October 17, 2019

2697 words 13 mins read

Paper Group ANR 915

Representation Learning over Dynamic Graphs. Zero-shot Sequence Labeling: Transferring Knowledge from Sentences to Tokens. Deep Network for Simultaneous Decomposition and Classification in UWB-SAR Imagery. Attribute-Centered Loss for Soft-Biometrics Guided Face Sketch-Photo Recognition. MIRIAM: A Multimodal Chat-Based Interface for Autonomous Syste …

Representation Learning over Dynamic Graphs


Title	Representation Learning over Dynamic Graphs
Authors	Rakshit Trivedi, Mehrdad Farajtabar, Prasenjeet Biswal, Hongyuan Zha
Abstract	How can we effectively encode evolving information over dynamic graphs into low-dimensional representations? In this paper, we propose DyRep, an inductive deep representation learning framework that learns a set of functions to efficiently produce low-dimensional node embeddings that evolves over time. The learned embeddings drive the dynamics of two key processes namely, communication and association between nodes in dynamic graphs. These processes exhibit complex nonlinear dynamics that evolve at different time scales and subsequently contribute to the update of node embeddings. We employ a time-scale dependent multivariate point process model to capture these dynamics. We devise an efficient unsupervised learning procedure and demonstrate that our approach significantly outperforms representative baselines on two real-world datasets for the problem of dynamic link prediction and event time prediction.
Tasks	Dynamic Link Prediction, Link Prediction, Representation Learning
Published	2018-03-11
URL	http://arxiv.org/abs/1803.04051v2
PDF	http://arxiv.org/pdf/1803.04051v2.pdf
PWC	https://paperswithcode.com/paper/representation-learning-over-dynamic-graphs
Repo
Framework

Zero-shot Sequence Labeling: Transferring Knowledge from Sentences to Tokens


Title	Zero-shot Sequence Labeling: Transferring Knowledge from Sentences to Tokens
Authors	Marek Rei, Anders Søgaard
Abstract	Can attention- or gradient-based visualization techniques be used to infer token-level labels for binary sequence tagging problems, using networks trained only on sentence-level labels? We construct a neural network architecture based on soft attention, train it as a binary sentence classifier and evaluate against token-level annotation on four different datasets. Inferring token labels from a network provides a method for quantitatively evaluating what the model is learning, along with generating useful feedback in assistance systems. Our results indicate that attention-based methods are able to predict token-level labels more accurately, compared to gradient-based methods, sometimes even rivaling the supervised oracle network.
Tasks
Published	2018-05-06
URL	http://arxiv.org/abs/1805.02214v1
PDF	http://arxiv.org/pdf/1805.02214v1.pdf
PWC	https://paperswithcode.com/paper/zero-shot-sequence-labeling-transferring
Repo
Framework

Deep Network for Simultaneous Decomposition and Classification in UWB-SAR Imagery


Title	Deep Network for Simultaneous Decomposition and Classification in UWB-SAR Imagery
Authors	Tiep Vu, Lam Nguyen, Tiantong Guo, Vishal Monga
Abstract	Classifying buried and obscured targets of interest from other natural and manmade clutter objects in the scene is an important problem for the U.S. Army. Targets of interest are often represented by signals captured using low-frequency (UHF to L-band) ultra-wideband (UWB) synthetic aperture radar (SAR) technology. This technology has been used in various applications, including ground penetration and sensing-through-the-wall. However, the technology still faces a significant issues regarding low-resolution SAR imagery in this particular frequency band, low radar cross sections (RCS), small objects compared to radar signal wavelengths, and heavy interference. The classification problem has been firstly, and partially, addressed by sparse representation-based classification (SRC) method which can extract noise from signals and exploit the cross-channel information. Despite providing potential results, SRC-related methods have drawbacks in representing nonlinear relations and dealing with larger training sets. In this paper, we propose a Simultaneous Decomposition and Classification Network (SDCN) to alleviate noise inferences and enhance classification accuracy. The network contains two jointly trained sub-networks: the decomposition sub-network handles denoising, while the classification sub-network discriminates targets from confusers. Experimental results show significant improvements over a network without decomposition and SRC-related methods.
Tasks	Denoising, Sparse Representation-based Classification
Published	2018-01-16
URL	http://arxiv.org/abs/1801.05458v2
PDF	http://arxiv.org/pdf/1801.05458v2.pdf
PWC	https://paperswithcode.com/paper/deep-network-for-simultaneous-decomposition
Repo
Framework

