X
Xiaoxu Li
Researcher at Lanzhou University of Technology
Publications - 38
Citations - 772
Xiaoxu Li is an academic researcher from Lanzhou University of Technology. The author has contributed to research in topics: Discriminative model & Contextual image classification. The author has an hindex of 7, co-authored 27 publications receiving 283 citations.
Papers
More filters
Journal ArticleDOI
The Devil is in the Channels: Mutual-Channel Loss for Fine-Grained Image Classification
Dongliang Chang,Yifeng Ding,Jiyang Xie,Ayan Kumar Bhunia,Xiaoxu Li,Zhanyu Ma,Ming Wu,Jun Guo,Yi-Zhe Song +8 more
TL;DR: In this article, a mutual channel loss (MC-Loss) is proposed for fine-grained image categorization, which consists of two channel-specific components: a discriminality component and a diversity component.
Journal ArticleDOI
Fine-Grained Vehicle Classification With Channel Max Pooling Modified CNNs
TL;DR: Experimental results on two fine-grained vehicle datasets demonstrate that the CMP modified CNNs can improve the classification accuracies on the task of fine- grained vehicle classification while a massive amount of parameters are reduced.
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
The Devil is in the Channels: Mutual-Channel Loss for Fine-Grained Image Classification
Dongliang Chang,Yifeng Ding,Jiyang Xie,Ayan Kumar Bhunia,Xiaoxu Li,Zhanyu Ma,Ming Wu,Jun Guo,Yi-Zhe Song +8 more
TL;DR: Experimental results show the superiority of the MC-Loss when implemented on top of common base networks can achieve state-of-the-art performance on all four fine-grained categorization datasets, and ablative studies further demonstrate the supremacy of the loss when compared with other recently proposed general-purpose losses for visual classification.
Journal ArticleDOI
A concise review of recent few-shot meta-learning methods
TL;DR: This short communication gives a concise review on recent representative methods in few-shot meta-learning, which are categorized into four branches according to their technical characteristics.