Date

2018-12-01

Author

Solmaz, Berkan
Gundogdu, Erhan
Yucesoy, Veysel
Koc, Aykut
Alatan, Abdullah Aydın

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

205
views

0
downloads

Cite This

Recent advances in large-scale image and video analysis have empowered the potential capabilities of visual surveillance systems. In particular, deep learning-based approaches bring in substantial benefits in solving certain computer vision problems such as fine-grained object recognition. Here, the authors mainly concentrate on classification and identification of maritime vessels and land vehicles, which are the key constituents of visual surveillance systems. Employing publicly available data sets for maritime vessels and land vehicles, the authors aim to improve visual recognition. Specifically, the authors focus on five tasks regarding visual recognition; coarse-grained classification, fine-grained classification, coarse-grained retrieval, fine-grained retrieval, and verification. To increase the performance in these tasks, the authors utilise a multi-task learning framework and present a novel loss function which simultaneously considers deep feature learning and classification by exploiting the available hierarchical labels of individual samples and the global statistics of distances between the data pairs. The authors observe that the proposed multi-task learning model improves the fine-grained recognition performance on MARVEL and Stanford Cars data sets, compared to training of a model targeting a single recognition task.

Subject Keywords

Marine vehicles, Stanford Cars data set, MARVEL data set, Data pairs, Hierarchical individual sample label, Global statistics, Loss function, Multitask learning framework, Verification task, Fine-grained retrieval task, Coarse-grained retrieval task, Fine-grained classification task, Coarse-grained classification task, Visual recognition, Land vehicle identification, Maritime vessel identification, Fine-grained object recognition, Computer vision problems, Deep learning-based approaches, Visual surveillance systems, Large-scale video analysis, Large-scale image analysis, Deep feature embedding, Fine-grained land vehicle recognition, Fine-grained maritime vessel recognition, Video retrieval, Traffic engineering computing, Statistical analysis, Learning (artificial intelligence), Object recognition, Image classification

URI

https://hdl.handle.net/11511/37334

Collections

Department of Electrical and Electronics Engineering, Article