Attribute-Centered Loss for Soft-Biometrics Guided Face Sketch-Photo Recognition


Title	Attribute-Centered Loss for Soft-Biometrics Guided Face Sketch-Photo Recognition
Authors	Hadi Kazemi, Sobhan Soleymani, Ali Dabouei, Mehdi Iranmanesh, Nasser M. Nasrabadi
Abstract	Face sketches are able to capture the spatial topology of a face while lacking some facial attributes such as race, skin, or hair color. Existing sketch-photo recognition approaches have mostly ignored the importance of facial attributes. In this paper, we propose a new loss function, called attribute-centered loss, to train a Deep Coupled Convolutional Neural Network (DCCNN) for the facial attribute guided sketch to photo matching. Specifically, an attribute-centered loss is proposed which learns several distinct centers, in a shared embedding space, for photos and sketches with different combinations of attributes. The DCCNN simultaneously is trained to map photos and pairs of testified attributes and corresponding forensic sketches around their associated centers, while preserving the spatial topology information. Importantly, the centers learn to keep a relative distance from each other, related to their number of contradictory attributes. Extensive experiments are performed on composite (E-PRIP) and semi-forensic (IIIT-D Semi-forensic) databases. The proposed method significantly outperforms the state-of-the-art.
Tasks
Published	2018-04-09
URL	http://arxiv.org/abs/1804.03082v1
PDF	http://arxiv.org/pdf/1804.03082v1.pdf
PWC	https://paperswithcode.com/paper/attribute-centered-loss-for-soft-biometrics
Repo
Framework

MIRIAM: A Multimodal Chat-Based Interface for Autonomous Systems


Title	MIRIAM: A Multimodal Chat-Based Interface for Autonomous Systems
Authors	Helen Hastie, Francisco J. Chiyah Garcia, David A. Robb, Pedro Patron, Atanas Laskov
Abstract	We present MIRIAM (Multimodal Intelligent inteRactIon for Autonomous systeMs), a multimodal interface to support situation awareness of autonomous vehicles through chat-based interaction. The user is able to chat about the vehicle’s plan, objectives, previous activities and mission progress. The system is mixed initiative in that it pro-actively sends messages about key events, such as fault warnings. We will demonstrate MIRIAM using SeeByte’s SeeTrack command and control interface and Neptune autonomy simulator.
Tasks	Autonomous Vehicles
Published	2018-03-06
URL	http://arxiv.org/abs/1803.02124v1
PDF	http://arxiv.org/pdf/1803.02124v1.pdf
PWC	https://paperswithcode.com/paper/miriam-a-multimodal-chat-based-interface-for
Repo
Framework

Supervised Sentiment Classification with CNNs for Diverse SE Datasets


Title	Supervised Sentiment Classification with CNNs for Diverse SE Datasets
Authors	Achyudh Ram, Meiyappan Nagappan
Abstract	Sentiment analysis, a popular technique for opinion mining, has been used by the software engineering research community for tasks such as assessing app reviews, developer emotions in issue trackers and developer opinions on APIs. Past research indicates that state-of-the-art sentiment analysis techniques have poor performance on SE data. This is because sentiment analysis tools are often designed to work on non-technical documents such as movie reviews. In this study, we attempt to solve the issues with existing sentiment analysis techniques for SE texts by proposing a hierarchical model based on convolutional neural networks (CNN) and long short-term memory (LSTM) trained on top of pre-trained word vectors. We assessed our model’s performance and reliability by comparing it with a number of frequently used sentiment analysis tools on five gold standard datasets. Our results show that our model pushes the state of the art further on all datasets in terms of accuracy. We also show that it is possible to get better accuracy after labelling a small sample of the dataset and re-training our model rather than using an unsupervised classifier.
Tasks	Opinion Mining, Sentiment Analysis
Published	2018-12-23
URL	http://arxiv.org/abs/1812.09653v1
PDF	http://arxiv.org/pdf/1812.09653v1.pdf
PWC	https://paperswithcode.com/paper/supervised-sentiment-classification-with-cnns
Repo
Framework

