Disentangled Feature Learning Network for Vehicle Re-Identification

Vehicle Re-Identification (ReID) has attracted lots of research efforts due to its great significance to the public security. In vehicle ReID, we aim to learn features that are powerful in discriminating subtle differences between vehicles which are visually similar, and also robust against different orientations of the same vehicle. However, these two characteristics are hard to be encapsulated into a single feature representation simultaneously with unified supervision. Here we propose a Disentangled Feature Learning Network (DFLNet) to learn orientation specific and common features concurrently, which are discriminative at details and invariant to orientations, respectively. Moreover, to effectively use these two types of features for ReID, we further design a feature metric alignment scheme to ensure the consistency of the metric scales. The experiments show the effectiveness of our method that achieves state-of-the-art performance on three challenging datasets.

Download Full-text

A Novel Detector Based on Convolution Neural Networks for Multiscale SAR Ship Detection in Complex Background

Sensors ◽

10.3390/s20092547 ◽

2020 ◽

Vol 20 (9) ◽

pp. 2547 ◽

Cited By ~ 2

Author(s):

Wenxin Dai ◽

Yuqing Mao ◽

Rongao Yuan ◽

Yijing Liu ◽

Xuemei Pu ◽

...

Keyword(s):

Region Of Interest ◽

Feature Representation ◽

Feature Maps ◽

Sar Images ◽

Feature Map ◽

The Public ◽

Single Feature ◽

Great Performance ◽

Residual Block ◽

Fusion Feature

Convolution neural network (CNN)-based detectors have shown great performance on ship detections of synthetic aperture radar (SAR) images. However, the performance of current models has not been satisfactory enough for detecting multiscale ships and small-size ones in front of complex backgrounds. To address the problem, we propose a novel SAR ship detector based on CNN, which consist of three subnetworks: the Fusion Feature Extractor Network (FFEN), Region Proposal Network (RPN), and Refine Detection Network (RDN). Instead of using a single feature map, we fuse feature maps in bottom–up and top–down ways and generate proposals from each fused feature map in FFEN. Furthermore, we further merge features generated by the region-of-interest (RoI) pooling layer in RDN. Based on the feature representation strategy, the CNN framework constructed can significantly enhance the location and semantics information for the multiscale ships, in particular for the small ships. On the other hand, the residual block is introduced to increase the network depth, through which the detection precision could be further improved. The public SAR ship dataset (SSDD) and China Gaofen-3 satellite SAR image are used to validate the proposed method. Our method shows excellent performance for detecting the multiscale and small-size ships with respect to some competitive models and exhibits high potential in practical application.

Download Full-text

3D Single-Person Concurrent Activity Detection Using Stacked Relation Network

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v34i07.6917 ◽

2020 ◽

Vol 34 (07) ◽

pp. 12329-12337

Author(s):

Yi Wei ◽

Wenbo Li ◽

Yanbo Fan ◽

Linghan Xu ◽

Ming-Ching Chang ◽

...

Keyword(s):

Real World ◽

State Of The Art ◽

Feature Representation ◽

Activity Detection ◽

Activity Class ◽

Single Person ◽

Class Level ◽

Public Dataset ◽

3D Skeleton ◽

Art Performance

We aim to detect real-world concurrent activities performed by a single person from a streaming 3D skeleton sequence. Different from most existing works that deal with concurrent activities performed by multiple persons that are seldom correlated, we focus on concurrent activities that are spatio-temporally or causally correlated and performed by a single person. For the sake of generalization, we propose an approach based on a decompositional design to learn a dedicated feature representation for each activity class. To address the scalability issue, we further extend the class-level decompositional design to the postural-primitive level, such that each class-wise representation does not need to be extracted by independent backbones, but through a dedicated weighted aggregation of a shared pool of postural primitives. There are multiple interdependent instances deriving from each decomposition. Thus, we propose Stacked Relation Networks (SRN), with a specialized relation network for each decomposition, so as to enhance the expressiveness of instance-wise representations via the inter-instance relationship modeling. SRN achieves state-of-the-art performance on a public dataset and a newly collected dataset. The relation weights within SRN are interpretable among the activity contexts. The new dataset and code are available at https://github.com/weiyi1991/UA_Concurrent/

