Boosting Standard Classification Architectures Through a Ranking Regularizer

Ahmed Taha, Yi-Ting Chen, Teruhisa Misu, Abhinav Shrivastava, Larry Davis; Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2020, pp. 758-766

Abstract


We employ triplet loss as a feature embedding regularizer to boost classification performance. Standard architectures, like ResNet and Inception, are extended to support both losses with minimal hyper-parameter tuning. This promotes generality while fine-tuning pretrained networks. Triplet loss is a powerful surrogate for recently proposed embedding regularizers. Yet, it is avoided due to large batch-size requirement and high computational cost. Through our experiments, we re-assess these assumptions. During inference, our network supports both classification and embedding tasks without any computational overhead. Quantitative evaluation highlights a steady improvement on five fine-grained recognition datasets. Further evaluation on an imbalanced video dataset achieves significant improvement. Triplet loss brings feature embedding capabilities like nearest neighbor to classification models. Code available at http://bit.ly/2LNYEqL

Related Material


[pdf]
[bibtex]
@InProceedings{Taha_2020_WACV,
author = {Taha, Ahmed and Chen, Yi-Ting and Misu, Teruhisa and Shrivastava, Abhinav and Davis, Larry},
title = {Boosting Standard Classification Architectures Through a Ranking Regularizer},
booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)},
month = {March},
year = {2020}
}