April 2, 2020

3098 words 15 mins read

Paper Group ANR 334

A General Pairwise Comparison Model for Extremely Sparse Networks. Dissecting Catastrophic Forgetting in Continual Learning by Deep Visualization. Domain-aware Visual Bias Eliminating for Generalized Zero-Shot Learning. The Pedestrian Patterns Dataset. PSC-Net: Learning Part Spatial Co-occurrence for Occluded Pedestrian Detection. Enhancement of Sh …

A General Pairwise Comparison Model for Extremely Sparse Networks


Title	A General Pairwise Comparison Model for Extremely Sparse Networks
Authors	Ruijian Han, Yiming Xu, Kani Chen
Abstract	Statistical inference using pairwise comparison data has been an effective approach to analyzing complex and sparse networks. In this paper we propose a general framework for modeling the mutual interaction in a probabilistic network, which enjoys ample flexibility in terms of parametrization. Within this set-up, we establish that the maximum likelihood estimator (MLE) for the latent scores of the subjects is uniformly consistent under a near-minimal condition on network sparsity. This condition is sharp in terms of the leading order asymptotics describing the sparsity. The proof utilizes a novel chaining technique based on the error-induced metric as well as careful counting of comparison graph structures. Our results guarantee that the MLE is a valid estimator for inference in large-scale comparison networks where data is asymptotically deficient. Numerical simulations are provided to complement the theoretical analysis.
Tasks
Published	2020-02-20
URL	https://arxiv.org/abs/2002.08853v1
PDF	https://arxiv.org/pdf/2002.08853v1.pdf
PWC	https://paperswithcode.com/paper/a-general-pairwise-comparison-model-for
Repo
Framework

Dissecting Catastrophic Forgetting in Continual Learning by Deep Visualization


Title	Dissecting Catastrophic Forgetting in Continual Learning by Deep Visualization
Authors	Giang Nguyen, Shuan Chen, Thao Do, Tae Joon Jun, Ho-Jin Choi, Daeyoung Kim
Abstract	Interpreting the behaviors of Deep Neural Networks (usually considered as a black box) is critical especially when they are now being widely adopted over diverse aspects of human life. Taking the advancements from Explainable Artificial Intelligent, this paper proposes a novel technique called Auto DeepVis to dissect catastrophic forgetting in continual learning. A new method to deal with catastrophic forgetting named critical freezing is also introduced upon investigating the dilemma by Auto DeepVis. Experiments on a captioning model meticulously present how catastrophic forgetting happens, particularly showing which components are forgetting or changing. The effectiveness of our technique is then assessed; and more precisely, critical freezing claims the best performance on both previous and coming tasks over baselines, proving the capability of the investigation. Our techniques could not only be supplementary to existing solutions for completely eradicating catastrophic forgetting for life-long learning but also explainable.
Tasks	Continual Learning
Published	2020-01-06
URL	https://arxiv.org/abs/2001.01578v2
PDF	https://arxiv.org/pdf/2001.01578v2.pdf
PWC	https://paperswithcode.com/paper/dissecting-catastrophic-forgetting-in
Repo
Framework

Domain-aware Visual Bias Eliminating for Generalized Zero-Shot Learning


Title	Domain-aware Visual Bias Eliminating for Generalized Zero-Shot Learning
Authors	Shaobo Min, Hantao Yao, Hongtao Xie, Chaoqun Wang, Zheng-Jun Zha, Yongdong Zhang
Abstract	Recent methods focus on learning a unified semantic-aligned visual representation to transfer knowledge between two domains, while ignoring the effect of semantic-free visual representation in alleviating the biased recognition problem. In this paper, we propose a novel Domain-aware Visual Bias Eliminating (DVBE) network that constructs two complementary visual representations, i.e., semantic-free and semantic-aligned, to treat seen and unseen domains separately. Specifically, we explore cross-attentive second-order visual statistics to compact the semantic-free representation, and design an adaptive margin Softmax to maximize inter-class divergences. Thus, the semantic-free representation becomes discriminative enough to not only predict seen class accurately but also filter out unseen images, i.e., domain detection, based on the predicted class entropy. For unseen images, we automatically search an optimal semantic-visual alignment architecture, rather than manual designs, to predict unseen classes. With accurate domain detection, the biased recognition problem towards the seen domain is significantly reduced. Experiments on five benchmarks for classification and segmentation show that DVBE outperforms existing methods by averaged 5.7% improvement.
Tasks	Zero-Shot Learning
Published	2020-03-30
URL	https://arxiv.org/abs/2003.13261v1
PDF	https://arxiv.org/pdf/2003.13261v1.pdf
PWC	https://paperswithcode.com/paper/domain-aware-visual-bias-eliminating-for
Repo
Framework