Download Full-text

An Actor-Critic-Attention Mechanism for Deep Reinforcement Learning in Multi-view Environments

Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence ◽

10.24963/ijcai.2019/277 ◽

2019 ◽

Cited By ~ 1

Author(s):

Elaheh Barati ◽

Xuewen Chen

Keyword(s):

Reinforcement Learning ◽

State Of The Art ◽

Attention Mechanism ◽

Feature Representation ◽

Decision Making Process ◽

Multiple Views ◽

Single Feature ◽

3D Environments ◽

Noisy Conditions ◽

Level Of Importance

In reinforcement learning algorithms, leveraging multiple views of the environment can improve the learning of complicated policies. In multi-view environments, due to the fact that the views may frequently suffer from partial observability, their level of importance are often different. In this paper, we propose a deep reinforcement learning method and an attention mechanism in a multi-view environment. Each view can provide various representative information about the environment. Through our attention mechanism, our method generates a single feature representation of environment given its multiple views. It learns a policy to dynamically attend to each view based on its importance in the decision-making process. Through experiments, we show that our method outperforms its state-of-the-art baselines on TORCS racing car simulator and three other complex 3D environments with obstacles. We also provide experimental results to evaluate the performance of our method on noisy conditions and partial observation settings.

Download Full-text

Revisiting Image Aesthetic Assessment via Self-Supervised Feature Learning

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v34i04.6026 ◽

2020 ◽

Vol 34 (04) ◽

pp. 5709-5716 ◽

Cited By ~ 1

Author(s):

Kekai Sheng ◽

Weiming Dong ◽

Menglei Chai ◽

Guohui Wang ◽

Peng Zhou ◽

...

Keyword(s):

Close Relationships ◽

State Of The Art ◽

Feature Learning ◽

Research Field ◽

Feature Representation ◽

The Self ◽

Linear Classifier ◽

Benchmark Datasets ◽

Supervised Methods ◽

Active Research

Visual aesthetic assessment has been an active research field for decades. Although latest methods have achieved promising performance on benchmark datasets, they typically rely on a large number of manual annotations including both aesthetic labels and related image attributes. In this paper, we revisit the problem of image aesthetic assessment from the self-supervised feature learning perspective. Our motivation is that a suitable feature representation for image aesthetic assessment should be able to distinguish different expert-designed image manipulations, which have close relationships with negative aesthetic effects. To this end, we design two novel pretext tasks to identify the types and parameters of editing operations applied to synthetic instances. The features from our pretext tasks are then adapted for a one-layer linear classifier to evaluate the performance in terms of binary aesthetic classification. We conduct extensive quantitative experiments on three benchmark datasets and demonstrate that our approach can faithfully extract aesthetics-aware features and outperform alternative pretext schemes. Moreover, we achieve comparable results to state-of-the-art supervised methods that use 10 million labels from ImageNet.

Download Full-text

Simultaneous Image Reconstruction and Feature Learning with 3D-CNNs for Image Set–Based Classification

ACM/IMS Transactions on Data Science ◽

10.1145/3420037 ◽

2021 ◽

Vol 2 (2) ◽

pp. 1-13

Author(s):

Xinyu Zhang ◽

Xiaocui Li ◽

Xiao-Yuan Jing ◽

Li Cheng

Keyword(s):

Image Reconstruction ◽

State Of The Art ◽

Feature Learning ◽

Temporal Information ◽

Classification Methods ◽

Learning Network ◽

Image Set Classification ◽

Image Set ◽

Deep Image ◽

3D Cnn

Image set–based classification has attracted substantial research interest because of its broad applications. Recently, lots of methods based on feature learning or dictionary learning have been developed to solve this problem, and some of them have made gratifying achievements. However, most of them transform the image set into a 2D matrix or use 2D convolutional neural networks (CNNs) for feature learning, so the spatial and temporal information is missing. At the same time, these methods extract features from original images in which there may exist huge intra-class diversity. To explore a possible solution to these issues, we propose a simultaneous image reconstruction with deep learning and feature learning with 3D-CNNs (SIRFL) for image set classification. The proposed SIRFL approach consists of a deep image reconstruction network and a 3D-CNN-based feature learning network. The deep image reconstruction network is used to reduce the diversity of images from the same set, and the feature learning network can effectively retain spatial and temporal information by using 3D-CNNs. Extensive experimental results on five widely used datasets show that our SIRFL approach is a strong competitor for the state-of-the-art image set classification methods.

