures
Authors	Anna Frühstück, Ibraheem Alhashim, Peter Wonka
Abstract	We tackle the problem of texture synthesis in the setting where many input images are given and a large-scale output is required. We build on recent generative adversarial networks and propose two extensions in this paper. First, we propose an algorithm to combine outputs of GANs trained on a smaller resolution to produce a large-scale plausible texture map with virtually no boundary artifacts. Second, we propose a user interface to enable artistic control. Our quantitative and qualitative results showcase the generation of synthesized high-resolution maps consisting of up to hundreds of megapixels as a case in point.
Tasks	Image Generation, Image Stylization, Texture Synthesis
Published	2019-04-29
URL	http://arxiv.org/abs/1904.12795v1
PDF	http://arxiv.org/pdf/1904.12795v1.pdf
PWC	https://paperswithcode.com/paper/tilegan-synthesis-of-large-scale-non
Repo	https://github.com/afruehstueck/tileGAN
Framework	tf

A 1d convolutional network for leaf and time series classification


Title	A 1d convolutional network for leaf and time series classification
Authors	Dongyang Kuang
Abstract	In this paper, a 1d convolutional neural network is designed for classification tasks of leaves with centroid contour distance curve (CCDC) as the single feature. With this classifier, simple feature as CCDC shows more discriminating power than people thought previously. The same architecture can also be applied for classifying 1 dimensional time series with little changes. Experiments on some benchmark datasets shows this architecture can provide classification accuracies that are higher than some existing methods. Code for the paper is available at https://github.com/dykuang/Leaf Project.
Tasks	Time Series, Time Series Classification
Published	2019-06-28
URL	https://arxiv.org/abs/1907.00069v1
PDF	https://arxiv.org/pdf/1907.00069v1.pdf
PWC	https://paperswithcode.com/paper/a-1d-convolutional-network-for-leaf-and-time
Repo	https://github.com/dykuang/Leaf_Project
Framework	tf

OpenMPR: Recognize Places Using Multimodal Data for People with Visual Impairments


Title	OpenMPR: Recognize Places Using Multimodal Data for People with Visual Impairments
Authors	Ruiqi Cheng, Kaiwei Wang, Jian Bai, Zhijie Xu
Abstract	Place recognition plays a crucial role in navigational assistance, and is also a challenging issue of assistive technology. The place recognition is prone to erroneous localization owing to various changes between database and query images. Aiming at the wearable assistive device for visually impaired people, we propose an open-sourced place recognition algorithm OpenMPR, which utilizes the multimodal data to address the challenging issues of place recognition. Compared with conventional place recognition, the proposed OpenMPR not only leverages multiple effective descriptors, but also assigns different weights to those descriptors in image matching. Incorporating GNSS data into the algorithm, the cone-based sequence searching is used for robust place recognition. The experiments illustrate that the proposed algorithm manages to solve the place recognition issue in the real-world scenarios and surpass the state-of-the-art algorithms in terms of assistive navigation performance. On the real-world testing dataset, the online OpenMPR achieves 88.7% precision at 100% recall without illumination changes, and achieves 57.8% precision at 99.3% recall with illumination changes. The OpenMPR is available at https://github.com/chengricky/OpenMultiPR.
Tasks
Published	2019-09-15
URL	https://arxiv.org/abs/1909.06795v1
PDF	https://arxiv.org/pdf/1909.06795v1.pdf
PWC	https://paperswithcode.com/paper/openmpr-recognize-places-using-multimodal
Repo	https://github.com/chengricky/OpenMultiPR
Framework	none

TASED-Net: Temporally-Aggregating Spatial Encoder-Decoder Network for Video Saliency Detection


Title	TASED-Net: Temporally-Aggregating Spatial Encoder-Decoder Network for Video Saliency Detection
Authors	Kyle Min, Jason J. Corso
Abstract	TASED-Net is a 3D fully-convolutional network architecture for video saliency detection. It consists of two building blocks: first, the encoder network extracts low-resolution spatiotemporal features from an input clip of several consecutive frames, and then the following prediction network decodes the encoded features spatially while aggregating all the temporal information. As a result, a single prediction map is produced from an input clip of multiple frames. Frame-wise saliency maps can be predicted by applying TASED-Net in a sliding-window fashion to a video. The proposed approach assumes that the saliency map of any frame can be predicted by considering a limited number of past frames. The results of our extensive experiments on video saliency detection validate this assumption and demonstrate that our fully-convolutional model with temporal aggregation method is effective. TASED-Net significantly outperforms previous state-of-the-art approaches on all three major large-scale datasets of video saliency detection: DHF1K, Hollywood2, and UCFSports. After analyzing the results qualitatively, we observe that our model is especially better at attending to salient moving objects.
Tasks	Saliency Detection, Video Saliency Detection
Published	2019-08-15
URL	https://arxiv.org/abs/1908.05786v1
PDF	https://arxiv.org/pdf/1908.05786v1.pdf
PWC	https://paperswithcode.com/paper/tased-net-temporally-aggregating-spatial
Repo	https://github.com/kylemin/TASED-Net
Framework	pytorch