Zoom-In-to-Check: Boosting Video Interpolation via Instance-level Discrimination


Title	Zoom-In-to-Check: Boosting Video Interpolation via Instance-level Discrimination
Authors	Liangzhe Yuan, Yibo Chen, Hantian Liu, Tao Kong, Jianbo Shi
Abstract	We propose a light-weight video frame interpolation algorithm. Our key innovation is an instance-level supervision that allows information to be learned from the high-resolution version of similar objects. Our experiment shows that the proposed method can generate state-of-the-art results across different datasets, with fractional computation resources (time and memory) of competing methods. Given two image frames, a cascade network creates an intermediate frame with 1) a flow-warping module that computes coarse bi-directional optical flow and creates an interpolated image via flow-based warping, followed by 2) an image synthesis module to make fine-scale corrections. In the learning stage, object detection proposals are generated on the interpolated image.Lower resolution objects are zoomed into, and the learning algorithms using an adversarial loss trained on high-resolution objects to guide the system towards the instance-level refinement corrects details of object shape and boundaries.
Tasks	Image Generation, Object Detection, Optical Flow Estimation, Video Frame Interpolation
Published	2018-12-04
URL	http://arxiv.org/abs/1812.01210v2
PDF	http://arxiv.org/pdf/1812.01210v2.pdf
PWC	https://paperswithcode.com/paper/zoom-in-to-check-boosting-video-interpolation
Repo
Framework

Distinctive-attribute Extraction for Image Captioning


Title	Distinctive-attribute Extraction for Image Captioning
Authors	Boeun Kim, Young Han Lee, Hyedong Jung, Choongsang Cho
Abstract	Image captioning, an open research issue, has been evolved with the progress of deep neural networks. Convolutional neural networks (CNNs) and recurrent neural networks (RNNs) are employed to compute image features and generate natural language descriptions in the research. In previous works, a caption involving semantic description can be generated by applying additional information into the RNNs. In this approach, we propose a distinctive-attribute extraction (DaE) which explicitly encourages significant meanings to generate an accurate caption describing the overall meaning of the image with their unique situation. Specifically, the captions of training images are analyzed by term frequency-inverse document frequency (TF-IDF), and the analyzed semantic information is trained to extract distinctive-attributes for inferring captions. The proposed scheme is evaluated on a challenge data, and it improves an objective performance while describing images in more detail.
Tasks	Image Captioning
Published	2018-07-25
URL	http://arxiv.org/abs/1807.09434v1
PDF	http://arxiv.org/pdf/1807.09434v1.pdf
PWC	https://paperswithcode.com/paper/distinctive-attribute-extraction-for-image
Repo
Framework

Learning Deep Structured Multi-Scale Features using Attention-Gated CRFs for Contour Prediction


Title	Learning Deep Structured Multi-Scale Features using Attention-Gated CRFs for Contour Prediction
Authors	Dan Xu, Wanli Ouyang, Xavier Alameda-Pineda, Elisa Ricci, Xiaogang Wang, Nicu Sebe
Abstract	Recent works have shown that exploiting multi-scale representations deeply learned via convolutional neural networks (CNN) is of tremendous importance for accurate contour detection. This paper presents a novel approach for predicting contours which advances the state of the art in two fundamental aspects, i.e. multi-scale feature generation and fusion. Different from previous works directly consider- ing multi-scale feature maps obtained from the inner layers of a primary CNN architecture, we introduce a hierarchical deep model which produces more rich and complementary representations. Furthermore, to refine and robustly fuse the representations learned at different scales, the novel Attention-Gated Conditional Random Fields (AG-CRFs) are proposed. The experiments ran on two publicly available datasets (BSDS500 and NYUDv2) demonstrate the effectiveness of the latent AG-CRF model and of the overall hierarchical framework.
Tasks	Contour Detection
Published	2018-01-01
URL	http://arxiv.org/abs/1801.00524v1
PDF	http://arxiv.org/pdf/1801.00524v1.pdf
PWC	https://paperswithcode.com/paper/learning-deep-structured-multi-scale-features
Repo
Framework