Download Full-text

Two-Branch Attention Learning for Fine-Grained Class Incremental Learning

Electronics ◽

10.3390/electronics10232987 ◽

2021 ◽

Vol 10 (23) ◽

pp. 2987

Author(s):

Jiaqi Guo ◽

Guanqiu Qi ◽

Shuiqing Xie ◽

Xiangyuan Li

Keyword(s):

Incremental Learning ◽

Network Architecture ◽

State Of The Art ◽

Research Area ◽

Feature Representation ◽

Learning Network ◽

Fine Grained ◽

Effective Training ◽

Critical Regions ◽

Number Of Classes

As a long-standing research area, class incremental learning (CIL) aims to effectively learn a unified classifier along with the growth of the number of classes. Due to the small inter-class variances and large intra-class variances, fine-grained visual categorization (FGVC) as a challenging visual task has not attracted enough attention in CIL. Therefore, the localization of critical regions specialized for fine-grained object recognition plays a crucial role in FGVC. Additionally, it is important to learn fine-grained features from critical regions in fine-grained CIL for the recognition of new object classes. This paper designs a network architecture named two-branch attention learning network (TBAL-Net) for fine-grained CIL. TBAL-Net can localize critical regions and learn fine-grained feature representation by a lightweight attention module. An effective training framework is proposed for fine-grained CIL by integrating TBAL-Net into an effective CIL process. This framework is tested on three popular fine-grained object datasets, including CUB-200-2011, FGVC-Aircraft, and Stanford-Car. The comparative experimental results demonstrate that the proposed framework can achieve the state-of-the-art performance on the three fine-grained object datasets.

Download Full-text

Integrating multi-network topology for gene function prediction using deep neural networks

10.1101/532408 ◽

2019 ◽

Author(s):

Hansheng Xue ◽

Jiajie Peng ◽

Xuequn Shang

Keyword(s):

Neural Network ◽

Gene Function ◽

State Of The Art ◽

Feature Learning ◽

Function Prediction ◽

Feature Representation ◽

Superior Performance ◽

Gene Function Prediction ◽

Multiple Networks ◽

Low Dimensional

AbstractMotivationThe emerging of abundant biological networks, which benefit from the development of advanced high-throughput techniques, contribute to describing and modeling complex internal interactions among biological entities such as genes and proteins. Multiple networks provide rich information for inferring the function of genes or proteins. To extract functional patterns of genes based on multiple heterogeneous networks, network embedding-based methods, aiming to capture non-linear and low-dimensional feature representation based on network biology, have recently achieved remarkable performance in gene function prediction. However, existing methods mainly do not consider the shared information among different networks during the feature learning process. Thus, we propose a novel multi-networks embedding-based function prediction method based on semi-supervised autoencoder and feature convolution neural network, named DeepMNE-CNN, which captures complex topological structures of multi-networks and takes the correlation among multi-networks into account.ResultsWe design a novel semi-supervised autoencoder method to integrate multiple networks and generate a low-dimensional feature representation. Then we utilize a convolutional neural network based on the integrated feature embedding to annotate unlabeled gene functions. We test our method on both yeast and human dataset and compare with four state-of-the-art methods. The results demonstrate the superior performance of our method over four state-of-the-art algorithms. From the future explorations, we find that semi-supervised autoencoder based multi-networks integration method and CNN-based feature learning methods both contribute to the task of function prediction.AvailabilityDeepMNE-CNN is freely available at https://github.com/xuehansheng/DeepMNE-CNN

Download Full-text

A Deep Feature Extraction Method for HEp-2 Cell Image Classification

Electronics ◽

10.3390/electronics8010020 ◽

2018 ◽

Vol 8 (1) ◽

pp. 20 ◽

Cited By ~ 7

Author(s):

