April 2, 2020

3199 words 16 mins read

Paper Group ANR 208

Localising Faster: Efficient and precise lidar-based robot localisation in large-scale environments. Permutohedral-GCN: Graph Convolutional Networks with Global Attention. Self-Enhanced GNN: Improving Graph Neural Networks Using Model Outputs. Explainable Deep Classification Models for Domain Generalization. Error Estimation for Sketched SVD via th …

Localising Faster: Efficient and precise lidar-based robot localisation in large-scale environments


Title	Localising Faster: Efficient and precise lidar-based robot localisation in large-scale environments
Authors	Li Sun, Daniel Adolfsson, Martin Magnusson, Henrik Andreasson, Ingmar Posner, Tom Duckett
Abstract	This paper proposes a novel approach for global localisation of mobile robots in large-scale environments. Our method leverages learning-based localisation and filtering-based localisation, to localise the robot efficiently and precisely through seeding Monte Carlo Localisation (MCL) with a deep-learned distribution. In particular, a fast localisation system rapidly estimates the 6-DOF pose through a deep-probabilistic model (Gaussian Process Regression with a deep kernel), then a precise recursive estimator refines the estimated robot pose according to the geometric alignment. More importantly, the Gaussian method (i.e. deep probabilistic localisation) and non-Gaussian method (i.e. MCL) can be integrated naturally via importance sampling. Consequently, the two systems can be integrated seamlessly and mutually benefit from each other. To verify the proposed framework, we provide a case study in large-scale localisation with a 3D lidar sensor. Our experiments on the Michigan NCLT long-term dataset show that the proposed method is able to localise the robot in 1.94 s on average (median of 0.8 s) with precision 0.75~m in a large-scale environment of approximately 0.5 km2.
Tasks
Published	2020-03-04
URL	https://arxiv.org/abs/2003.01875v1
PDF	https://arxiv.org/pdf/2003.01875v1.pdf
PWC	https://paperswithcode.com/paper/localising-faster-efficient-and-precise-lidar
Repo
Framework

Permutohedral-GCN: Graph Convolutional Networks with Global Attention


Title	Permutohedral-GCN: Graph Convolutional Networks with Global Attention
Authors	Hesham Mostafa, Marcel Nassar
Abstract	Graph convolutional networks (GCNs) update a node’s feature vector by aggregating features from its neighbors in the graph. This ignores potentially useful contributions from distant nodes. Identifying such useful distant contributions is challenging due to scalability issues (too many nodes can potentially contribute) and oversmoothing (aggregating features from too many nodes risks swamping out relevant information and may result in nodes having different labels but indistinguishable features). We introduce a global attention mechanism where a node can selectively attend to, and aggregate features from, any other node in the graph. The attention coefficients depend on the Euclidean distance between learnable node embeddings, and we show that the resulting attention-based global aggregation scheme is analogous to high-dimensional Gaussian filtering. This makes it possible to use efficient approximate Gaussian filtering techniques to implement our attention-based global aggregation scheme. By employing an approximate filtering method based on the permutohedral lattice, the time complexity of our proposed global aggregation scheme only grows linearly with the number of nodes. The resulting GCNs, which we term permutohedral-GCNs, are differentiable and trained end-to-end, and they achieve state of the art performance on several node classification benchmarks.
Tasks	Node Classification
Published	2020-03-02
URL	https://arxiv.org/abs/2003.00635v1
PDF	https://arxiv.org/pdf/2003.00635v1.pdf
PWC	https://paperswithcode.com/paper/permutohedral-gcn-graph-convolutional
Repo
Framework

Self-Enhanced GNN: Improving Graph Neural Networks Using Model Outputs


Title	Self-Enhanced GNN: Improving Graph Neural Networks Using Model Outputs
Authors	Han Yang, Xiao Yan, Xinyan Dai, James Cheng
Abstract	Graph neural networks (GNNs) have received much attention recently because of their excellent performance on graph-based tasks. However, existing research on GNNs focuses on designing more effective models without considering much the quality of the input data itself. In this paper, we propose self-enhanced GNN, which improves the quality of the input data using the outputs of existing GNN models for better performance on semi-supervised node classification. As graph data consist of both topology and node labels, we improve input data quality from both perspectives. For topology, we observe that higher classification accuracy can be achieved when the ratio of inter-class edges (connecting nodes from different classes) is low and propose topology update to remove inter-class edges and add intra-class edges. For node labels, we propose training node augmentation, which enlarges the training set using the labels predicted by existing GNN models. As self-enhanced GNN improves the quality of the input graph data, it is general and can be easily combined with existing GNN models. Experimental results on three well-known GNN models and seven popular datasets show that self-enhanced GNN consistently improves the performance of the three models. The reduction in classification error is 16.2% on average and can be as high as 35.1%.
Tasks	Node Classification
Published	2020-02-18
URL	https://arxiv.org/abs/2002.07518v2
PDF	https://arxiv.org/pdf/2002.07518v2.pdf
PWC	https://paperswithcode.com/paper/self-enhanced-gnn-improving-graph-neural
Repo
Framework

