Leveraging Weakly Annotated Data for Fashion Image Retrieval and Label Prediction
This work addresses the challenge of reducing labeling costs for fashion image analysis, though it is incremental as it builds on existing weakly supervised methods.
The paper tackles the problem of learning visual representations for e-commerce products using weakly supervised learning from noisy, unlabeled datasets crawled from websites, eliminating the need for manual labeling. It achieves nearly state-of-the-art results on DeepFashion benchmarks for image retrieval and category prediction without using the provided training data.
In this paper, we present a method to learn a visual representation adapted for e-commerce products. Based on weakly supervised learning, our model learns from noisy datasets crawled on e-commerce website catalogs and does not require any manual labeling. We show that our representation can be used for downward classification tasks over clothing categories with different levels of granularity. We also demonstrate that the learnt representation is suitable for image retrieval. We achieve nearly state-of-art results on the DeepFashion In-Shop Clothes Retrieval and Categories Attributes Prediction tasks, without using the provided training set.