The Pedestrian Patterns Dataset


Title	The Pedestrian Patterns Dataset
Authors	Kasra Mokhtari, Alan R. Wagner
Abstract	We present the pedestrian patterns dataset for autonomous driving. The dataset was collected by repeatedly traversing the same three routes for one week starting at different specific timeslots. The purpose of the dataset is to capture the patterns of social and pedestrian behavior along the traversed routes at different times and to eventually use this information to make predictions about the risk associated with autonomously traveling along different routes. This dataset contains the Full HD videos and GPS data for each traversal. Fast R-CNN pedestrian detection method is applied to the captured videos to count the number of pedestrians at each video frame in order to assess the density of pedestrians along a route. By providing this large-scale dataset to researchers, we hope to accelerate autonomous driving research not only to estimate the risk, both to the public and to the autonomous vehicle but also accelerate research on long-term vision-based localization of mobile robots and autonomous vehicles of the future.
Tasks	Autonomous Driving, Autonomous Vehicles, Pedestrian Detection
Published	2020-01-06
URL	https://arxiv.org/abs/2001.01816v1
PDF	https://arxiv.org/pdf/2001.01816v1.pdf
PWC	https://paperswithcode.com/paper/the-pedestrian-patterns-dataset
Repo
Framework

PSC-Net: Learning Part Spatial Co-occurrence for Occluded Pedestrian Detection


Title	PSC-Net: Learning Part Spatial Co-occurrence for Occluded Pedestrian Detection
Authors	Jin Xie, Yanwei Pang, Hisham Cholakkal, Rao Muhammad Anwer, Fahad Shahbaz Khan, Ling Shao
Abstract	Detecting pedestrians, especially under heavy occlusions, is a challenging computer vision problem with numerous real-world applications. This paper introduces a novel approach, termed as PSC-Net, for occluded pedestrian detection. The proposed PSC-Net contains a dedicated module that is designed to explicitly capture both inter and intra-part co-occurrence information of different pedestrian body parts through a Graph Convolutional Network (GCN). Both inter and intra-part co-occurrence information contribute towards improving the feature representation for handling varying level of occlusions, ranging from partial to severe occlusions. Our PSC-Net exploits the topological structure of pedestrian and does not require part-based annotations or additional visible bounding-box (VBB) information to learn part spatial co-occurrence. Comprehensive experiments are performed on two challenging datasets: CityPersons and Caltech datasets. The proposed PSC-Net achieves state-of-the-art detection performance on both. On the heavy occluded (\textbf{HO}) set of CityPerosns test set, our PSC-Net obtains an absolute gain of 4.0% in terms of log-average miss rate over the state-of-the-art with same backbone, input scale and without using additional VBB supervision. Further, PSC-Net improves the state-of-the-art from 37.9 to 34.8 in terms of log-average miss rate on Caltech (\textbf{HO}) test set.
Tasks	Pedestrian Detection
Published	2020-01-25
URL	https://arxiv.org/abs/2001.09252v2
PDF	https://arxiv.org/pdf/2001.09252v2.pdf
PWC	https://paperswithcode.com/paper/psc-net-learning-part-spatial-co-occurence
Repo
Framework

Enhancement of Short Text Clustering by Iterative Classification


Title	Enhancement of Short Text Clustering by Iterative Classification
Authors	Md Rashadul Hasan Rakib, Norbert Zeh, Magdalena Jankowska, Evangelos Milios
Abstract	Short text clustering is a challenging task due to the lack of signal contained in such short texts. In this work, we propose iterative classification as a method to b o ost the clustering quality (e.g., accuracy) of short texts. Given a clustering of short texts obtained using an arbitrary clustering algorithm, iterative classification applies outlier removal to obtain outlier-free clusters. Then it trains a classification algorithm using the non-outliers based on their cluster distributions. Using the trained classification model, iterative classification reclassifies the outliers to obtain a new set of clusters. By repeating this several times, we obtain a much improved clustering of texts. Our experimental results show that the proposed clustering enhancement method not only improves the clustering quality of different clustering methods (e.g., k-means, k-means–, and hierarchical clustering) but also outperforms the state-of-the-art short text clustering methods on several short text datasets by a statistically significant margin.
Tasks	Text Clustering
Published	2020-01-31
URL	https://arxiv.org/abs/2001.11631v1
PDF	https://arxiv.org/pdf/2001.11631v1.pdf
PWC	https://paperswithcode.com/paper/enhancement-of-short-text-clustering-by
Repo
Framework

