University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Deep Spatial-Semantic Attention for Fine-Grained Sketch-Based Image Retrieval

Song, J., Yu, Q., Song, Yi-Zhe, Xiang, T. and Hospedales, T.M. (2018) Deep Spatial-Semantic Attention for Fine-Grained Sketch-Based Image Retrieval In: 2017 IEEE International Conference on Computer Vision (ICCV), 22-29 Oct 2017, Venice, Italy.

Full text not available from this repository.


Human sketches are unique in being able to capture both the spatial topology of a visual object, as well as its subtle appearance details. Fine-grained sketch-based image retrieval (FG-SBIR) importantly leverages on such fine-grained characteristics of sketches to conduct instance-level retrieval of photos. Nevertheless, human sketches are often highly abstract and iconic, resulting in severe misalignments with candidate photos which in turn make subtle visual detail matching difficult. Existing FG-SBIR approaches focus only on coarse holistic matching via deep cross-domain representation learning, yet ignore explicitly accounting for fine-grained details and their spatial context. In this paper, a novel deep FG-SBIR model is proposed which differs significantly from the existing models in that: (1) It is spatially aware, achieved by introducing an attention module that is sensitive to the spatial position of visual details: (2) It combines coarse and fine semantic information via a shortcut connection fusion block: and (3) It models feature correlation and is robust to misalignments between the extracted features across the two domains by introducing a novel higher-order learnable energy function (HOLEF) based loss. Extensive experiments show that the proposed deep spatial-semantic attention model significantly outperforms the state-of-the-art.

Item Type: Conference or Workshop Item (Conference Paper)
Divisions : Faculty of Engineering and Physical Sciences > Electronic Engineering
Authors :
Song, J.
Yu, Q.
Xiang, T.
Hospedales, T.M.
Date : February 2018
DOI : 10.1109/ICCV.2017.592
Uncontrolled Keywords : Computational modeling; Feature extraction; Robustness; Computer architecture; Visualization; Semantics; Image retrieval
Related URLs :
Additional Information : Printed proceedings published by Curran Associates Inc.,
Depositing User : Clive Harris
Date Deposited : 11 Jul 2019 08:57
Last Modified : 11 Jul 2019 08:57

Actions (login required)

View Item View Item


Downloads per month over past year

Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800