Learning Unified Embedding for Apparel Recognition

TL;DR

This paper proposes a unified embedding model for apparel recognition that matches the accuracy of multiple specialized models while reducing complexity, by optimizing training data selection and introducing a novel learning scheme using specialized model outputs as targets.

Contribution

It introduces a new training scheme using specialized model outputs as targets, enabling effective unified apparel recognition models without sacrificing accuracy.

Findings

Unified model achieves same accuracy as multiple specialized models

New loss function simplifies training and improves feature space utilization

Approach reduces model complexity and deployment costs

Abstract

In apparel recognition, specialized models (e.g. models trained for a particular vertical like dresses) can significantly outperform general models (i.e. models that cover a wide range of verticals). Therefore, deep neural network models are often trained separately for different verticals. However, using specialized models for different verticals is not scalable and expensive to deploy. This paper addresses the problem of learning one unified embedding model for multiple object verticals (e.g. all apparel classes) without sacrificing accuracy. The problem is tackled from two aspects: training data and training difficulty. On the training data aspect, we figure out that for a single model trained with triplet loss, there is an accuracy sweet spot in terms of how many verticals are trained together. To ease the training difficulty, a novel learning scheme is proposed by using the output from specialized models as learning targets so that L2 loss can be used instead of triplet loss. This new loss makes the training easier and make it possible for more efficient use of the feature space. The end result is a unified model which can achieve the same retrieval accuracy as a number of separate specialized models, while having the model complexity as one. The effectiveness of our approach is shown in experiments.