CONVINCE: Collaborative Cross-Camera Video Analytics at the Edge


Title	CONVINCE: Collaborative Cross-Camera Video Analytics at the Edge
Authors	Hannaneh Barahouei Pasandi, Tamer Nadeem
Abstract	Today, video cameras are deployed in dense for monitoring physical places e.g., city, industrial, or agricultural sites. In the current systems, each camera node sends its feed to a cloud server individually. However, this approach suffers from several hurdles including higher computation cost, large bandwidth requirement for analyzing the enormous data, and privacy concerns. In dense deployment, video nodes typically demonstrate a significant spatio-temporal correlation. To overcome these obstacles in current approaches, this paper introduces CONVINCE, a new approach to look at the network cameras as a collective entity that enables collaborative video analytics pipeline among cameras. CONVINCE aims at 1) reducing the computation cost and bandwidth requirements by leveraging spatio-temporal correlations among cameras in eliminating redundant frames intelligently, and ii) improving vision algorithms’ accuracy by enabling collaborative knowledge sharing among relevant cameras. Our results demonstrate that CONVINCE achieves an object identification accuracy of $\sim$91%, by transmitting only about $\sim$25% of all the recorded frames.
Tasks
Published	2020-02-05
URL	https://arxiv.org/abs/2002.03797v1
PDF	https://arxiv.org/pdf/2002.03797v1.pdf
PWC	https://paperswithcode.com/paper/convince-collaborative-cross-camera-video
Repo
Framework

Towards Deep Machine Reasoning: a Prototype-based Deep Neural Network with Decision Tree Inference


Title	Towards Deep Machine Reasoning: a Prototype-based Deep Neural Network with Decision Tree Inference
Authors	Plamen Angelov, Eduardo Soares
Abstract	In this paper we introduce the DMR – a prototype-based method and network architecture for deep learning which is using a decision tree (DT)-based inference and synthetic data to balance the classes. It builds upon the recently introduced xDNN method addressing more complex multi-class problems, specifically when classes are highly imbalanced. DMR moves away from a direct decision based on all classes towards a layered DT of pair-wise class comparisons. In addition, it forces the prototypes to be balanced between classes regardless of possible class imbalances of the training data. It has two novel mechanisms, namely i) using a DT to determine the winning class label, and ii) balancing the classes by synthesizing data around the prototypes determined from the available training data. As a result, we improved significantly the performance of the resulting fully explainable DNN as evidenced by the best reported result on the well know benchmark problem Caltech-101 surpassing our own recently published “world record”. Furthermore, we also achieved another “world record” for another very hard benchmark problem, namely Caltech-256 as well as surpassed the results of other approaches on Faces-1999 problem. In summary, we propose a new approach specifically advantageous for imbalanced multi-class problems that achieved two world records on well known hard benchmark problems and the best result on another problem in terms of accuracy. Moreover, DMR offers full explainability, does not require GPUs and can continue to learn from new data by adding new prototypes preserving the previous ones but not requiring full retraining.
Tasks
Published	2020-02-02
URL	https://arxiv.org/abs/2002.03776v1
PDF	https://arxiv.org/pdf/2002.03776v1.pdf
PWC	https://paperswithcode.com/paper/towards-deep-machine-reasoning-a-prototype
Repo
Framework

On Learning a Hidden Directed Graph with Path Queries


Title	On Learning a Hidden Directed Graph with Path Queries
Authors	Mano Vikash Janardhanan, Lev Reyzin
Abstract	In this paper, we consider the problem of reconstructing a directed graph using path queries. In this query model of learning, a graph is hidden from the learner, and the learner can access information about it with path queries. For a source and destination node, a path query returns whether there is a directed path from the source to the destination node in the hidden graph. In this paper we first give bounds for learning graphs on $n$ vertices and $k$ strongly connected components. We then study the case of bounded degree directed trees and give new algorithms for learning “almost-trees” – directed trees to which extra edges have been added. We also give some lower bound constructions justifying our approach.
Tasks
Published	2020-02-26
URL	https://arxiv.org/abs/2002.11541v1
PDF	https://arxiv.org/pdf/2002.11541v1.pdf
PWC	https://paperswithcode.com/paper/on-learning-a-hidden-directed-graph-with-path
Repo
Framework