Explainable Deep Classification Models for Domain Generalization


Title	Explainable Deep Classification Models for Domain Generalization
Authors	Andrea Zunino, Sarah Adel Bargal, Riccardo Volpi, Mehrnoosh Sameki, Jianming Zhang, Stan Sclaroff, Vittorio Murino, Kate Saenko
Abstract	Conventionally, AI models are thought to trade off explainability for lower accuracy. We develop a training strategy that not only leads to a more explainable AI system for object classification, but as a consequence, suffers no perceptible accuracy degradation. Explanations are defined as regions of visual evidence upon which a deep classification network makes a decision. This is represented in the form of a saliency map conveying how much each pixel contributed to the network’s decision. Our training strategy enforces a periodic saliency-based feedback to encourage the model to focus on the image regions that directly correspond to the ground-truth object. We quantify explainability using an automated metric, and using human judgement. We propose explainability as a means for bridging the visual-semantic gap between different domains where model explanations are used as a means of disentagling domain specific information from otherwise relevant features. We demonstrate that this leads to improved generalization to new domains without hindering performance on the original domain.
Tasks	Domain Generalization, Object Classification
Published	2020-03-13
URL	https://arxiv.org/abs/2003.06498v1
PDF	https://arxiv.org/pdf/2003.06498v1.pdf
PWC	https://paperswithcode.com/paper/explainable-deep-classification-models-for
Repo
Framework

Error Estimation for Sketched SVD via the Bootstrap


Title	Error Estimation for Sketched SVD via the Bootstrap
Authors	Miles E. Lopes, N. Benjamin Erichson, Michael W. Mahoney
Abstract	In order to compute fast approximations to the singular value decompositions (SVD) of very large matrices, randomized sketching algorithms have become a leading approach. However, a key practical difficulty of sketching an SVD is that the user does not know how far the sketched singular vectors/values are from the exact ones. Indeed, the user may be forced to rely on analytical worst-case error bounds, which do not account for the unique structure of a given problem. As a result, the lack of tools for error estimation often leads to much more computation than is really necessary. To overcome these challenges, this paper develops a fully data-driven bootstrap method that numerically estimates the actual error of sketched singular vectors/values. In particular, this allows the user to inspect the quality of a rough initial sketched SVD, and then adaptively predict how much extra work is needed to reach a given error tolerance. Furthermore, the method is computationally inexpensive, because it operates only on sketched objects, and it requires no passes over the full matrix being factored. Lastly, the method is supported by theoretical guarantees and a very encouraging set of experimental results.
Tasks
Published	2020-03-10
URL	https://arxiv.org/abs/2003.04937v1
PDF	https://arxiv.org/pdf/2003.04937v1.pdf
PWC	https://paperswithcode.com/paper/error-estimation-for-sketched-svd-via-the
Repo
Framework

Weakly Supervised Attention Pyramid Convolutional Neural Network for Fine-Grained Visual Classification


Title	Weakly Supervised Attention Pyramid Convolutional Neural Network for Fine-Grained Visual Classification
Authors	Yifeng Ding, Shaoguo Wen, Jiyang Xie, Dongliang Chang, Zhanyu Ma, Zhongwei Si, Haibin Ling
Abstract	Classifying the sub-categories of an object from the same super-category (e.g. bird species, car and aircraft models) in fine-grained visual classification (FGVC) highly relies on discriminative feature representation and accurate region localization. Existing approaches mainly focus on distilling information from high-level features. In this paper, however, we show that by integrating low-level information (e.g. color, edge junctions, texture patterns), performance can be improved with enhanced feature representation and accurately located discriminative regions. Our solution, named Attention Pyramid Convolutional Neural Network (AP-CNN), consists of a) a pyramidal hierarchy structure with a top-down feature pathway and a bottom-up attention pathway, and hence learns both high-level semantic and low-level detailed feature representation, and b) an ROI guided refinement strategy with ROI guided dropblock and ROI guided zoom-in, which refines features with discriminative local regions enhanced and background noises eliminated. The proposed AP-CNN can be trained end-to-end, without the need of additional bounding box/part annotations. Extensive experiments on three commonly used FGVC datasets (CUB-200-2011, Stanford Cars, and FGVC-Aircraft) demonstrate that our approach can achieve state-of-the-art performance. Code available at \url{http://dwz1.cc/ci8so8a}
Tasks	Fine-Grained Image Classification
Published	2020-02-09
URL	https://arxiv.org/abs/2002.03353v1
PDF	https://arxiv.org/pdf/2002.03353v1.pdf
PWC	https://paperswithcode.com/paper/weakly-supervised-attention-pyramid
Repo
Framework


