Mix-ViT: Mixing attentive vision transformer for ultra-fine-grained visual categorization
Authors:
- Xiaohan YuXYXiaohan Yu
- Jun WangJWJun Wang
- Yang ZhaoYZYang Zhao
- Yongsheng GaoYGYongsheng Gao
- 28 October 2022
- journal article
- research article
- Published by Elsevier in Pattern Recognition
- Vol. 135
Abstract
No abstract availableKeywords
Funding Information
- Australian Research Council (DP180100958, IH180100002)
This publication has 11 references indexed in Scilit:
- Learning upper patch attention using dual-branch training strategy for masked face recognitionPattern Recognition, 2022
- Learning multiscale hierarchical attention for video summarizationPattern Recognition, 2022
- Unimodal regularisation based on beta distribution for deep ordinal regressionPattern Recognition, 2022
- Learning discriminative region representation for person retrievalPattern Recognition, 2022
- MaskCOV: A random mask covariance network for ultra-fine-grained visual categorizationPattern Recognition, 2021
- Learning deep part-aware embedding for person retrievalPattern Recognition, 2021
- BBAS: Towards large scale effective ensemble adversarial attacks against deep neural network learningInformation Sciences, 2021
- Attention-based convolutional neural network for deep face recognitionMultimedia Tools and Applications, 2019
- Enhancing Sketch-Based Image Retrieval by CNN Semantic Re-rankingIEEE Transactions on Cybernetics, 2019
- Automatic classification of legumes using leaf vein image featuresPattern Recognition, 2014