Distributed Estimation of Gaussian Correlations


Title	Distributed Estimation of Gaussian Correlations
Authors	Uri Hadar, Ofer Shayevitz
Abstract	We study a distributed estimation problem in which two remotely located parties, Alice and Bob, observe an unlimited number of i.i.d. samples corresponding to two different parts of a random vector. Alice can send $k$ bits on average to Bob, who in turn wants to estimate the cross-correlation matrix between the two parts of the vector. In the case where the parties observe jointly Gaussian scalar random variables with an unknown correlation $\rho$, we obtain two constructive and simple unbiased estimators attaining a variance of $(1-\rho^2)/(2k\ln 2)$, which coincides with a known but non-constructive random coding result of Zhang and Berger. We extend our approach to the vector Gaussian case, which has not been treated before, and construct an estimator that is uniformly better than the scalar estimator applied separately to each of the correlations. We then show that the Gaussian performance can essentially be attained even when the distribution is completely unknown. This in particular implies that in the general problem of distributed correlation estimation, the variance can decay at least as $O(1/k)$ with the number of transmitted bits. This behavior, however, is not tight: we give an example of a rich family of distributions for which local samples reveal essentially nothing about the correlations, and where a slightly modified estimator attains a variance of $2^{-\Omega(k)}$.
Tasks
Published	2018-05-31
URL	http://arxiv.org/abs/1805.12472v2
PDF	http://arxiv.org/pdf/1805.12472v2.pdf
PWC	https://paperswithcode.com/paper/distributed-estimation-of-gaussian
Repo
Framework

Zero-Shot Transfer VQA Dataset


Title	Zero-Shot Transfer VQA Dataset
Authors	Yuanpeng Li, Yi Yang, Jianyu Wang, Wei Xu
Abstract	Acquiring a large vocabulary is an important aspect of human intelligence. Onecommon approach for human to populating vocabulary is to learn words duringreading or listening, and then use them in writing or speaking. This ability totransfer from input to output is natural for human, but it is difficult for machines.Human spontaneously performs this knowledge transfer in complicated multimodaltasks, such as Visual Question Answering (VQA). In order to approach human-levelArtificial Intelligence, we hope to equip machines with such ability. Therefore, toaccelerate this research, we propose a newzero-shot transfer VQA(ZST-VQA)dataset by reorganizing the existing VQA v1.0 dataset in the way that duringtraining, some words appear only in one module (i.e. questions) but not in theother (i.e. answers). In this setting, an intelligent model should understand andlearn the concepts from one module (i.e. questions), and at test time, transfer themto the other (i.e. predict the concepts as answers). We conduct evaluation on thisnew dataset using three existing state-of-the-art VQA neural models. Experimentalresults show a significant drop in performance on this dataset, indicating existingmethods do not address the zero-shot transfer problem. Besides, our analysis findsthat this may be caused by the implicit bias learned during training.
Tasks	Question Answering, Transfer Learning, Visual Question Answering
Published	2018-11-02
URL	http://arxiv.org/abs/1811.00692v1
PDF	http://arxiv.org/pdf/1811.00692v1.pdf
PWC	https://paperswithcode.com/paper/zero-shot-transfer-vqa-dataset
Repo
Framework