Learning Hierarchical Interactions at Scale: A Convex Optimization Approach


Title	Learning Hierarchical Interactions at Scale: A Convex Optimization Approach
Authors	Hussein Hazimeh, Rahul Mazumder
Abstract	In many learning settings, it is beneficial to augment the main features with pairwise interactions. Such interaction models can be often enhanced by performing variable selection under the so-called strong hierarchy constraint: an interaction is non-zero only if its associated main features are non-zero. Existing convex optimization based algorithms face difficulties in handling problems where the number of main features $p \sim 10^3$ (with total number of features $\sim p^2$). In this paper, we study a convex relaxation which enforces strong hierarchy and develop a highly scalable algorithm based on proximal gradient descent. We introduce novel screening rules that allow for solving the complicated proximal problem in parallel. In addition, we introduce a specialized active-set strategy with gradient screening for avoiding costly gradient computations. The framework can handle problems having dense design matrices, with $p = 50,000$ ($\sim 10^9$ interactions)—instances that are much larger than current state of the art. Experiments on real and synthetic data suggest that our toolkit hierScale outperforms the state of the art in terms of prediction and variable selection and can achieve over a 4900x speed-up.
Tasks	Feature Selection, Structured Prediction
Published	2019-02-05
URL	https://arxiv.org/abs/1902.01542v3
PDF	https://arxiv.org/pdf/1902.01542v3.pdf
PWC	https://paperswithcode.com/paper/learning-hierarchical-interactions-at-scale-a
Repo	https://github.com/hazimehh/hierScale
Framework	none

Shared Visual Abstractions


Title	Shared Visual Abstractions
Authors	Tom White
Abstract	This paper presents abstract art created by neural networks and broadly recognizable across various computer vision systems. The existence of abstract forms that trigger specific labels independent of neural architecture or training set suggests convolutional neural networks build shared visual representations for the categories they understand. Computer vision classifiers encountering these drawings often respond with strong responses for specific labels - in extreme cases stronger than all examples from the validation set. By surveying human subjects we confirm that these abstract artworks are also broadly recognizable by people, suggesting visual representations triggered by these drawings are shared across human and computer vision systems.
Tasks
Published	2019-11-19
URL	https://arxiv.org/abs/1912.04217v1
PDF	https://arxiv.org/pdf/1912.04217v1.pdf
PWC	https://paperswithcode.com/paper/shared-visual-abstractions
Repo	https://github.com/dribnet/perceptionengines
Framework	none

Variational Shape Completion for Virtual Planning of Jaw Reconstructive Surgery


Title	Variational Shape Completion for Virtual Planning of Jaw Reconstructive Surgery
Authors	Amir H. Abdi, Mehran Pesteie, Eitan Prisman, Purang Abolmaesumi, Sidney Fels
Abstract	The premorbid geometry of the mandible is of significant relevance in jaw reconstructive surgeries and occasionally unknown to the surgical team. In this paper, an optimization framework is introduced to train deep models for completion (reconstruction) of the missing segments of the bone based on the remaining healthy structure. To leverage the contextual information of the surroundings of the dissected region, the voxel-weighted Dice loss is introduced. To address the non-deterministic nature of the shape completion problem, we leverage a weighted multi-target probabilistic solution which is an extension to the conditional variational autoencoder (CVAE). This approach considers multiple targets as acceptable reconstructions, each weighted according to their conformity with the original shape. We quantify the performance gain of the proposed method against similar algorithms, including CVAE, where we report statistically significant improvements in both deterministic and probabilistic paradigms. The probabilistic model is also evaluated on its ability to generate anatomically relevant variations for the missing bone. As a unique aspect of this work, the model is tested on real surgical cases where the clinical relevancy of its reconstructions and their compliance with surgeon’s virtual plan are demonstrated as necessary steps towards clinical adoption.
Tasks
Published	2019-06-27
URL	https://arxiv.org/abs/1906.11957v3
PDF	https://arxiv.org/pdf/1906.11957v3.pdf
PWC	https://paperswithcode.com/paper/variational-mandible-shape-completion-for
Repo	https://github.com/amir-abdi/prob-shape-completion
Framework	pytorch