July 29, 2019

2988 words 15 mins read

Paper Group AWR 139

FSSD: Feature Fusion Single Shot Multibox Detector. Enhancement of SSD by concatenating feature maps for object detection. SRN: Side-output Residual Network for Object Symmetry Detection in the Wild. Learning a Rotation Invariant Detector with Rotatable Bounding Box. An adaptive prefix-assignment technique for symmetry reduction. CayleyNets: Graph …

FSSD: Feature Fusion Single Shot Multibox Detector


Title	FSSD: Feature Fusion Single Shot Multibox Detector
Authors	Zuoxin Li, Fuqiang Zhou
Abstract	SSD (Single Shot Multibox Detector) is one of the best object detection algorithms with both high accuracy and fast speed. However, SSD’s feature pyramid detection method makes it hard to fuse the features from different scales. In this paper, we proposed FSSD (Feature Fusion Single Shot Multibox Detector), an enhanced SSD with a novel and lightweight feature fusion module which can improve the performance significantly over SSD with just a little speed drop. In the feature fusion module, features from different layers with different scales are concatenated together, followed by some down-sampling blocks to generate new feature pyramid, which will be fed to multibox detectors to predict the final detection results. On the Pascal VOC 2007 test, our network can achieve 82.7 mAP (mean average precision) at the speed of 65.8 FPS (frame per second) with the input size 300$\times$300 using a single Nvidia 1080Ti GPU. In addition, our result on COCO is also better than the conventional SSD with a large margin. Our FSSD outperforms a lot of state-of-the-art object detection algorithms in both aspects of accuracy and speed. Code is available at https://github.com/lzx1413/CAFFE_SSD/tree/fssd.
Tasks	Object Detection
Published	2017-12-04
URL	http://arxiv.org/abs/1712.00960v3
PDF	http://arxiv.org/pdf/1712.00960v3.pdf
PWC	https://paperswithcode.com/paper/fssd-feature-fusion-single-shot-multibox
Repo	https://github.com/lzx1413/PytorchSSD
Framework	pytorch

Enhancement of SSD by concatenating feature maps for object detection


Title	Enhancement of SSD by concatenating feature maps for object detection
Authors	Jisoo Jeong, Hyojin Park, Nojun Kwak
Abstract	We propose an object detection method that improves the accuracy of the conventional SSD (Single Shot Multibox Detector), which is one of the top object detection algorithms in both aspects of accuracy and speed. The performance of a deep network is known to be improved as the number of feature maps increases. However, it is difficult to improve the performance by simply raising the number of feature maps. In this paper, we propose and analyze how to use feature maps effectively to improve the performance of the conventional SSD. The enhanced performance was obtained by changing the structure close to the classifier network, rather than growing layers close to the input data, e.g., by replacing VGGNet with ResNet. The proposed network is suitable for sharing the weights in the classifier networks, by which property, the training can be faster with better generalization power. For the Pascal VOC 2007 test set trained with VOC 2007 and VOC 2012 training sets, the proposed network with the input size of 300 x 300 achieved 78.5% mAP (mean average precision) at the speed of 35.0 FPS (frame per second), while the network with a 512 x 512 sized input achieved 80.8% mAP at 16.6 FPS using Nvidia Titan X GPU. The proposed network shows state-of-the-art mAP, which is better than those of the conventional SSD, YOLO, Faster-RCNN and RFCN. Also, it is faster than Faster-RCNN and RFCN.
Tasks	Object Detection
Published	2017-05-26
URL	http://arxiv.org/abs/1705.09587v1
PDF	http://arxiv.org/pdf/1705.09587v1.pdf
PWC	https://paperswithcode.com/paper/enhancement-of-ssd-by-concatenating-feature
Repo	https://github.com/espectre/Object_Detection
Framework	pytorch

