FashionFail: Addressing Failure Cases in Fashion Object Detection and Segmentation
This work addresses robustness issues in fashion parsing for industrial applications, but it is incremental as it focuses on dataset creation and baseline improvements.
The paper tackles the problem of failure cases in fashion object detection and segmentation for online shopping images by introducing the FashionFail dataset, which reveals shortcomings in leading models and proposes a baseline approach using naive data augmentation to improve robustness.
In the realm of fashion object detection and segmentation for online shopping images, existing state-of-the-art fashion parsing models encounter limitations, particularly when exposed to non-model-worn apparel and close-up shots. To address these failures, we introduce FashionFail; a new fashion dataset with e-commerce images for object detection and segmentation. The dataset is efficiently curated using our novel annotation tool that leverages recent foundation models. The primary objective of FashionFail is to serve as a test bed for evaluating the robustness of models. Our analysis reveals the shortcomings of leading models, such as Attribute-Mask R-CNN and Fashionformer. Additionally, we propose a baseline approach using naive data augmentation to mitigate common failure cases and improve model robustness. Through this work, we aim to inspire and support further research in fashion item detection and segmentation for industrial applications. The dataset, annotation tool, code, and models are available at \url{https://rizavelioglu.github.io/fashionfail/}.