A Balanced Triplet Loss for Person Re-Identification
- 28 January 2023
- journal article
- research article
- Published by World Scientific Pub Co Pte Ltd in International Journal of Pattern Recognition and Artificial Intelligence
- Vol. 37 (01)
Abstract
Compared to cross-entropy in deep learning, triplet loss is less affected by the biased label information and widely used in fine-grained visual tasks. Especially in person re-identification (re-ID), triplet loss is improved with batch-hard sampling which only selects the hardest samples during the training process to reduce invalid triplets involved in the loss computation. The hardest samples’ loss computation can provide a more intense gradient descent than raw samples. However, the batch-hard triplet loss discards multiple samples with important information, which can negatively impact feature learning. Besides, the hardest samples cause loss stuck problems frequently in training. In this work, we propose a balanced triplet loss for comprehensive feature learning and stable model convergence. The balanced triplet loss only mines the hardest negative samples of each category within a mini-batch. Compared with batch-hard triplet loss, it preserves the features of all the negative categories rather than one negative category with the hardest negative sample. It achieves a balance between triplet selection and information loss. The experiments show that our method can produce competitive results in re-ID tasks. In addition, we analyze the correlation between the intensity of data mining and the granularity of feature learning and further adapt the balanced triplet loss to general fine-grained image classification. The experiments prove the adapted balanced triplet loss also outperforms cross-entropy in multiple datasets of different scales.Keywords
Funding Information
- The National Key R&D Program of China (2017YFE0111900, 2018YFB1003205)
This publication has 14 references indexed in Scilit:
- Deep Fusion Feature Representation Learning With Hard Mining Center-Triplet Loss for Person Re-IdentificationIEEE Transactions on Multimedia, 2020
- Compact Triplet Loss for person re-identification in camera sensor networksAd Hoc Networks, 2019
- Pose-Invariant Embedding for Deep Person Re-IdentificationIEEE Transactions on Image Processing, 2019
- A Survey of Open-World Person Re-IdentificationIEEE Transactions on Circuits and Systems for Video Technology, 2019
- Beyond Part Models: Person Retrieval with Refined Part Pooling (and A Strong Convolutional Baseline)2018
- End-to-End Learning of Deep Visual Representations for Image RetrievalInternational Journal of Computer Vision, 2017
- FaceNet: A unified embedding for face recognition and clustering2015
- Automated Flower Classification over a Large Number of Classes2008
- On Information and SufficiencyThe Annals of Mathematical Statistics, 1951
- A Mathematical Theory of CommunicationBell System Technical Journal, 1948