Weakly Supervised Fine-Grained Categorization With Part-Based Image Representation

By Yu Zhang, Xiu-Shen Wei, Jianxin Wu, Jianfei Cai, Jiangbo Lu, Viet Anh Nguyen, Minh N. Do. 2016

187 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Luc Van Gool
2. Yu Qiao
3. G. Wang
4. Dacheng Tao
5. Jianfei Cai
6. Ming-Hsuan Yang
7. Trevor Darrell
8. Yi Yang

Citations in the corpus

• Recent advances in convolutional neural networks (2015, methodology): “[190] use the unsupervised selective search to generate object proposals, and then select the useful parts from the multi-scale generated part proposals.”
• The Devil is in the Tails: Fine-grained Classification in the Wild (2017, background): “Most fine-grained research papers present a novel model for classification [4, 6, 7, 12, 15, 17, 25, 31, 40, 45, 46, 57, 58, 59, 61, 62].”
• Delving Deep Into Label Smoothing (2020, unknown): “The fine-grained image classifi-cation task [60], [61], [62], [63], [64] focuses on distinguishing [18] 102 2040 6149 Cars [20] 196 8144 8041 Aircrafts [21] 90 6667 3333 subordinate categories within entry-level categories [27], [65], [66], [67].”
• Knowledge Guided Disambiguation for Large-Scale Scene Classification With Multi-Resolution CNNs (2016, background): “The multi-scale representation have been also exploited in variety of tasks, such as fine-grained recognition [43], scene recognition [11], and so on.”
• Integrating Scene Text and Visual Appearance for Fine-Grained Image Classification (2017, unknown): “In [13], the authors proposed to select”
• Improving Fine-Grained Visual Classification using Pairwise Confusion (2017, unknown): “Most of the prior work in FGVC has focused on tackling the intra-class variation in pose, lighting, and viewpoint using localization techniques [1,2,3,4,5], and by augmenting training datasets with additional data from the Web [6,7].”
• Object-Part Attention Model for Fine-Grained Image Classification (2017, methodology): “Most existing weakly supervised methods [7], [14] ignore the spatial relationships between the object and its parts as”
• Training with Confusion for Fine-Grained Visual Classification (2017, methodology): “Most of the prior work in FGVC has focused on tackling the variations in pose, lighting, and viewpoint using localization techniques [12, 20, 25, 53, 55], and by augmenting training datasets with additional data from the Web [6, 21].”