Title	A CNN-Based Blind Denoising Method for Endoscopic Images
Authors	Shaofeng Zou, Mingzhu Long, Xuyang Wang, Xiang Xie, Guolin Li, Zhihua Wang
Abstract	The quality of images captured by wireless capsule endoscopy (WCE) is key for doctors to diagnose diseases of gastrointestinal (GI) tract. However, there exist many low-quality endoscopic images due to the limited illumination and complex environment in GI tract. After an enhancement process, the severe noise become an unacceptable problem. The noise varies with different cameras, GI tract environments and image enhancement. And the noise model is hard to be obtained. This paper proposes a convolutional blind denoising network for endoscopic images. We apply Deep Image Prior (DIP) method to reconstruct a clean image iteratively using a noisy image without a specific noise model and ground truth. Then we design a blind image quality assessment network based on MobileNet to estimate the quality of the reconstructed images. The estimated quality is used to stop the iterative operation in DIP method. The number of iterations is reduced about 36% by using transfer learning in our DIP process. Experimental results on endoscopic images and real-world noisy images demonstrate the superiority of our proposed method over the state-of-the-art methods in terms of visual quality and quantitative metrics.
Tasks	Blind Image Quality Assessment, Denoising, Image Enhancement, Image Quality Assessment, Transfer Learning
Published	2020-03-16
URL	https://arxiv.org/abs/2003.06986v1
PDF	https://arxiv.org/pdf/2003.06986v1.pdf
PWC	https://paperswithcode.com/paper/a-cnn-based-blind-denoising-method-for-1
Repo
Framework


Title	Active Fine-Tuning from gMAD Examples Improves Blind Image Quality Assessment
Authors	Zhihua Wang, Kede Ma
Abstract	The research in image quality assessment (IQA) has a long history, and significant progress has been made by leveraging recent advances in deep neural networks (DNNs). Despite high correlation numbers on existing IQA datasets, DNN-based models may be easily falsified in the group maximum differentiation (gMAD) competition with strong counterexamples being identified. Here we show that gMAD examples can be used to improve blind IQA (BIQA) methods. Specifically, we first pre-train a DNN-based BIQA model using multiple noisy annotators, and fine-tune it on multiple subject-rated databases of synthetically distorted images, resulting in a top-performing baseline model. We then seek pairs of images by comparing the baseline model with a set of full-reference IQA methods in gMAD. The resulting gMAD examples are most likely to reveal the relative weaknesses of the baseline, and suggest potential ways for refinement. We query ground truth quality annotations for the selected images in a well controlled laboratory environment, and further fine-tune the baseline on the combination of human-rated images from gMAD and existing databases. This process may be iterated, enabling active and progressive fine-tuning from gMAD examples for BIQA. We demonstrate the feasibility of our active learning scheme on a large-scale unlabeled image set, and show that the fine-tuned method achieves improved generalizability in gMAD, without destroying performance on previously trained databases.
Tasks	Active Learning, Blind Image Quality Assessment, Image Quality Assessment
Published	2020-03-08
URL	https://arxiv.org/abs/2003.03849v1
PDF	https://arxiv.org/pdf/2003.03849v1.pdf
PWC	https://paperswithcode.com/paper/active-fine-tuning-from-gmad-examples
Repo
Framework

If I Hear You Correctly: Building and Evaluating Interview Chatbots with Active Listening Skills