A Review on InSAR Phase Denoising


Title	A Review on InSAR Phase Denoising
Authors	Gang Xu, Yandong Gao, Jinwei Li, Mengdao Xing
Abstract	Nowadays, interferometric synthetic aperture radar (InSAR) has been a powerful tool in remote sensing by enhancing the information acquisition. During the InSAR processing, phase denoising of interferogram is a mandatory step for topography mapping and deformation monitoring. Over the last three decades, a large number of effective algorithms have been developed to do efforts on this topic. In this paper, we give a comprehensive overview of InSAR phase denoising methods, classifying the established and emerging algorithms into four main categories. The first two parts refer to the categories of traditional local filters and transformed-domain filters, respectively. The third part focuses on the category of nonlocal (NL) filters, considering their outstanding performances. Latter, some advanced methods based on new concept of signal processing are also introduced to show their potentials in this field. Moreover, several popular phase denoising methods are illustrated and compared by performing the numerical experiments using both simulated and measured data. The purpose of this paper is intended to provide necessary guideline and inspiration to related researchers by promoting the architecture development of InSAR signal processing.
Tasks	Denoising
Published	2020-01-03
URL	https://arxiv.org/abs/2001.00769v1
PDF	https://arxiv.org/pdf/2001.00769v1.pdf
PWC	https://paperswithcode.com/paper/a-review-on-insar-phase-denoising
Repo
Framework

SiamSNN: Spike-based Siamese Network for Energy-Efficient and Real-time Object Tracking


Title	SiamSNN: Spike-based Siamese Network for Energy-Efficient and Real-time Object Tracking
Authors	Yihao Luo, Min Xu, Caihong Yuan, Xiang Cao, Yan Xu, Tianjiang Wang, Qi Feng
Abstract	Although deep neural networks (DNNs) have achieved fantastic success in various scenarios, it’s difficult to employ DNNs on many systems with limited resources due to their high energy consumption. It’s well known that spiking neural networks (SNNs) are attracting more attention due to the capability of energy-efficient computing. Recently many works focus on converting DNNs into SNNs with little accuracy degradation in image classification on MNIST, CIFAR-10/100. However, few studies on shortening latency, and spike-based modules of more challenging tasks on complex datasets. In this paper, we focus on the similarity matching method of deep spike features and present a first spike-based Siamese network for object tracking called SiamSNN. Specifically, we propose a hybrid spiking similarity matching method with membrane potential and time step to evaluate the response map between exemplar and candidate images, with the same function as correlation layer in SiamFC. Then we present a coding scheme for utilizing temporal information of spike trains, and implement it in output spiking layers to improve the performance and shorten the latency. Our experiments show that SiamSNN achieves short latency and low precision loss of the original SiamFC on the tracking datasets OTB-2013, OTB-2015 and VOT2016. Moreover, SiamSNN achieves real-time (50 FPS) and extremely low energy consumption on TrueNorth.
Tasks	Image Classification, Object Tracking
Published	2020-03-17
URL	https://arxiv.org/abs/2003.07584v1
PDF	https://arxiv.org/pdf/2003.07584v1.pdf
PWC	https://paperswithcode.com/paper/siamsnn-spike-based-siamese-network-for
Repo
Framework

