Garment Attribute Manipulation with Multi-level Attention

TL;DR

GAMMA is a novel framework that enables precise manipulation of garment attributes in fashion images using multi-level attention, improving interactive image retrieval accuracy.

Contribution

The paper introduces GAMMA, combining attribute-disentangled representations with multi-stage attention for targeted garment attribute editing.

Findings

Achieves state-of-the-art results on Shopping100k and DeepFashion datasets.

Enables precise, targeted manipulation of garment attributes.

Improves interactive fashion image retrieval accuracy.

Abstract

In the rapidly evolving field of online fashion shopping, the need for more personalized and interactive image retrieval systems has become paramount. Existing methods often struggle with precisely manipulating specific garment attributes without inadvertently affecting others. To address this challenge, we propose GAMMA (Garment Attribute Manipulation with Multi-level Attention), a novel framework that integrates attribute-disentangled representations with a multi-stage attention-based architecture. GAMMA enables targeted manipulation of fashion image attributes, allowing users to refine their searches with high accuracy. By leveraging a dual-encoder Transformer and memory block, our model achieves state-of-the-art performance on popular datasets like Shopping100k and DeepFashion.