Semi-supervised Learning with a Teacher-student Network for Generalized Attribute Prediction

Abstract

This paper presents a study on semi-supervised learning to solve the visual attribute prediction problem. In many applications of vision algorithms, the precise recognition of visual attributes of objects is important but still challenging. This is because defining a class hierarchy of attributes is ambiguous, so training data inevitably suffer from class imbalance and label sparsity, leading to a lack of effective annotations. An intuitive solution is to find a method to effectively learn image representations by utilizing unlabeled images. With that in mind, we propose a multi-teacher-single-student (MTSS) approach inspired by the multi-task learning and the distillation of semi-supervised learning. Our MTSS learns task-specific domain experts called teacher networks using the label embedding technique and learns a unified model called a student network by forcing a model to mimic the distributions learned by domain experts. Our experiments demonstrate that our method not only achieves competitive performance on various benchmarks for fashion attribute prediction, but also improves robustness and cross-domain adaptability for unseen domains.

arXiv comment14 pages, Accepted to ECCV 2020

References in corpus (9)

• Prototypical Networks for Few-shot Learning
• Label-Embedding for Image Classification
• Meta-Learning for Semi-Supervised Few-Shot Classification
• Billion-scale semi-supervised learning for image classification
• Self-training with Noisy Student improves ImageNet classification
• Leveraging Weakly Annotated Data for Fashion Image Retrieval and Label Prediction
• Unsupervised Meta-Learning For Few-Shot Image Classification
• Progressive Fashion Attribute Extraction
• The iMaterialist Fashion Attribute Dataset