SRN: Side-output Residual Network for Object Symmetry Detection in the Wild


Title	SRN: Side-output Residual Network for Object Symmetry Detection in the Wild
Authors	Wei Ke, Jie Chen, Jianbin Jiao, Guoying Zhao, Qixiang Ye
Abstract	In this paper, we establish a baseline for object symmetry detection in complex backgrounds by presenting a new benchmark and an end-to-end deep learning approach, opening up a promising direction for symmetry detection in the wild. The new benchmark, named Sym-PASCAL, spans challenges including object diversity, multi-objects, part-invisibility, and various complex backgrounds that are far beyond those in existing datasets. The proposed symmetry detection approach, named Side-output Residual Network (SRN), leverages output Residual Units (RUs) to fit the errors between the object symmetry groundtruth and the outputs of RUs. By stacking RUs in a deep-to-shallow manner, SRN exploits the ‘flow’ of errors among multiple scales to ease the problems of fitting complex outputs with limited layers, suppressing the complex backgrounds, and effectively matching object symmetry of different scales. Experimental results validate both the benchmark and its challenging aspects related to realworld images, and the state-of-the-art performance of our symmetry detection approach. The benchmark and the code for SRN are publicly available at https://github.com/KevinKecc/SRN.
Tasks
Published	2017-03-07
URL	http://arxiv.org/abs/1703.02243v2
PDF	http://arxiv.org/pdf/1703.02243v2.pdf
PWC	https://paperswithcode.com/paper/srn-side-output-residual-network-for-object-1
Repo	https://github.com/KevinKecc/SRN
Framework	caffe2

Learning a Rotation Invariant Detector with Rotatable Bounding Box


Title	Learning a Rotation Invariant Detector with Rotatable Bounding Box
Authors	Lei Liu, Zongxu Pan, Bin Lei
Abstract	Detection of arbitrarily rotated objects is a challenging task due to the difficulties of locating the multi-angle objects and separating them effectively from the background. The existing methods are not robust to angle varies of the objects because of the use of traditional bounding box, which is a rotation variant structure for locating rotated objects. In this article, a new detection method is proposed which applies the newly defined rotatable bounding box (RBox). The proposed detector (DRBox) can effectively handle the situation where the orientation angles of the objects are arbitrary. The training of DRBox forces the detection networks to learn the correct orientation angle of the objects, so that the rotation invariant property can be achieved. DRBox is tested to detect vehicles, ships and airplanes on satellite images, compared with Faster R-CNN and SSD, which are chosen as the benchmark of the traditional bounding box based methods. The results shows that DRBox performs much better than traditional bounding box based methods do on the given tasks, and is more robust against rotation of input image and target objects. Besides, results show that DRBox correctly outputs the orientation angles of the objects, which is very useful for locating multi-angle objects efficiently. The code and models are available at https://github.com/liulei01/DRBox.
Tasks
Published	2017-11-26
URL	http://arxiv.org/abs/1711.09405v1
PDF	http://arxiv.org/pdf/1711.09405v1.pdf
PWC	https://paperswithcode.com/paper/learning-a-rotation-invariant-detector-with
Repo	https://github.com/tadasi12/DRBox
Framework	none

An adaptive prefix-assignment technique for symmetry reduction


Title	An adaptive prefix-assignment technique for symmetry reduction
Authors	Tommi Junttila, Matti Karppa, Petteri Kaski, Jukka Kohonen
Abstract	This paper presents a technique for symmetry reduction that adaptively assigns a prefix of variables in a system of constraints so that the generated prefix-assignments are pairwise nonisomorphic under the action of the symmetry group of the system. The technique is based on McKay’s canonical extension framework [J.~Algorithms 26 (1998), no.~2, 306–324]. Among key features of the technique are (i) adaptability—the prefix sequence can be user-prescribed and truncated for compatibility with the group of symmetries; (ii) parallelizability—prefix-assignments can be processed in parallel independently of each other; (iii) versatility—the method is applicable whenever the group of symmetries can be concisely represented as the automorphism group of a vertex-colored graph; and (iv) implementability—the method can be implemented relying on a canonical labeling map for vertex-colored graphs as the only nontrivial subroutine. To demonstrate the practical applicability of our technique, we have prepared an experimental open-source implementation of the technique and carry out a set of experiments that demonstrate ability to reduce symmetry on hard instances. Furthermore, we demonstrate that the implementation effectively parallelizes to compute clusters with multiple nodes via a message-passing interface.
Tasks
Published	2017-06-26
URL	http://arxiv.org/abs/1706.08325v2
PDF	http://arxiv.org/pdf/1706.08325v2.pdf
PWC	https://paperswithcode.com/paper/an-adaptive-prefix-assignment-technique-for
Repo	https://github.com/pkaski/reduce
Framework	none

