SceneSketcher-v2: Fine-grained scene-level sketch-based image retrieval using adaptive GCNs

Liu, Fang, Deng, Xiaoming, Zou, Changqing, Lai, Yu-Kun ORCID: https://orcid.org/0000-0002-2094-5680, Chen, Keqi, Zuo, Ran, Ma, Cuixia, Liu, Yong-Jin and Wang, Hongan 2022. SceneSketcher-v2: Fine-grained scene-level sketch-based image retrieval using adaptive GCNs. IEEE Transactions on Image Processing 31 , pp. 3737-3751. 10.1109/TIP.2022.3175403

Preview

PDF - Accepted Post-Print Version Download (19MB) | Preview

Abstract

Sketch-based image retrieval (SBIR) is a long-standing research topic in computer vision. Existing methods mainly focus on category-level or instance-level image retrieval. This paper investigates the fine-grained scene-level SBIR problem where a free-hand sketch depicting a scene is used to retrieve desired images. This problem is useful yet challenging mainly because of two entangled facts: 1) achieving an effective representation of the input query data and scene-level images is difficult as it requires to model the information across multiple modalities such as object layout, relative size and visual appearances, and 2) there is a great domain gap between the query sketch input and target images. We present SceneSketcher-v2, a Graph Convolutional Network (GCN) based architecture to address these challenges. SceneSketcher-v2 employs a carefully designed graph convolution network to fuse the multi-modality information in the query sketch and target images and uses a triplet training process and end-to-end training manner to alleviate the domain gap. Extensive experiments demonstrate SceneSketcher-v2 outperforms state-of-the-art scene-level SBIR models with a significant margin.

Item Type:	Article
Date Type:	Publication
Status:	Published
Schools:	Computer Science & Informatics
Publisher:	Institute of Electrical and Electronics Engineers
ISSN:	1057-7149
Date of First Compliant Deposit:	14 June 2022
Date of Acceptance:	29 April 2022
Last Modified:	26 Nov 2024 02:15
URI:	https://orca.cardiff.ac.uk/id/eprint/150486

Actions (repository staff only)

Edit Item