May 7, 2019

2499 words 12 mins read

Paper Group AWR 32

Car Type Recognition with Deep Neural Networks. Learning Covariant Feature Detectors. PAMPO: using pattern matching and pos-tagging for effective Named Entities recognition in Portuguese. Beyond Skip Connections: Top-Down Modulation for Object Detection. Mixing Dirichlet Topic Models and Word Embeddings to Make lda2vec. Character-level Convolutiona …

Car Type Recognition with Deep Neural Networks


Title	Car Type Recognition with Deep Neural Networks
Authors	Heikki Huttunen, Fatemeh Shokrollahi Yancheshmeh, Ke Chen
Abstract	In this paper we study automatic recognition of cars of four types: Bus, Truck, Van and Small car. For this problem we consider two data driven frameworks: a deep neural network and a support vector machine using SIFT features. The accuracy of the methods is validated with a database of over 6500 images, and the resulting prediction accuracy is over 97 %. This clearly exceeds the accuracies of earlier studies that use manually engineered feature extraction pipelines.
Tasks
Published	2016-02-23
URL	http://arxiv.org/abs/1602.07125v2
PDF	http://arxiv.org/pdf/1602.07125v2.pdf
PWC	https://paperswithcode.com/paper/car-type-recognition-with-deep-neural
Repo	https://github.com/Valentin4869/BinCNN
Framework	none

Learning Covariant Feature Detectors


Title	Learning Covariant Feature Detectors
Authors	Karel Lenc, Andrea Vedaldi
Abstract	Local covariant feature detection, namely the problem of extracting viewpoint invariant features from images, has so far largely resisted the application of machine learning techniques. In this paper, we propose the first fully general formulation for learning local covariant feature detectors. We propose to cast detection as a regression problem, enabling the use of powerful regressors such as deep neural networks. We then derive a covariance constraint that can be used to automatically learn which visual structures provide stable anchors for local feature detection. We support these ideas theoretically, proposing a novel analysis of local features in term of geometric transformations, and we show that all common and many uncommon detectors can be derived in this framework. Finally, we present empirical results on translation and rotation covariant detectors on standard feature benchmarks, showing the power and flexibility of the framework.
Tasks
Published	2016-05-04
URL	http://arxiv.org/abs/1605.01224v2
PDF	http://arxiv.org/pdf/1605.01224v2.pdf
PWC	https://paperswithcode.com/paper/learning-covariant-feature-detectors
Repo	https://github.com/lenck/ddet
Framework	none

PAMPO: using pattern matching and pos-tagging for effective Named Entities recognition in Portuguese


Title	PAMPO: using pattern matching and pos-tagging for effective Named Entities recognition in Portuguese
Authors	Conceição Rocha, Alípio Jorge, Roberta Sionara, Paula Brito, Carlos Pimenta, Solange Rezende
Abstract	This paper deals with the entity extraction task (named entity recognition) of a text mining process that aims at unveiling non-trivial semantic structures, such as relationships and interaction between entities or communities. In this paper we present a simple and efficient named entity extraction algorithm. The method, named PAMPO (PAttern Matching and POs tagging based algorithm for NER), relies on flexible pattern matching, part-of-speech tagging and lexical-based rules. It was developed to process texts written in Portuguese, however it is potentially applicable to other languages as well. We compare our approach with current alternatives that support Named Entity Recognition (NER) for content written in Portuguese. These are Alchemy, Zemanta and Rembrandt. Evaluation of the efficacy of the entity extraction method on several texts written in Portuguese indicates a considerable improvement on $recall$ and $F_1$ measures.
Tasks	Entity Extraction, Named Entity Recognition, Part-Of-Speech Tagging
Published	2016-12-30
URL	http://arxiv.org/abs/1612.09535v1
PDF	http://arxiv.org/pdf/1612.09535v1.pdf
PWC	https://paperswithcode.com/paper/pampo-using-pattern-matching-and-pos-tagging
Repo	https://github.com/LIAAD/py-pampo
Framework	none

