J
Jie Cao
Researcher at Lanzhou University of Technology
Publications - 16
Citations - 298
Jie Cao is an academic researcher from Lanzhou University of Technology. The author has contributed to research in topics: Contextual image classification & Artificial neural network. The author has an hindex of 5, co-authored 15 publications receiving 116 citations.
Papers
More filters
Journal ArticleDOI
Dual Cross-Entropy Loss for Small-Sample Fine-Grained Vehicle Classification
TL;DR: This work adds a regularization term to the cross-entropy loss and proposes a new loss function, Dual Cross-Entropy Loss, which improves the fine-grained vehicle classification performance and has good performance on three other general image classification tasks.
Journal ArticleDOI
BSNet: Bi-Similarity Network for Few-shot Fine-grained Image Classification
TL;DR: Li et al. as mentioned in this paper proposed a Bi-Similarity Network (BSNet) which consists of a single embedding module and a bi-similarity module of two similarity measures.
Journal ArticleDOI
BSNet: Bi-Similarity Network for Few-shot Fine-grained Image Classification
TL;DR: A so-called Bi-Similarity Network (BSNet) that consists of a single embedding module and a bi-similarity module of two similarity measures of diverse characteristics that is enabled to learn more discriminative and less similarity-biased features from few shots of fine-grained images, such that the model generalization ability can be significantly improved.
Proceedings ArticleDOI
Softmax Cross Entropy Loss with Unbiased Decision Boundary for Image Classification
TL;DR: A new softmax cross entropy loss is proposed, which adjusts the position of decision boundary so that it is not biased to any class, and experimental results show that the proposed loss is superior to softmaxCross entropy loss.
Journal ArticleDOI
Large-Margin Regularized Softmax Cross-Entropy Loss
TL;DR: This work proposes a large-margin regularization method for softmax cross-entropy loss, inspired by regularized logistic regression, where the regularized term is responsible for adjusting the width of decision margin.