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

TL;DR

Sketch-QNet introduces a quadruplet convolutional network that improves color sketch-based image retrieval by better discriminating weakly relevant items, achieving state-of-the-art results in the field.

Contribution

The paper proposes a novel quadruplet network architecture, Sketch-QNet, specifically designed for color sketch-based image retrieval, addressing limitations of triplet-based methods.

Findings

Achieves state-of-the-art performance on CSBIR tasks.

Effectively discriminates weakly relevant items in image retrieval.

Outperforms existing triplet-based architectures.

Abstract

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.