Beyond Skip Connections: Top-Down Modulation for Object Detection


Title	Beyond Skip Connections: Top-Down Modulation for Object Detection
Authors	Abhinav Shrivastava, Rahul Sukthankar, Jitendra Malik, Abhinav Gupta
Abstract	In recent years, we have seen tremendous progress in the field of object detection. Most of the recent improvements have been achieved by targeting deeper feedforward networks. However, many hard object categories such as bottle, remote, etc. require representation of fine details and not just coarse, semantic representations. But most of these fine details are lost in the early convolutional layers. What we need is a way to incorporate finer details from lower layers into the detection architecture. Skip connections have been proposed to combine high-level and low-level features, but we argue that selecting the right features from low-level requires top-down contextual information. Inspired by the human visual pathway, in this paper we propose top-down modulations as a way to incorporate fine details into the detection framework. Our approach supplements the standard bottom-up, feedforward ConvNet with a top-down modulation (TDM) network, connected using lateral connections. These connections are responsible for the modulation of lower layer filters, and the top-down network handles the selection and integration of contextual information and low-level features. The proposed TDM architecture provides a significant boost on the COCO testdev benchmark, achieving 28.6 AP for VGG16, 35.2 AP for ResNet101, and 37.3 for InceptionResNetv2 network, without any bells and whistles (e.g., multi-scale, iterative box refinement, etc.).
Tasks	Object Detection
Published	2016-12-20
URL	http://arxiv.org/abs/1612.06851v2
PDF	http://arxiv.org/pdf/1612.06851v2.pdf
PWC	https://paperswithcode.com/paper/beyond-skip-connections-top-down-modulation
Repo	https://github.com/MTCloudVision/mxnet-dssd
Framework	mxnet

Mixing Dirichlet Topic Models and Word Embeddings to Make lda2vec


Title	Mixing Dirichlet Topic Models and Word Embeddings to Make lda2vec
Authors	Christopher E Moody
Abstract	Distributed dense word vectors have been shown to be effective at capturing token-level semantic and syntactic regularities in language, while topic models can form interpretable representations over documents. In this work, we describe lda2vec, a model that learns dense word vectors jointly with Dirichlet-distributed latent document-level mixtures of topic vectors. In contrast to continuous dense document representations, this formulation produces sparse, interpretable document mixtures through a non-negative simplex constraint. Our method is simple to incorporate into existing automatic differentiation frameworks and allows for unsupervised document representations geared for use by scientists while simultaneously learning word vectors and the linear relationships between them.
Tasks	Topic Models, Word Embeddings
Published	2016-05-06
URL	http://arxiv.org/abs/1605.02019v1
PDF	http://arxiv.org/pdf/1605.02019v1.pdf
PWC	https://paperswithcode.com/paper/mixing-dirichlet-topic-models-and-word
Repo	https://github.com/folivetti/HBLCoClust
Framework	none

Character-level Convolutional Network for Text Classification Applied to Chinese Corpus


Title	Character-level Convolutional Network for Text Classification Applied to Chinese Corpus
Authors	Weijie Huang, Jun Wang
Abstract	This article provides an interesting exploration of character-level convolutional neural network solving Chinese corpus text classification problem. We constructed a large-scale Chinese language dataset, and the result shows that character-level convolutional neural network works better on Chinese corpus than its corresponding pinyin format dataset. This is the first time that character-level convolutional neural network applied to text classification problem.
Tasks	Text Classification
Published	2016-11-14
URL	http://arxiv.org/abs/1611.04358v2
PDF	http://arxiv.org/pdf/1611.04358v2.pdf
PWC	https://paperswithcode.com/paper/character-level-convolutional-network-for
Repo	https://github.com/koalaGreener/Character-level-Convolutional-Network-for-Text-Classification-Applied-to-Chinese-Corpus
Framework	tf

Unifying Registration based Tracking: A Case Study with Structural Similarity


Title	Unifying Registration based Tracking: A Case Study with Structural Similarity
Authors	Abhineet Singh, Mennatullah Siam, Martin Jagersand
Abstract	This paper adapts a popular image quality measure called structural similarity for high precision registration based tracking while also introducing a simpler and faster variant of the same. Further, these are evaluated comprehensively against existing measures using a unified approach to study registration based trackers that decomposes them into three constituent sub modules - appearance model, state space model and search method. Several popular trackers in literature are broken down using this method so that their contributions - as of this paper - are shown to be limited to only one or two of these submodules. An open source tracking framework is made available that follows this decomposition closely through extensive use of generic programming. It is used to perform all experiments on four publicly available datasets so the results are easily reproducible. This framework provides a convenient interface to plug in a new method for any sub module and combine it with existing methods for the other two. It can also serve as a fast and flexible solution for practical tracking needs due to its highly efficient implementation.
Tasks
Published	2016-07-15
URL	http://arxiv.org/abs/1607.04673v4
PDF	http://arxiv.org/pdf/1607.04673v4.pdf
PWC	https://paperswithcode.com/paper/unifying-registration-based-tracking-a-case
Repo	https://github.com/abhineet123/MTF
Framework	none

