A Strong Baseline for Fashion Retrieval with Person Re-Identification Models
This work provides a strong baseline for fashion retrieval, which is important for e-commerce and fashion industries, though it is incremental as it adapts existing models to a new task.
The paper tackled the problem of fashion retrieval by adapting person re-identification models to address challenges like fine-grained differences and domain gaps between street and catalogue photos, resulting in a simple baseline model that significantly outperformed previous state-of-the-art results on Street2Shop and DeepFashion datasets.
Fashion retrieval is the challenging task of finding an exact match for fashion items contained within an image. Difficulties arise from the fine-grained nature of clothing items, very large intra-class and inter-class variance. Additionally, query and source images for the task usually come from different domains - street photos and catalogue photos respectively. Due to these differences, a significant gap in quality, lighting, contrast, background clutter and item presentation exists between domains. As a result, fashion retrieval is an active field of research both in academia and the industry. Inspired by recent advancements in Person Re-Identification research, we adapt leading ReID models to be used in fashion retrieval tasks. We introduce a simple baseline model for fashion retrieval, significantly outperforming previous state-of-the-art results despite a much simpler architecture. We conduct in-depth experiments on Street2Shop and DeepFashion datasets and validate our results. Finally, we propose a cross-domain (cross-dataset) evaluation method to test the robustness of fashion retrieval models.