Fine-grained visual categorization using meta-learning optimization with sample selection of auxiliary data
Fine-grained visual categorization (FGVC) is challenging due in part to the fact that it is often
difficult to acquire an enough number of training samples. To employ large models for FGVC …
difficult to acquire an enough number of training samples. To employ large models for FGVC …
Fine-Grained Visual Categorization Using Meta-learning Optimization with Sample Selection of Auxiliary Data
Y Zhang, H Tang, K Jia - European Conference on Computer Vision, 2018 - dl.acm.org
Fine-grained visual categorization (FGVC) is challenging due in part to the fact that it is often
difficult to acquire an enough number of training samples. To employ large models for FGVC …
difficult to acquire an enough number of training samples. To employ large models for FGVC …
[PDF][PDF] Fine-Grained Visual Categorization using Meta-Learning Optimization with Sample Selection of Auxiliary Data
Y Zhang, H Tang, K Jia - eccv2018.org
Fine-grained visual categorization (FGVC) is challenging due in part to the fact that it is often
difficult to acquire an enough number of training samples. To employ large models for FGVC …
difficult to acquire an enough number of training samples. To employ large models for FGVC …
Fine-Grained Visual Categorization Using Meta-learning Optimization with Sample Selection of Auxiliary Data
Y Zhang, H Tang, K Jia - Computer Vision–ECCV 2018: 15th European …, 2018 - Springer
Fine-grained visual categorization (FGVC) is challenging due in part to the fact that it is often
difficult to acquire an enough number of training samples. To employ large models for FGVC …
difficult to acquire an enough number of training samples. To employ large models for FGVC …
Fine-Grained Visual Categorization using Meta-Learning Optimization with Sample Selection of Auxiliary Data
Y Zhang, H Tang, K Jia - arXiv e-prints, 2018 - ui.adsabs.harvard.edu
Fine-grained visual categorization (FGVC) is challenging due in part to the fact that it is often
difficult to acquire an enough number of training samples. To employ large models for FGVC …
difficult to acquire an enough number of training samples. To employ large models for FGVC …
Fine-Grained Visual Categorization using Meta-Learning Optimization with Sample Selection of Auxiliary Data
Y Zhang, H Tang, K Jia - arXiv preprint arXiv:1807.10916, 2018 - arxiv.org
Fine-grained visual categorization (FGVC) is challenging due in part to the fact that it is often
difficult to acquire an enough number of training samples. To employ large models for FGVC …
difficult to acquire an enough number of training samples. To employ large models for FGVC …
[PDF][PDF] Fine-Grained Visual Categorization using Meta-Learning Optimization with Sample Selection of Auxiliary Data
Y Zhang, H Tang, K Jia - ecva.net
Fine-grained visual categorization (FGVC) is challenging due in part to the fact that it is often
difficult to acquire an enough number of training samples. To employ large models for FGVC …
difficult to acquire an enough number of training samples. To employ large models for FGVC …
[PDF][PDF] Fine-Grained Visual Categorization using Meta-Learning Optimization with Sample Selection of Auxiliary Data
Y Zhang, H Tang, K Jia - arXiv preprint arXiv:1807.10916, 2018 - researchgate.net
Fine-grained visual categorization (FGVC) is challenging due in part to the fact that it is often
difficult to acquire an enough number of training samples. To employ large models for FGVC …
difficult to acquire an enough number of training samples. To employ large models for FGVC …
[PDF][PDF] Fine-Grained Visual Categorization using Meta-Learning Optimization with Sample Selection of Auxiliary Data
Y Zhang, H Tang, K Jia - researchgate.net
Fine-grained visual categorization (FGVC) is challenging due in part to the fact that it is often
difficult to acquire an enough number of training samples. To employ large models for FGVC …
difficult to acquire an enough number of training samples. To employ large models for FGVC …