Swivel: Improving Embeddings by Noticing What’s Missing


Title	Swivel: Improving Embeddings by Noticing What’s Missing
Authors	Noam Shazeer, Ryan Doherty, Colin Evans, Chris Waterson
Abstract	We present Submatrix-wise Vector Embedding Learner (Swivel), a method for generating low-dimensional feature embeddings from a feature co-occurrence matrix. Swivel performs approximate factorization of the point-wise mutual information matrix via stochastic gradient descent. It uses a piecewise loss with special handling for unobserved co-occurrences, and thus makes use of all the information in the matrix. While this requires computation proportional to the size of the entire matrix, we make use of vectorized multiplication to process thousands of rows and columns at once to compute millions of predicted values. Furthermore, we partition the matrix into shards in order to parallelize the computation across many nodes. This approach results in more accurate embeddings than can be achieved with methods that consider only observed co-occurrences, and can scale to much larger corpora than can be handled with sampling methods.
Tasks
Published	2016-02-06
URL	http://arxiv.org/abs/1602.02215v1
PDF	http://arxiv.org/pdf/1602.02215v1.pdf
PWC	https://paperswithcode.com/paper/swivel-improving-embeddings-by-noticing-whats
Repo	https://github.com/tensorflow/models/tree/master/research/swivel
Framework	tf

Interpretable Distribution Features with Maximum Testing Power


Title	Interpretable Distribution Features with Maximum Testing Power
Authors	Wittawat Jitkrittum, Zoltan Szabo, Kacper Chwialkowski, Arthur Gretton
Abstract	Two semimetrics on probability distributions are proposed, given as the sum of differences of expectations of analytic functions evaluated at spatial or frequency locations (i.e, features). The features are chosen so as to maximize the distinguishability of the distributions, by optimizing a lower bound on test power for a statistical test using these features. The result is a parsimonious and interpretable indication of how and where two distributions differ locally. An empirical estimate of the test power criterion converges with increasing sample size, ensuring the quality of the returned features. In real-world benchmarks on high-dimensional text and image data, linear-time tests using the proposed semimetrics achieve comparable performance to the state-of-the-art quadratic-time maximum mean discrepancy test, while returning human-interpretable features that explain the test results.
Tasks
Published	2016-05-22
URL	http://arxiv.org/abs/1605.06796v2
PDF	http://arxiv.org/pdf/1605.06796v2.pdf
PWC	https://paperswithcode.com/paper/interpretable-distribution-features-with
Repo	https://github.com/wittawatj/interpretable-test
Framework	none

Missing Data Imputation for Supervised Learning


Title	Missing Data Imputation for Supervised Learning
Authors	Jason Poulos, Rafael Valle
Abstract	Missing data imputation can help improve the performance of prediction models in situations where missing data hide useful information. This paper compares methods for imputing missing categorical data for supervised classification tasks. We experiment on two machine learning benchmark datasets with missing categorical data, comparing classifiers trained on non-imputed (i.e., one-hot encoded) or imputed data with different levels of additional missing-data perturbation. We show imputation methods can increase predictive accuracy in the presence of missing-data perturbation, which can actually improve prediction accuracy by regularizing the classifier. We achieve the state-of-the-art on the Adult dataset with missing-data perturbation and k-nearest-neighbors (k-NN) imputation.
Tasks	Imputation
Published	2016-10-28
URL	http://arxiv.org/abs/1610.09075v2
PDF	http://arxiv.org/pdf/1610.09075v2.pdf
PWC	https://paperswithcode.com/paper/missing-data-imputation-for-supervised
Repo	https://github.com/rafaelvalle/MDI
Framework	none

SwiDeN : Convolutional Neural Networks For Depiction Invariant Object Recognition


Title	SwiDeN : Convolutional Neural Networks For Depiction Invariant Object Recognition
Authors	Ravi Kiran Sarvadevabhatla, Shiv Surya, Srinivas S S Kruthiventi, Venkatesh Babu R
Abstract	Current state of the art object recognition architectures achieve impressive performance but are typically specialized for a single depictive style (e.g. photos only, sketches only). In this paper, we present SwiDeN : our Convolutional Neural Network (CNN) architecture which recognizes objects regardless of how they are visually depicted (line drawing, realistic shaded drawing, photograph etc.). In SwiDeN, we utilize a novel `deep’ depictive style-based switching mechanism which appropriately addresses the depiction-specific and depiction-invariant aspects of the problem. We compare SwiDeN with alternative architectures and prior work on a 50-category Photo-Art dataset containing objects depicted in multiple styles. Experimental results show that SwiDeN outperforms other approaches for the depiction-invariant object recognition problem. \|
Tasks	Depiction Invariant Object Recognition, Object Recognition
Published	2016-07-29
URL	http://arxiv.org/abs/1607.08764v1
PDF	http://arxiv.org/pdf/1607.08764v1.pdf
PWC	https://paperswithcode.com/paper/swiden-convolutional-neural-networks-for
Repo	https://github.com/val-iisc/swiden
Framework	none