Caleb Vununu ◽

Suk-Hwan Lee ◽

Ki-Ryong Kwon

Keyword(s):

Feature Extraction ◽

Deep Learning ◽

Extraction Method ◽

State Of The Art ◽

Feature Learning ◽

Cell Types ◽

Feature Representation ◽

Feature Extraction Method ◽

Cell Image ◽

Art Methods

The automated and accurate classification of the images portraying the Human Epithelial cells of type 2 (HEp-2) represents one of the most important steps in the diagnosis procedure of many autoimmune diseases. The extreme intra-class variations of the HEp-2 cell images datasets drastically complicates the classification task. We propose in this work a classification framework that, unlike most of the state-of-the-art methods, uses a deep learning-based feature extraction method in a strictly unsupervised way. We propose a deep learning-based hybrid feature learning with two levels of deep convolutional autoencoders. The first level takes the original cell images as the inputs and learns to reconstruct them, in order to capture the features related to the global shape of the cells, and the second network takes the gradients of the images, in order to encode the localized changes in intensity (gray variations) that characterize each cell type. A final feature vector is constructed by combining the latent representations extracted from the two networks, giving a highly discriminative feature representation. The created features will be fed to a nonlinear classifier whose output will represent the type of the cell image. We have tested the discriminability of the proposed features on two of the most popular HEp-2 cell classification datasets, the SNPHEp-2 and ICPR 2016 datasets. The results show that the proposed features manage to capture the distinctive characteristics of the different cell types while performing at least as well as the actual deep learning-based state-of-the-art methods in terms of discrimination.

Download Full-text

EXAM: A Framework of Learning Extreme and Moderate Embeddings for Person Re-ID

Journal of Imaging ◽

10.3390/jimaging7010006 ◽

2021 ◽

Vol 7 (1) ◽

pp. 6

Author(s):

Guanqiu Qi ◽

Gang Hu ◽

Xiaofei Wang ◽

Neal Mazur ◽

Zhiqin Zhu ◽

...

Keyword(s):

State Of The Art ◽

Feature Learning ◽

Feature Representation ◽

Cross Entropy ◽

Loss Functions ◽

Entropy Loss ◽

Max Pooling ◽

Discriminative Feature ◽

Bounding Boxes ◽

New Framework

Person re-identification (Re-ID) is challenging due to host of factors: the variety of human positions, difficulties in aligning bounding boxes, and complex backgrounds, among other factors. This paper proposes a new framework called EXAM (EXtreme And Moderate feature embeddings) for Re-ID tasks. This is done using discriminative feature learning, requiring attention-based guidance during training. Here “Extreme” refers to salient human features and “Moderate” refers to common human features. In this framework, these types of embeddings are calculated by global max-pooling and average-pooling operations respectively; and then, jointly supervised by multiple triplet and cross-entropy loss functions. The processes of deducing attention from learned embeddings and discriminative feature learning are incorporated, and benefit from each other in this end-to-end framework. From the comparative experiments and ablation studies, it is shown that the proposed EXAM is effective, and its learned feature representation reaches state-of-the-art performance.

Download Full-text

Health Care

10.1093/oso/9780198817055.003.0011 ◽

2018 ◽

Author(s):

Pierre Pestieau ◽

Mathieu Lefebvre

Keyword(s):

Health Care ◽

Technological Progress ◽

Health Care Systems ◽

Third Party ◽

Medical Expenditure ◽

Public Health Care ◽

The Public ◽

Common Features ◽

Care Systems

This chapter reviews the public health care systems as well as their challenges. It first shows how expenditure on health care has evolved in previous decades and deals with the reasons for the growth observed in almost every European country. It emphasizes the role of technological progress as a main explanatory factor of the increase in medical expenditure but also points to the challenges facing cost-containment policies. Especially, the main common features of health care systems in Europe, such as third-party payment, single provider approach and cost-based reimbursement are discussed. Finally the chapter shows that although inequalities in health exist in the population, health care systems are redistributive. Reforms are thus needed but the trade-off between budgetary efficiency and equity is difficult.

Download Full-text