CayleyNets: Graph Convolutional Neural Networks with Complex Rational Spectral Filters


Title	CayleyNets: Graph Convolutional Neural Networks with Complex Rational Spectral Filters
Authors	Ron Levie, Federico Monti, Xavier Bresson, Michael M. Bronstein
Abstract	The rise of graph-structured data such as social networks, regulatory networks, citation graphs, and functional brain networks, in combination with resounding success of deep learning in various applications, has brought the interest in generalizing deep learning models to non-Euclidean domains. In this paper, we introduce a new spectral domain convolutional architecture for deep learning on graphs. The core ingredient of our model is a new class of parametric rational complex functions (Cayley polynomials) allowing to efficiently compute spectral filters on graphs that specialize on frequency bands of interest. Our model generates rich spectral filters that are localized in space, scales linearly with the size of the input data for sparsely-connected graphs, and can handle different constructions of Laplacian operators. Extensive experimental results show the superior performance of our approach, in comparison to other spectral domain convolutional architectures, on spectral image classification, community detection, vertex classification and matrix completion tasks.
Tasks	Community Detection, Image Classification, Matrix Completion, Node Classification
Published	2017-05-22
URL	http://arxiv.org/abs/1705.07664v2
PDF	http://arxiv.org/pdf/1705.07664v2.pdf
PWC	https://paperswithcode.com/paper/cayleynets-graph-convolutional-neural
Repo	https://github.com/amoliu/CayleyNet
Framework	tf

Automatic Mapping of French Discourse Connectives to PDTB Discourse Relations


Title	Automatic Mapping of French Discourse Connectives to PDTB Discourse Relations
Authors	Majid Laali, Leila Kosseim
Abstract	In this paper, we present an approach to exploit phrase tables generated by statistical machine translation in order to map French discourse connectives to discourse relations. Using this approach, we created ConcoLeDisCo, a lexicon of French discourse connectives and their PDTB relations. When evaluated against LEXCONN, ConcoLeDisCo achieves a recall of 0.81 and an Average Precision of 0.68 for the Concession and Condition relations.
Tasks	Machine Translation
Published	2017-06-29
URL	http://arxiv.org/abs/1706.09856v1
PDF	http://arxiv.org/pdf/1706.09856v1.pdf
PWC	https://paperswithcode.com/paper/automatic-mapping-of-french-discourse
Repo	https://github.com/mjlaali/ConcoLeDisCo
Framework	none

MRA - Proof of Concept of a Multilingual Report Annotator Web Application


Title	MRA - Proof of Concept of a Multilingual Report Annotator Web Application
Authors	Luís Campos, Francisco Couto
Abstract	MRA (Multilingual Report Annotator) is a web application that translates Radiology text and annotates it with RadLex terms. Its goal is to explore the solution of translating non-English Radiology reports as a way to solve the problem of most of the Text Mining tools being developed for English. In this brief paper we explain the language barrier problem and shortly describe the application. MRA can be found at https://github.com/lasigeBioTM/MRA .
Tasks
Published	2017-04-06
URL	http://arxiv.org/abs/1704.01748v3
PDF	http://arxiv.org/pdf/1704.01748v3.pdf
PWC	https://paperswithcode.com/paper/mra-proof-of-concept-of-a-multilingual-report
Repo	https://github.com/lasigeBioTM/MRA
Framework	none

