Sketch Less for More: On-the-Fly Fine-Grained Sketch Based Image Retrieval

Song, Yi-Zhe (2020) Sketch Less for More: On-the-Fly Fine-Grained Sketch Based Image Retrieval In: CVPR 2020, 2020-06-14-2020-06-19.

Text On_the_Fly_CVPR_2020.pdf - Accepted version Manuscript Restricted to Repository staff only Download (3MB)

Abstract

Fine-grained sketch-based image retrieval (FG-SBIR) addresses the problem of retrieving a particular photo instance given a user’s query sketch. Its widespread applicability is however hindered by the fact that drawing a sketch takes time, and most people struggle to draw a complete and faithful sketch. In this paper, we reformulate the conventional FG-SBIR framework to tackle these challenges, with the ultimate goal of retrieving the target photo with the least number of strokes possible. We further propose an on-the-fly design that starts retrieving as soon as the user starts drawing. To accomplish this, we devise a reinforcement learning based cross-modal retrieval framework that directly optimizes rank of the ground-truth photo over a complete sketch drawing episode. Additionally, we introduce a novel reward scheme that circumvents the problems related to irrelevant sketch strokes, and thus provides us with a more consistent rank list during the retrieval. We achievesuperiorearly-retrievalefficiencyoverstate-of-theartmethodsandalternativebaselinesontwopubliclyavailable fine-grained sketch retrieval datasets.

Item Type:	Conference or Workshop Item (Conference Paper)
Divisions :	Faculty of Engineering and Physical Sciences > Electronic Engineering
Authors :	Name Email ORCID Song, Yi-Zhe y.song@surrey.ac.uk
Date :	27 February 2020
Related URLs :	Organisation Publisher
Depositing User :	Diane Maxfield
Date Deposited :	07 Oct 2020 17:23
Last Modified :	07 Oct 2020 17:23
URI:	http://epubs.surrey.ac.uk/id/eprint/858717

Actions (login required)

View Item

Downloads