Multiple Granularity Descriptors for Fine-Grained Categorization
By Dequan Wang, Zhiqiang Shen, Jie Shao, Wei Zhang, Xiangyang Xue, Zeyu Zhang. 2015
223 citations recorded by the source corpus.
Subfields: Artificial Intelligence, 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 Artificial Intelligence
In Computer Vision and Pattern Recognition
Citations in the corpus
- Object-Part Attention Model for Fine-Grained Image Classification (2017, methodology): “However, the external labels of ontology tree are necessary for the method of [24].”
- Fine-Grained Representation Learning and Recognition by Exploiting Hierarchical Semantic Embedding (2018, methodology): “√ 82.8 CB-CNN w/ bbox [9] √ 84.6 FCAN w/ bbox [28] √ 84.7 B-CNN w/ bbox [25] √ 85.1 AGAL w/ bbox [27] √ 85.5 TLAN [43] 77.9 DVAN [49] 79.0 MG-CNN [40] 81.7 B-CNN w/o bbox [25] 84.1 ST-CNN [17] 84.1 FCAN w/o bbox [28] 84.3 PDFR [48] 84.5 CB-CNN w/o bbox [9] 85.0 RA-CNN [8] 85.3 AGAL w/o bbox [27] 85.”
- Learning Layer-Skippable Inference Network (2020, methodology): “Particularly, our method is superior to MG-CNN [24], Bilinear-CNN [22] and RA-CNN (scale 1 + 2) [20], all of which use multiple VGGNets [11].”
- Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in Vitro (2017, unknown): “[39] 3×VGGNet × 83.”
- Attribute-Aware Attention Model for Fine-grained Representation Learning (2018, unknown): “on. 4.4 Evaluations on Image Classification Table 2: Experimental results on CUB-200-2011 dataset. w/ means using attributes or parts annotation during training. Methods Attribute Parts Acc(%) MG-CNN [38] 83.0 DeepLAC [49] 84.5 Bilinear-CNN [21] 85.1 RA-CNN [10] 85.3 Part RCNN [48] w/ 76.4 PS-CNN [1”
- Learning Multi-attention Convolutional Neural Network for Fine-Grained Image Recognition (2017, background): “• MG-CNN [27]: multiple granularity descriptors learn multi-region of interests for all the grain levels.”
- A survey on deep learning-based fine-grained object classification and semantic segmentation (2017, methodology): “Subset FL [30] AlexNet − − 77.5 MixDCNN [31] AlexNet BBox BBox 74.1 Multiple granularity CNN [33] VGGNet BBox − 83.0 Multiple granularity CNN [33] VGGNet − − 81.7 Bilinear CNN [34] VGGNet BBox BBox 77.2 Bilinear CNN [34] VGGNet − − 72.5 Visual attention based approaches Two-level attention [38]…”
- Looking for the Devil in the Details: Learning Trilinear Attention Sampling Network for Fine-Grained Image Recognition (2019, background): “• MG-CNN [29]: Multiple granularity descriptors, which leverage the hierarchical labels to generate comprehensive descriptors.”
- The Devil is in the Channels: Mutual-Channel Loss for Fine-Grained Image Classification (2020, methodology): “In this paper, we follow the same motivation as above [40], [49], [50] to address the unique challenges of fine-grained classification.”
- Part-Stacked CNN for Fine-Grained Visual Categorization (2015, background): “…on how to classify highly similar object categories explicitly. classification accuracy of fine-grained visual categorization [10, 9, 6, 22, 46], we argue that another important aspect of the problem has yet been severely overlooked, i.e ., the ability to generate a human-understandable…”
- Look Closer to See Better: Recurrent Attention Convolutional Neural Network for Fine-Grained Image Recognition (2017, background): “FCAN [20] and MG-CNN [28] are two relevant works to ours, which also use feature combination scheme from multiple scales/granularities.”
- Mask-CNN: Localizing parts and selecting descriptors for fine-grained bird species categorization (2018, unknown): “0% Multi-grained [46] X VGG-19×3 12,288 83.”
- Learning to Navigate for Fine-grained Classification (2018, methodology): “Other methods [49,47,48,43] employ an unsupervised learning scheme to localize informative regions.”