Title	If I Hear You Correctly: Building and Evaluating Interview Chatbots with Active Listening Skills
Authors	Ziang Xiao, Michelle X. Zhou, Wenxi Chen, Huahai Yang, Changyan Chi
Abstract	Interview chatbots engage users in a text-based conversation to draw out their views and opinions. It is, however, challenging to build effective interview chatbots that can handle user free-text responses to open-ended questions and deliver engaging user experience. As the first step, we are investigating the feasibility and effectiveness of using publicly available, practical AI technologies to build effective interview chatbots. To demonstrate feasibility, we built a prototype scoped to enable interview chatbots with a subset of active listening skills - the abilities to comprehend a user’s input and respond properly. To evaluate the effectiveness of our prototype, we compared the performance of interview chatbots with or without active listening skills on four common interview topics in a live evaluation with 206 users. Our work presents practical design implications for building effective interview chatbots, hybrid chatbot platforms, and empathetic chatbots beyond interview tasks.
Tasks	Chatbot
Published	2020-02-05
URL	https://arxiv.org/abs/2002.01862v1
PDF	https://arxiv.org/pdf/2002.01862v1.pdf
PWC	https://paperswithcode.com/paper/if-i-hear-you-correctly-building-and
Repo
Framework

Reinforcement Learning of Control Policy for Linear Temporal Logic Specifications Using Limit-Deterministic Generalized Büchi Automata


Title	Reinforcement Learning of Control Policy for Linear Temporal Logic Specifications Using Limit-Deterministic Generalized Büchi Automata
Authors	Ryohei Oura, Ami Sakakibara, Toshimitsu Ushio
Abstract	This letter proposes a novel reinforcement learning method for the synthesis of a control policy satisfying a control specification described by a linear temporal logic formula. We assume that the controlled system is modeled by a Markov decision process (MDP). We convert the specification to a limit-deterministic generalized B"uchi automaton (LDGBA) with several accepting sets that accepts all infinite sequences satisfying the formula. The LDGBA is augmented so that it explicitly records the previous visits to accepting sets. We take a product of the augmented LDGBA and the MDP, based on which we define a reward function. The agent gets rewards whenever state transitions are in an accepting set that has not been visited for a certain number of steps. Consequently, sparsity of rewards is relaxed and optimal circulations among the accepting sets are learned. We show that the proposed method can learn an optimal policy when the discount factor is sufficiently close to one.
Tasks
Published	2020-01-14
URL	https://arxiv.org/abs/2001.04669v3
PDF	https://arxiv.org/pdf/2001.04669v3.pdf
PWC	https://paperswithcode.com/paper/reinforcement-learning-of-control-policy-for
Repo
Framework

Moment-Matching Conditions for Exponential Families with Conditioning or Hidden Data


Title	Moment-Matching Conditions for Exponential Families with Conditioning or Hidden Data
Authors	Justin Domke
Abstract	Maximum likelihood learning with exponential families leads to moment-matching of the sufficient statistics, a classic result. This can be generalized to conditional exponential families and/or when there are hidden data. This document gives a first-principles explanation of these generalized moment-matching conditions, along with a self-contained derivation.
Tasks
Published	2020-01-07
URL	https://arxiv.org/abs/2001.09771v1
PDF	https://arxiv.org/pdf/2001.09771v1.pdf
PWC	https://paperswithcode.com/paper/moment-matching-conditions-for-exponential
Repo
Framework

Better Compression with Deep Pre-Editing


Title	Better Compression with Deep Pre-Editing
Authors	Hossein Talebi, Damien Kelly, Xiyang Luo, Ignacio Garcia Dorado, Feng Yang, Peyman Milanfar, Michael Elad
Abstract	Could we compress images via standard codecs while avoiding artifacts? The answer is obvious – this is doable as long as the bit budget is generous enough. What if the allocated bit-rate for compression is insufficient? Then unfortunately, artifacts are a fact of life. Many attempts were made over the years to fight this phenomenon, with various degrees of success. In this work we aim to break the unholy connection between bit-rate and image quality, and propose a way to circumvent compression artifacts by pre-editing the incoming image and modifying its content to fit the given bits. We design this editing operation as a learned convolutional neural network, and formulate an optimization problem for its training. Our loss takes into account a proximity between the original image and the edited one, a bit-budget penalty over the proposed image, and a no-reference image quality measure for forcing the outcome to be visually pleasing. The proposed approach is demonstrated on the popular JPEG compression, showing savings in bits and/or improvements in visual quality, obtained with intricate editing effects.
Tasks
Published	2020-02-01
URL	https://arxiv.org/abs/2002.00113v1
PDF	https://arxiv.org/pdf/2002.00113v1.pdf
PWC	https://paperswithcode.com/paper/better-compression-with-deep-pre-editing
Repo
Framework

