Sketch-QNet: A Quadruplet ConvNet for Color Sketch-based Image Retrieval

Architectures based on siamese networks with triplet loss have shown outstanding performance on the image-based similarity search problem. This approach attempts to discriminate between positive (relevant) and negative (irrelevant) items. However, it undergoes a critical weakness. Given a query, it...

Full description

Saved in:
Bibliographic Details
Main Authors: Fuentes, Anibal, Saavedra, Jose M.
Format: Conference Proceeding
Language:English
Subjects:
Computer architecture
Computer vision
Conferences
Image color analysis
Image retrieval
Training
Visualization
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Architectures based on siamese networks with triplet loss have shown outstanding performance on the image-based similarity search problem. This approach attempts to discriminate between positive (relevant) and negative (irrelevant) items. However, it undergoes a critical weakness. Given a query, it cannot discriminate weakly relevant items, for instance, items of the same type but different color or texture as the given query, which could be a serious limitation for many real-world search applications. Therefore, in this work, we present a quadruplet-based architecture that overcomes the aforementioned weakness. Moreover, we present an instance of this quadruplet network, which we call Sketch-QNet, to deal with the color sketch-based image retrieval (CSBIR) problem, achieving new state-of- the-art results.
ISSN:2160-7516
DOI:10.1109/CVPRW53098.2021.00242