Abstract
Visual similarity discovery (VSD) is an important task with broad e-commerce applications. Given an image of a certain object, the goal of VSD is to retrieve images of different objects with high perceptual visual similarity. Although being a highly addressed problem, the evaluation of proposed methods for VSD is often based on a proxy of an identification-retrieval task, evaluating the ability of a model to retrieve different images of the same object. We posit that evaluating VSD methods based on identification tasks is limited, and faithful evaluation must rely on expert annotations. In this paper, we introduce the first large-scale fashion visual similarity benchmark dataset, consisting of more than 110K expert-annotated image pairs. Besides this major contribution, we share insight from the challenges we faced while curating this dataset. Based on these insights, we propose a novel and efficient labeling procedure that can be applied to any dataset. Our analysis examines its limitations and inductive biases, and based on these findings, we propose metrics to mitigate those limitations. Though our primary focus lies on visual similarity, the methodologies we present have broader applications for discovering and evaluating perceptual similarity across various domains.
Original language | English |
---|---|
Title of host publication | Proceedings - 2023 IEEE/CVF International Conference on Computer Vision, ICCV 2023 |
Publisher | Institute of Electrical and Electronics Engineers Inc. |
Pages | 19950-19961 |
Number of pages | 12 |
ISBN (Electronic) | 9798350307184 |
DOIs | |
State | Published - 2023 |
Externally published | Yes |
Event | 2023 IEEE/CVF International Conference on Computer Vision, ICCV 2023 - Paris, France Duration: 2 Oct 2023 → 6 Oct 2023 |
Publication series
Name | Proceedings of the IEEE International Conference on Computer Vision |
---|---|
ISSN (Print) | 1550-5499 |
Conference
Conference | 2023 IEEE/CVF International Conference on Computer Vision, ICCV 2023 |
---|---|
Country/Territory | France |
City | Paris |
Period | 2/10/23 → 6/10/23 |
Bibliographical note
Publisher Copyright:© 2023 IEEE.