An On-Device Federated Learning Approach for Cooperative Anomaly Detection


Title	An On-Device Federated Learning Approach for Cooperative Anomaly Detection
Authors	Rei Ito, Mineto Tsukada, Hiroki Matsutani
Abstract	Most edge AI focuses on prediction tasks on resource-limited edge devices, while the training is done at server machines, so retraining a model on the edge devices to reflect environmental changes is a complicated task. To follow such a concept drift, a neural-network based on-device learning approach is recently proposed, so that edge devices train incoming data at runtime to update their model. In this case, since a training is done at distributed edge devices, the issue is that only a limited amount of training data can be used for each edge device. To address this issue, one approach is a cooperative learning or federated learning, where edge devices exchange their trained results and update their model by using those collected from the other devices. In this paper, as an on-device learning algorithm, we focus on OS-ELM (Online Sequential Extreme Learning Machine) and combine it with Autoencoder for anomaly detection. We extend it for an on-device federated learning so that edge devices exchange their trained results and update their model by using those collected from the other edge devices. Experimental results using a driving dataset of cars demonstrate that the proposed on-device federated learning can produce more accurate model by combining trained results from multiple edge devices compared to a single model.
Tasks	Anomaly Detection
Published	2020-02-27
URL	https://arxiv.org/abs/2002.12301v1
PDF	https://arxiv.org/pdf/2002.12301v1.pdf
PWC	https://paperswithcode.com/paper/an-on-device-federated-learning-approach-for
Repo
Framework

Aspect-based Academic Search using Domain-specific KB


Title	Aspect-based Academic Search using Domain-specific KB
Authors	Prajna Upadhyay, Srikanta Bedathur, Tanmoy Chakraborty, Maya Ramanath
Abstract	Academic search engines allow scientists to explore related work relevant to a given query. Often, the user is also aware of the “aspect” to retrieve a relevant document. In such cases, existing search engines can be used by expanding the query with terms describing that aspect. However, this approach does not guarantee good results since plain keyword matches do not always imply relevance. To address this issue, we define and solve a novel academic search task, called “aspect-based retrieval”, which allows the user to specify the aspect along with the query to retrieve a ranked list of relevant documents. The primary idea is to estimate a language model for the aspect as well as the query using a domain-specific knowledge base and use a mixture of the two to determine the relevance of the article. Our evaluation of the results over the Open Research Corpus dataset shows that our method outperforms keyword-based expansion of query with aspect with and without relevance feedback.
Tasks	Language Modelling
Published	2020-01-29
URL	https://arxiv.org/abs/2001.10781v1
PDF	https://arxiv.org/pdf/2001.10781v1.pdf
PWC	https://paperswithcode.com/paper/aspect-based-academic-search-using-domain
Repo
Framework


Title	Refinements in Motion and Appearance for Online Multi-Object Tracking
Authors	Piao Huang, Shoudong Han, Jun Zhao, Donghaisheng Liu, Hongwei Wang, En Yu, Alex ChiChung Kot
Abstract	Modern multi-object tracking (MOT) system usually involves separated modules, such as motion model for location and appearance model for data association. However, the compatible problems within both motion and appearance models are always ignored. In this paper, a general architecture named as MIF is presented by seamlessly blending the Motion integration, three-dimensional(3D) Integral image and adaptive appearance feature Fusion. Since the uncertain pedestrian and camera motions are usually handled separately, the integrated motion model is designed using our defined intension of camera motion. Specifically, a 3D integral image based spatial blocking method is presented to efficiently cut useless connections between trajectories and candidates with spatial constraints. Then the appearance model and visibility prediction are jointly built. Considering scale, pose and visibility, the appearance features are adaptively fused to overcome the feature misalignment problem. Our MIF based tracker (MIFT) achieves the state-of-the-art accuracy with 60.1 MOTA on both MOT16&17 challenges.
Tasks	Multi-Object Tracking, Object Tracking, Online Multi-Object Tracking
Published	2020-03-16
URL	https://arxiv.org/abs/2003.07177v2
PDF	https://arxiv.org/pdf/2003.07177v2.pdf
PWC	https://paperswithcode.com/paper/refinements-in-motion-and-appearance-for
Repo
Framework

Talking-Heads Attention


Title	Talking-Heads Attention
Authors	Noam Shazeer, Zhenzhong Lan, Youlong Cheng, Nan Ding, Le Hou
Abstract	We introduce “talking-heads attention” - a variation on multi-head attention which includes linearprojections across the attention-heads dimension, immediately before and after the softmax operation.While inserting only a small number of additional parameters and a moderate amount of additionalcomputation, talking-heads attention leads to better perplexities on masked language modeling tasks, aswell as better quality when transfer-learning to language comprehension and question answering tasks.
Tasks	Language Modelling, Question Answering, Transfer Learning
Published	2020-03-05
URL	https://arxiv.org/abs/2003.02436v1
PDF	https://arxiv.org/pdf/2003.02436v1.pdf
PWC	https://paperswithcode.com/paper/talking-heads-attention
Repo
Framework