Rademacher Generalization Bounds for Classifier Chains


Title	Rademacher Generalization Bounds for Classifier Chains
Authors	Moura Simon, Amini Massih-Reza, Louhichi Sana, Clausel Marianne
Abstract	In this paper, we propose a new framework to study the generalization property of classifier chains trained over observations associated with multiple and interdependent class labels. The results are based on large deviation inequalities for Lipschitz functions of weakly dependent sequences proposed by Rio in 2000. We believe that the resulting generalization error bound brings many advantages and could be adapted to other frameworks that consider interdependent outputs. First, it explicitly exhibits the dependencies between class labels. Secondly, it provides insights of the effect of the order of the chain on the algorithm generalization performances. Finally, the two dependency coefficients that appear in the bound could also be used to design new strategies to decide the order of the chain.
Tasks
Published	2018-07-26
URL	http://arxiv.org/abs/1807.10166v1
PDF	http://arxiv.org/pdf/1807.10166v1.pdf
PWC	https://paperswithcode.com/paper/rademacher-generalization-bounds-for
Repo
Framework

I/O Logic in HOL — First Steps


Title	I/O Logic in HOL — First Steps
Authors	Christoph Benzmüller, Xavier Parent
Abstract	A semantical embedding of input/output logic in classical higher-order logic is presented. This embedding enables the mechanisation and automation of reasoning tasks in input/output logic with off-the-shelf higher-order theorem provers and proof assistants. The key idea for the solution presented here results from the analysis of an inaccurate previous embedding attempt, which we will discuss as well.
Tasks
Published	2018-03-26
URL	http://arxiv.org/abs/1803.09681v2
PDF	http://arxiv.org/pdf/1803.09681v2.pdf
PWC	https://paperswithcode.com/paper/io-logic-in-hol-first-steps
Repo
Framework

Saliency Prediction in the Deep Learning Era: Successes, Limitations, and Future Challenges


Title	Saliency Prediction in the Deep Learning Era: Successes, Limitations, and Future Challenges
Authors	Ali Borji
Abstract	Visual saliency models have enjoyed a big leap in performance in recent years, thanks to advances in deep learning and large scale annotated data. Despite enormous effort and huge breakthroughs, however, models still fall short in reaching human-level accuracy. In this work, I explore the landscape of the field emphasizing on new deep saliency models, benchmarks, and datasets. A large number of image and video saliency models are reviewed and compared over two image benchmarks and two large scale video datasets. Further, I identify factors that contribute to the gap between models and humans and discuss remaining issues that need to be addressed to build the next generation of more powerful saliency models. Some specific questions that are addressed include: in what ways current models fail, how to remedy them, what can be learned from cognitive studies of attention, how explicit saliency judgments relate to fixations, how to conduct fair model comparison, and what are the emerging applications of saliency models.
Tasks	Saliency Prediction
Published	2018-10-08
URL	https://arxiv.org/abs/1810.03716v3
PDF	https://arxiv.org/pdf/1810.03716v3.pdf
PWC	https://paperswithcode.com/paper/saliency-prediction-in-the-deep-learning-era
Repo
Framework

Statistical Optimality of Interpolated Nearest Neighbor Algorithms


Title	Statistical Optimality of Interpolated Nearest Neighbor Algorithms
Authors	Yue Xing, Qifan Song, Guang Cheng
Abstract	In the era of deep learning, understanding over-fitting phenomenon becomes increasingly important. It is observed that carefully designed deep neural networks achieve small testing error even when the training error is close to zero. One possible explanation is that for many modern machine learning algorithms, over-fitting can greatly reduce the estimation bias, while not increasing the estimation variance too much. To illustrate the above idea, we prove that the proposed interpolated nearest neighbor algorithm achieves the minimax optimal rate in both regression and classification regimes, and observe that they are empirically better than the traditional $k$ nearest neighbor method in some cases.
Tasks
Published	2018-10-05
URL	http://arxiv.org/abs/1810.02814v2
PDF	http://arxiv.org/pdf/1810.02814v2.pdf
PWC	https://paperswithcode.com/paper/statistical-optimality-of-interpolated
Repo
Framework