Hybrid Style Siamese Network: Incorporating style loss in complementary apparels retrieval

TL;DR

This paper introduces a hybrid Siamese network that incorporates style loss to improve the retrieval of visually compatible fashion items, addressing the limitations of traditional Siamese networks in capturing low-level style features.

Contribution

It proposes a novel hybrid loss and network architecture that effectively captures low-level style features for better complementary apparel retrieval.

Findings

Outperforms traditional Siamese networks in retrieval accuracy.

Effectively captures low-level style features using style transfer techniques.

Demonstrates improved compatibility detection in fashion item retrieval.

Abstract

Image Retrieval grows to be an integral part of fashion e-commerce ecosystem as it keeps expanding in multitudes. Other than the retrieval of visually similar items, the retrieval of visually compatible or complementary items is also an important aspect of it. Normal Siamese Networks tend to work well on complementary items retrieval. But it fails to identify low level style features which make items compatible in human eyes. These low level style features are captured to a large extent in techniques used in neural style transfer. This paper proposes a mechanism of utilising those methods in this retrieval task and capturing the low level style features through a hybrid siamese network coupled with a hybrid loss. The experimental results indicate that the proposed method outperforms traditional siamese networks in retrieval tasks for complementary items.