Joint Learning of Dictionary and Convolutional Network for Pedestrian Attribute Recognition

In this paper, we propose a new end-to-end network, named Joint Learning of Attribute and Contextual relations (JLAC), to solve the task of pedestrian attribute recognition. It includes two novel modules: Attribute Relation Module (ARM) and Contextual Relation Module (CRM). For ARM, we construct an attribute graph with attribute-specific features which are learned by the constrained losses, and further use Graph Convolutional Network (GCN) to explore the correlations among multiple attributes. For CRM, we first propose a graph projection scheme to project the 2-D feature map into a set of nodes from different image regions, and then employ GCN to explore the contextual relations among those regions. Since the relation information in the above two modules is correlated and complementary, we incorporate them into a unified framework to learn both together. Experiments on three benchmarks, including PA-100K, RAP, PETA attribute datasets, demonstrate the effectiveness of the proposed JLAC.

Download Full-text

Correlation Graph Convolutional Network for Pedestrian Attribute Recognition

IEEE Transactions on Multimedia ◽

10.1109/tmm.2020.3045286 ◽

2020 ◽

pp. 1-1

Author(s):

Haonan Fan ◽

Hai-Miao Hu ◽

Shuailing Liu ◽

Weiqing Lu ◽

Shiliang Pu

Keyword(s):

Convolutional Network ◽

Correlation Graph ◽

Attribute Recognition

Download Full-text

Visual-Semantic Graph Reasoning for Pedestrian Attribute Recognition

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v33i01.33018634 ◽

2019 ◽

Vol 33 ◽

pp. 8634-8641 ◽

Cited By ~ 4

Author(s):

Qiaozhe Li ◽

Xin Zhao ◽

Ran He ◽

Kaiqi Huang

Keyword(s):

Large Scale ◽

State Of The Art ◽

Relational Learning ◽

Spatial Relations ◽

Semantic Relations ◽

Prediction Problem ◽

Convolutional Network ◽

Semantic Graph ◽

Spatial Graph ◽

Attribute Recognition

Pedestrian attribute recognition in surveillance is a challenging task due to poor image quality, significant appearance variations and diverse spatial distribution of different attributes. This paper treats pedestrian attribute recognition as a sequential attribute prediction problem and proposes a novel visual-semantic graph reasoning framework to address this problem. Our framework contains a spatial graph and a directed semantic graph. By performing reasoning using the Graph Convolutional Network (GCN), one graph captures spatial relations between regions and the other learns potential semantic relations between attributes. An end-to-end architecture is presented to perform mutual embedding between these two graphs to guide the relational learning for each other. We verify the proposed framework on three large scale pedestrian attribute datasets including PETA, RAP, and PA100k. Experiments show superiority of the proposed method over state-of-the-art methods and effectiveness of our joint GCN structures for sequential attribute prediction.

Download Full-text

Joint Learning for Spatial Context-based Seismic Inversion of Multiple Datasets for Improved Generalizability and Robustness

Geophysics ◽

10.1190/geo2020-0432.1 ◽

2021 ◽

pp. 1-50

Author(s):

Ahmad Mustafa ◽

Motaz Alfarraj ◽

Ghassan AlRegib

Keyword(s):

Machine Learning ◽

Seismic Data ◽

Seismic Inversion ◽

Spatial Context ◽

Reservoir Properties ◽

Convolutional Network ◽

Joint Learning ◽

Multiple Datasets ◽

Spatial Consistency ◽

Seismic Volumes

Seismic inversion plays a very useful role in detailed stratigraphic interpretation of migrated seismic volumes by enabling the estimation of reservoir properties over the complete volume. Traditional and machine learning-based seismic inversion workflows are limited to inverting each seismic trace independently of other traces to estimate impedance profiles, leading to lateral discontinuities in the presence of noise and large geological variations in the seismic data. In addition, machine learning-based approaches suffer the problem of overfitting if there is only a small number of wells on which the model is trained. We propose a two-pronged strategy to overcome these problems. We present a temporal convolutional network that models seismic traces temporally. We further inject spatial context for each trace into its estimations of the impedance profile. To counter the problem of limited labeled data, we also present a joint learning scheme whereby multiple datasets are simultaneously used for training, sharing beneficial information among each other. This results in the improvement in generalization performance on all datasets. We present a case study of acoustic impedance inversion using the open-source SEAM and Marmousi 2 datasets. Our evaluations show that our proposed approach is able to estimate impedance in the presence of noisy seismic data and a limited number of well logs with greater robustness and spatial consistency. We compare and contrast our approach to other learning-based seismic inversion methodologies in the literature. On SEAM, we are able to obtain an average MSE of 0.0476, the lowest among all other methodologies.

Download Full-text

Pedestrian Attribute Recognition with Graph Convolutional Network in Surveillance Scenarios

Future Internet ◽

10.3390/fi11110245 ◽

2019 ◽

Vol 11 (11) ◽

pp. 245 ◽

Cited By ~ 2

Author(s):

Xiangpeng Song ◽

Hongbin Yang ◽

Congcong Zhou

Keyword(s):

Neural Network ◽

Spatial Distribution ◽

Correlation Matrix ◽

State Of The Art ◽

Recognition Performance ◽

Image Representation ◽

Normal Operation ◽

Convolutional Network ◽

Attribute Recognition ◽

Novel Model

Pedestrian attribute recognition is to predict a set of attribute labels of the pedestrian from surveillance scenarios, which is a very challenging task for computer vision due to poor image quality, continual appearance variations, as well as diverse spatial distribution of imbalanced attributes. It is desirable to model the label dependencies between different attributes to improve the recognition performance as each pedestrian normally possesses many attributes. In this paper, we treat pedestrian attribute recognition as multi-label classification and propose a novel model based on the graph convolutional network (GCN). The model is mainly divided into two parts, we first use convolutional neural network (CNN) to extract pedestrian feature, which is a normal operation processing image in deep learning, then we transfer attribute labels to word embedding and construct a correlation matrix between labels to help GCN propagate information between nodes. This paper applies the object classifiers learned by GCN to the image representation extracted by CNN to enable the model to have the ability to be end-to-end trainable. Experiments on pedestrian attribute recognition dataset show that the approach obviously outperforms other existing state-of-the-art methods.

Download Full-text