Data Efficient Training with Imbalanced Label Sample Distribution for Fashion Detection

TL;DR

This paper introduces a weighted loss function to improve multi-label fashion attribute classification in imbalanced datasets, demonstrating enhanced performance over existing methods in real-world e-commerce scenarios.

Contribution

It proposes a novel weighted objective function tailored for deep neural networks to handle long-tailed data distributions in fashion attribute detection.

Findings

Weighted loss improves classification accuracy

Outperforms inverse-frequency weighting methods

Effective across different fashion attribute types

Abstract

Multi-label classification models have a wide range of applications in E-commerce, including visual-based label predictions and language-based sentiment classifications. A major challenge in achieving satisfactory performance for these tasks in the real world is the notable imbalance in data distribution. For instance, in fashion attribute detection, there may be only six 'puff sleeve' clothes among 1000 products in most E-commerce fashion catalogs. To address this issue, we explore more data-efficient model training techniques rather than acquiring a huge amount of annotations to collect sufficient samples, which is neither economic nor scalable. In this paper, we propose a state-of-the-art weighted objective function to boost the performance of deep neural networks (DNNs) for multi-label classification with long-tailed data distribution. Our experiments involve image-based attribute classification of fashion apparels, and the results demonstrate favorable performance for the new weighting method compared to non-weighted and inverse-frequency-based weighting mechanisms. We further evaluate the robustness of the new weighting mechanism using two popular fashion attribute types in today's fashion industry: sleevetype and archetype.