Dual Cross-Entropy Loss for Small-Sample Fine-Grained Vehicle Classification
- 28 January 2019
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 68 (5) , 4204-4212
Abstract
Fine-grained vehicle classification is a challenging topic in computer vision due to the high intraclass variance and low interclass variance. Recently, considerable progress has been made in fine-grained vehicle classification due to the huge success of deep neural networks. Most studies of fine-grained vehicle classification based on neural networks, focus on the neural network structure to improve the classification performance. In contrast to existing works on fine-grained vehicle classification, we focus on the loss function of the neural network. We add a regularization term to the cross-entropy loss and propose a new loss function, Dual Cross-Entropy Loss . The regularization term places a constraint on the probability that a data point is assigned to a class other than its ground-truth class, which can alleviate the vanishing of the gradient when the value of the cross-entropy loss is close to zero. To demonstrate the effectiveness of our loss function, we perform two sets of experiments. The first set is conducted on a small-sample fine-grained vehicle classification dataset, the Stanford Cars-196 dataset. The second set is conducted on two small-sample datasets, the LabelMe dataset and the UIUC-Sports dataset, as well as on one large-sample dataset, the CIFAR-10 dataset. The experimental results show that the proposed loss function improves the fine-grained vehicle classification performance and has good performance on three other general image classification tasks.Keywords
Funding Information
- National Natural Science Foundation of China (61563030, 61402047, 61763028)
- Natural Science Foundation of Gansu Province, China (17JR5RA125)
- Hongliu Outstanding Youth Talents Foundation of Lanzhou University of Technology
This publication has 40 references indexed in Scilit:
- Bilinear CNN Models for Fine-Grained Visual Recognition2015
- FaceNet: A unified embedding for face recognition and clustering2015
- A large-scale car dataset for fine-grained categorization and verification2015
- Deep learningNature, 2015
- Video Tracking Using Learned Hierarchical FeaturesIEEE Transactions on Image Processing, 2015
- Variational Bayesian Matrix Factorization for Bounded Support DataIEEE Transactions on Pattern Analysis and Machine Intelligence, 2014
- Bayesian estimation of Dirichlet mixture model with variational inferencePattern Recognition, 2014
- Bayesian Estimation of Beta Mixture Models with Variational InferenceIEEE Transactions on Pattern Analysis and Machine Intelligence, 2011
- What, where and who? Classifying events by scene and object recognition2007
- A handwritten character recognition system using directional element feature and asymmetric Mahalanobis distanceIEEE Transactions on Pattern Analysis and Machine Intelligence, 1999