The Real-World-Weight Cross-Entropy Loss Function: Modeling the Costs of Mislabeling


Title	The Real-World-Weight Cross-Entropy Loss Function: Modeling the Costs of Mislabeling
Authors	Yaoshiang Ho, Samuel Wookey
Abstract	In this paper, we propose a new metric to measure goodness-of-fit for classifiers, the Real World Cost function. This metric factors in information about a real world problem, such as financial impact, that other measures like accuracy or F1 do not. This metric is also more directly interpretable for users. To optimize for this metric, we introduce the Real-World- Weight Crossentropy loss function, in both binary and single-label classification variants. Both variants allow direct input of real world costs as weights. For single-label, multicategory classification, our loss function also allows direct penalization of probabilistic false positives, weighted by label, during the training of a machine learning model. We compare the design of our loss function to the binary crossentropy and categorical crossentropy functions, as well as their weighted variants, to discuss the potential for improvement in handling a variety of known shortcomings of machine learning, ranging from imbalanced classes to medical diagnostic error to reinforcement of social bias. We create scenarios that emulate those issues using the MNIST data set and demonstrate empirical results of our new loss function. Finally, we sketch a proof of this function based on Maximum Likelihood Estimation and discuss future directions.
Tasks
Published	2020-01-03
URL	https://arxiv.org/abs/2001.00570v1
PDF	https://arxiv.org/pdf/2001.00570v1.pdf
PWC	https://paperswithcode.com/paper/the-real-world-weight-cross-entropy-loss
Repo
Framework

KEML: A Knowledge-Enriched Meta-Learning Framework for Lexical Relation Classification


Title	KEML: A Knowledge-Enriched Meta-Learning Framework for Lexical Relation Classification
Authors	Chengyu Wang, Minghui Qiu, Jun Huang, Xiaofeng He
Abstract	Lexical relations describe how concepts are semantically related, in the form of relation triples. The accurate prediction of lexical relations between concepts is challenging, due to the sparsity of patterns indicating the existence of such relations. We propose the Knowledge-Enriched Meta-Learning (KEML) framework to address the task of lexical relation classification. In KEML, the LKB-BERT (Lexical Knowledge Base-BERT) model is presented to learn concept representations from massive text corpora, with rich lexical knowledge injected by distant supervision. A probabilistic distribution of auxiliary tasks is defined to increase the model’s ability to recognize different types of lexical relations. We further combine a meta-learning process over the auxiliary task distribution and supervised learning to train the neural lexical relation classifier. Experiments over multiple datasets show that KEML outperforms state-of-the-art methods.
Tasks	Meta-Learning, Relation Classification
Published	2020-02-25
URL	https://arxiv.org/abs/2002.10903v1
PDF	https://arxiv.org/pdf/2002.10903v1.pdf
PWC	https://paperswithcode.com/paper/keml-a-knowledge-enriched-meta-learning
Repo
Framework

Supervised Quantile Normalization for Low-rank Matrix Approximation


Title	Supervised Quantile Normalization for Low-rank Matrix Approximation
Authors	Marco Cuturi, Olivier Teboul, Jonathan Niles-Weed, Jean-Philippe Vert
Abstract	Low rank matrix factorization is a fundamental building block in machine learning, used for instance to summarize gene expression profile data or word-document counts. To be robust to outliers and differences in scale across features, a matrix factorization step is usually preceded by ad-hoc feature normalization steps, such as \texttt{tf-idf} scaling or data whitening. We propose in this work to learn these normalization operators jointly with the factorization itself. More precisely, given a $d\times n$ matrix $X$ of $d$ features measured on $n$ individuals, we propose to learn the parameters of quantile normalization operators that can operate row-wise on the values of $X$ and/or of its factorization $UV$ to improve the quality of the low-rank representation of $X$ itself. This optimization is facilitated by the introduction of a differentiable quantile normalization operator built using optimal transport, providing new results on top of existing work by Cuturi et al. (2019). We demonstrate the applicability of these techniques on synthetic and genomics datasets.
Tasks
Published	2020-02-08
URL	https://arxiv.org/abs/2002.03229v1
PDF	https://arxiv.org/pdf/2002.03229v1.pdf
PWC	https://paperswithcode.com/paper/supervised-quantile-normalization-for-low
Repo
Framework