Garment Attribute Manipulation with Multi-level Attention
This addresses the need for personalized and interactive image retrieval in online fashion shopping, though it appears incremental as it builds on existing attribute manipulation methods.
The paper tackles the problem of precisely manipulating specific garment attributes in fashion images without affecting others, proposing GAMMA, which achieves state-of-the-art performance on datasets like Shopping100k and DeepFashion.
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.