Cross-domain Generative Learning for Fine-Grained Sketch-Based Image Retrieval

Kaiyue Pang, Yi-zhe Song, Tony Xiang and Timothy Hospedales

Abstract

The key challenge for learning a fine-grained sketch-based image retrieval (FG-SBIR) model is to bridge the domain gap between photo and sketch. Existing models learn a deep joint embedding space with discriminative losses where a photo and a sketch can be compared. In this paper, we propose a novel discriminative-generative hybrid model by introducing a generative task of cross-domain image synthesis. This task enforces the learned embedding space to preserve all the domain invariant information that is useful for cross-domain reconstruction, thus explicitly reducing the domain gap as opposed to existing models.

Session

Posters

Files

PDF iconPaper (PDF)

DOI

10.5244/C.31.46
https://dx.doi.org/10.5244/C.31.46

Citation

Kaiyue Pang, Yi-zhe Song, Tony Xiang and Timothy Hospedales. Cross-domain Generative Learning for Fine-Grained Sketch-Based Image Retrieval. In T.K. Kim, S. Zafeiriou, G. Brostow and K. Mikolajczyk, editors, Proceedings of the British Machine Vision Conference (BMVC), pages 46.1-46.12. BMVA Press, September 2017.

Bibtex

            @inproceedings{BMVC2017_46,
                title={Cross-domain Generative Learning for Fine-Grained Sketch-Based Image Retrieval},
                author={Kaiyue Pang, Yi-zhe Song, Tony Xiang and Timothy Hospedales},
                year={2017},
                month={September},
                pages={46.1-46.12},
                articleno={46},
                numpages={12},
                booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
                publisher={BMVA Press},
                editor={Tae-Kyun Kim, Stefanos Zafeiriou, Gabriel Brostow and Krystian Mikolajczyk},
                doi={10.5244/C.31.46},
                isbn={1-901725-60-X},
                url={https://dx.doi.org/10.5244/C.31.46}
            }