Learning to Compose Neural Networks for Question Answering


Title	Learning to Compose Neural Networks for Question Answering
Authors	Jacob Andreas, Marcus Rohrbach, Trevor Darrell, Dan Klein
Abstract	We describe a question answering model that applies to both images and structured knowledge bases. The model uses natural language strings to automatically assemble neural networks from a collection of composable modules. Parameters for these modules are learned jointly with network-assembly parameters via reinforcement learning, with only (world, question, answer) triples as supervision. Our approach, which we term a dynamic neural model network, achieves state-of-the-art results on benchmark datasets in both visual and structured domains.
Tasks	Question Answering
Published	2016-01-07
URL	http://arxiv.org/abs/1601.01705v4
PDF	http://arxiv.org/pdf/1601.01705v4.pdf
PWC	https://paperswithcode.com/paper/learning-to-compose-neural-networks-for
Repo	https://github.com/abhigoyal1997/CS-763-Project
Framework	pytorch

Learning Domain-Invariant Subspace using Domain Features and Independence Maximization


Title	Learning Domain-Invariant Subspace using Domain Features and Independence Maximization
Authors	Ke Yan, Lu Kou, David Zhang
Abstract	Domain adaptation algorithms are useful when the distributions of the training and the test data are different. In this paper, we focus on the problem of instrumental variation and time-varying drift in the field of sensors and measurement, which can be viewed as discrete and continuous distributional change in the feature space. We propose maximum independence domain adaptation (MIDA) and semi-supervised MIDA (SMIDA) to address this problem. Domain features are first defined to describe the background information of a sample, such as the device label and acquisition time. Then, MIDA learns a subspace which has maximum independence with the domain features, so as to reduce the inter-domain discrepancy in distributions. A feature augmentation strategy is also designed to project samples according to their backgrounds so as to improve the adaptation. The proposed algorithms are flexible and fast. Their effectiveness is verified by experiments on synthetic datasets and four real-world ones on sensors, measurement, and computer vision. They can greatly enhance the practicability of sensor systems, as well as extend the application scope of existing domain adaptation algorithms by uniformly handling different kinds of distributional change.
Tasks	Domain Adaptation
Published	2016-03-15
URL	http://arxiv.org/abs/1603.04535v2
PDF	http://arxiv.org/pdf/1603.04535v2.pdf
PWC	https://paperswithcode.com/paper/learning-domain-invariant-subspace-using
Repo	https://github.com/zhangxuhuizju/TCA
Framework	none

Border-Peeling Clustering


Title	Border-Peeling Clustering
Authors	Hadar Averbuch-Elor, Nadav Bar, Daniel Cohen-Or
Abstract	In this paper, we present a novel non-parametric clustering technique. Our technique is based on the notion that each latent cluster is comprised of layers that surround its core, where the external layers, or border points, implicitly separate the clusters. Unlike previous techniques, such as DBSCAN, where the cores of the clusters are defined directly by their densities, here the latent cores are revealed by a progressive peeling of the border points. Analyzing the density of the local neighborhoods allows identifying the border points and associating them with points of inner layers. We show that the peeling process adapts to the local densities and characteristics to successfully separate adjacent clusters (of possibly different densities). We extensively tested our technique on large sets of labeled data, including high-dimensional datasets of deep features that were trained by a convolutional neural network. We show that our technique is competitive to other state-of-the-art non-parametric methods using a fixed set of parameters throughout the experiments.
Tasks
Published	2016-12-14
URL	https://arxiv.org/abs/1612.04869v2
PDF	https://arxiv.org/pdf/1612.04869v2.pdf
PWC	https://paperswithcode.com/paper/border-peeling-clustering
Repo	https://github.com/nadavbar/BorderPeelingClustering
Framework	none

Muffled Semi-Supervised Learning


Title	Muffled Semi-Supervised Learning
Authors	Akshay Balsubramani, Yoav Freund
Abstract	We explore a novel approach to semi-supervised learning. This approach is contrary to the common approach in that the unlabeled examples serve to “muffle,” rather than enhance, the guidance provided by the labeled examples. We provide several variants of the basic algorithm and show experimentally that they can achieve significantly higher AUC than boosted trees, random forests and logistic regression when unlabeled examples are available.
Tasks
Published	2016-05-28
URL	http://arxiv.org/abs/1605.08833v1
PDF	http://arxiv.org/pdf/1605.08833v1.pdf
PWC	https://paperswithcode.com/paper/muffled-semi-supervised-learning
Repo	https://github.com/aikanor/marvin
Framework	none