End-to-End Neural Ad-hoc Ranking with Kernel Pooling


Title	End-to-End Neural Ad-hoc Ranking with Kernel Pooling
Authors	Chenyan Xiong, Zhuyun Dai, Jamie Callan, Zhiyuan Liu, Russell Power
Abstract	This paper proposes K-NRM, a kernel based neural model for document ranking. Given a query and a set of documents, K-NRM uses a translation matrix that models word-level similarities via word embeddings, a new kernel-pooling technique that uses kernels to extract multi-level soft match features, and a learning-to-rank layer that combines those features into the final ranking score. The whole model is trained end-to-end. The ranking layer learns desired feature patterns from the pairwise ranking loss. The kernels transfer the feature patterns into soft-match targets at each similarity level and enforce them on the translation matrix. The word embeddings are tuned accordingly so that they can produce the desired soft matches. Experiments on a commercial search engine’s query log demonstrate the improvements of K-NRM over prior feature-based and neural-based states-of-the-art, and explain the source of K-NRM’s advantage: Its kernel-guided embedding encodes a similarity metric tailored for matching query words to document words, and provides effective multi-level soft matches.
Tasks	Ad-Hoc Information Retrieval, Document Ranking, Learning-To-Rank, Word Embeddings
Published	2017-06-20
URL	http://arxiv.org/abs/1706.06613v1
PDF	http://arxiv.org/pdf/1706.06613v1.pdf
PWC	https://paperswithcode.com/paper/end-to-end-neural-ad-hoc-ranking-with-kernel
Repo	https://github.com/thunlp/Kernel-Based-Neural-Ranking-Models
Framework	pytorch

Active Learning for Convolutional Neural Networks: A Core-Set Approach


Title	Active Learning for Convolutional Neural Networks: A Core-Set Approach
Authors	Ozan Sener, Silvio Savarese
Abstract	Convolutional neural networks (CNNs) have been successfully applied to many recognition and learning tasks using a universal recipe; training a deep model on a very large dataset of supervised examples. However, this approach is rather restrictive in practice since collecting a large set of labeled images is very expensive. One way to ease this problem is coming up with smart ways for choosing images to be labelled from a very large collection (ie. active learning). Our empirical study suggests that many of the active learning heuristics in the literature are not effective when applied to CNNs in batch setting. Inspired by these limitations, we define the problem of active learning as core-set selection, ie. choosing set of points such that a model learned over the selected subset is competitive for the remaining data points. We further present a theoretical result characterizing the performance of any selected subset using the geometry of the datapoints. As an active learning algorithm, we choose the subset which is expected to yield best result according to our characterization. Our experiments show that the proposed method significantly outperforms existing approaches in image classification experiments by a large margin.
Tasks	Active Learning, Image Classification
Published	2017-08-01
URL	http://arxiv.org/abs/1708.00489v4
PDF	http://arxiv.org/pdf/1708.00489v4.pdf
PWC	https://paperswithcode.com/paper/active-learning-for-convolutional-neural
Repo	https://github.com/rpinsler/active-bayesian-coresets
Framework	pytorch

Time Series Cluster Kernel for Learning Similarities between Multivariate Time Series with Missing Data


Title	Time Series Cluster Kernel for Learning Similarities between Multivariate Time Series with Missing Data
Authors	Karl Øyvind Mikalsen, Filippo Maria Bianchi, Cristina Soguero-Ruiz, Robert Jenssen
Abstract	Similarity-based approaches represent a promising direction for time series analysis. However, many such methods rely on parameter tuning, and some have shortcomings if the time series are multivariate (MTS), due to dependencies between attributes, or the time series contain missing data. In this paper, we address these challenges within the powerful context of kernel methods by proposing the robust \emph{time series cluster kernel} (TCK). The approach taken leverages the missing data handling properties of Gaussian mixture models (GMM) augmented with informative prior distributions. An ensemble learning approach is exploited to ensure robustness to parameters by combining the clustering results of many GMM to form the final kernel. We evaluate the TCK on synthetic and real data and compare to other state-of-the-art techniques. The experimental results demonstrate that the TCK is robust to parameter choices, provides competitive results for MTS without missing data and outstanding results for missing data.
Tasks	Time Series, Time Series Analysis
Published	2017-04-03
URL	http://arxiv.org/abs/1704.00794v2
PDF	http://arxiv.org/pdf/1704.00794v2.pdf
PWC	https://paperswithcode.com/paper/time-series-cluster-kernel-for-learning
Repo	https://github.com/FilippoMB/TCK_AE
Framework	tf

Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Data


Title	Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Data
Authors	Gintare Karolina Dziugaite, Daniel M. Roy
Abstract	One of the defining properties of deep learning is that models are chosen to have many more parameters than available training data. In light of this capacity for overfitting, it is remarkable that simple algorithms like SGD reliably return solutions with low test error. One roadblock to explaining these phenomena in terms of implicit regularization, structural properties of the solution, and/or easiness of the data is that many learning bounds are quantitatively vacuous when applied to networks learned by SGD in this “deep learning” regime. Logically, in order to explain generalization, we need nonvacuous bounds. We return to an idea by Langford and Caruana (2001), who used PAC-Bayes bounds to compute nonvacuous numerical bounds on generalization error for stochastic two-layer two-hidden-unit neural networks via a sensitivity analysis. By optimizing the PAC-Bayes bound directly, we are able to extend their approach and obtain nonvacuous generalization bounds for deep stochastic neural network classifiers with millions of parameters trained on only tens of thousands of examples. We connect our findings to recent and old work on flat minima and MDL-based explanations of generalization.
Tasks
Published	2017-03-31
URL	http://arxiv.org/abs/1703.11008v2
PDF	http://arxiv.org/pdf/1703.11008v2.pdf
PWC	https://paperswithcode.com/paper/computing-nonvacuous-generalization-bounds
Repo	https://github.com/gkdziugaite/pacbayes-opt
Framework	tf

Is prioritized sweeping the better episodic control?


Title	Is prioritized sweeping the better episodic control?
Authors	Johanni Brea
Abstract	Episodic control has been proposed as a third approach to reinforcement learning, besides model-free and model-based control, by analogy with the three types of human memory. i.e. episodic, procedural and semantic memory. But the theoretical properties of episodic control are not well investigated. Here I show that in deterministic tree Markov decision processes, episodic control is equivalent to a form of prioritized sweeping in terms of sample efficiency as well as memory and computation demands. For general deterministic and stochastic environments, prioritized sweeping performs better even when memory and computation demands are restricted to be equal to those of episodic control. These results suggest generalizations of prioritized sweeping to partially observable environments, its combined use with function approximation and the search for possible implementations of prioritized sweeping in brains.
Tasks
Published	2017-11-20
URL	http://arxiv.org/abs/1711.06677v2
PDF	http://arxiv.org/pdf/1711.06677v2.pdf
PWC	https://paperswithcode.com/paper/is-prioritized-sweeping-the-better-episodic
Repo	https://github.com/jbrea/episodiccontrol
Framework	none

Bayesian Compression for Deep Learning


Title	Bayesian Compression for Deep Learning
Authors	Christos Louizos, Karen Ullrich, Max Welling
Abstract	Compression and computational efficiency in deep learning have become a problem of great significance. In this work, we argue that the most principled and effective way to attack this problem is by adopting a Bayesian point of view, where through sparsity inducing priors we prune large parts of the network. We introduce two novelties in this paper: 1) we use hierarchical priors to prune nodes instead of individual weights, and 2) we use the posterior uncertainties to determine the optimal fixed point precision to encode the weights. Both factors significantly contribute to achieving the state of the art in terms of compression rates, while still staying competitive with methods designed to optimize for speed or energy efficiency.
Tasks
Published	2017-05-24
URL	http://arxiv.org/abs/1705.08665v4
PDF	http://arxiv.org/pdf/1705.08665v4.pdf
PWC	https://paperswithcode.com/paper/bayesian-compression-for-deep-learning
Repo	https://github.com/cambridge-mlg/miracle
Framework	tf

On the Real-time Vehicle Placement Problem


Title	On the Real-time Vehicle Placement Problem
Authors	Abhinav Jauhri, Carlee Joe-Wong, John Paul Shen
Abstract	Motivated by ride-sharing platforms’ efforts to reduce their riders’ wait times for a vehicle, this paper introduces a novel problem of placing vehicles to fulfill real-time pickup requests in a spatially and temporally changing environment. The real-time nature of this problem makes it fundamentally different from other placement and scheduling problems, as it requires not only real-time placement decisions but also handling real-time request dynamics, which are influenced by human mobility patterns. We use a dataset of ten million ride requests from four major U.S. cities to show that the requests exhibit significant self-similarity. We then propose distributed online learning algorithms for the real-time vehicle placement problem and bound their expected performance under this observed self-similarity.
Tasks
Published	2017-12-04
URL	http://arxiv.org/abs/1712.01235v1
PDF	http://arxiv.org/pdf/1712.01235v1.pdf
PWC	https://paperswithcode.com/paper/on-the-real-time-vehicle-placement-problem
Repo	https://github.com/ajauhri/mobility-modeling
Framework	none