Attention Convolutional Binary Neural Tree for Fine-Grained Visual Categorization

By Ruyi Ji, Longyin Wen, Libo Zhang, Dawei Du, Ynajun Wu, Chen Zhao, Xianglong Liu, Feiyue Huang. 2019

198 citations recorded by the source corpus.

Fine-grained visual categorization (FGVC) is an important but challenging task due to high intra-class variances and low inter-class variances caused by deformation, occlusion, illumination, etc. An attention convolutional binary neural tree architecture is presented to address those problems for weakly supervised FGVC. Specifically, we incorporate convolutional operations along edges of the tree structure, and use the routing functions in each node to determine the root-to-leaf computational paths within the tree. The final decision is computed as the summation of the predictions from leaf nodes. The deep convolutional operations learn to capture the representations of objects, and the tree structure characterizes the coarse-to-fine hierarchical feature learning process. In addition, we use the attention transformer module to enforce the network to capture discriminative features. The negative log-likelihood loss is used to train the entire network in an end-to-end fashion by SGD with back-propagation. Several experiments on the CUB-200-2011, Stanford Cars and Aircraft datasets demonstrate that the proposed method performs favorably against the state-of-the-arts.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Model Architectures

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

1. Xiu-Shen Wei
2. Jian Yang
3. Jianxin Wu
4. Jinhui Tang
5. Longyin Wen
6. Yi-Zhe Song
7. Yuxin Peng
8. Christin Seifert

In Computer Vision and Pattern Recognition

1. Dacheng Tao
2. Luc Van Gool
3. Yi Yang
4. Yuxin Peng
5. Xiaogang Wang
6. Yi-Zhe Song
7. Ming-Hsuan Yang
8. Tao A. Xiang

In Model Architectures

1. Yuxin Peng
2. Christin Seifert
3. Yi-Zhe Song
4. Meike Nauta
5. Jianxin Wu
6. Ron van Bree
7. Libo Zhang
8. Xiu-Shen Wei

Citations in the corpus

• Towards Real-World Prohibited Item Detection: A Large-Scale X-ray Benchmark (2021, background): “In recent years, due to the substantial development of deep learning and computer vision technologies[31, 24, 34, 14, 13, 16, 3], automatic security inspection of prohibited items becomes possible.”
• Neural Prototype Trees for Interpretable Fine-grained Image Recognition (2020, methodology): “Other tree approaches for image classification apply post-hoc explanation techniques, by showing example images per node [2, 55], visualizing typical CNN filters of each node that can be manually labelled [55], showing class activation maps [25] or manual inspection of leaf labels and the meaning of”
• Fine-Grained Image Analysis With Deep Learning: A Survey (2021, methodology): “[89] presented an attention based convolutional binary neural tree, which incorporates attention mechanisms with a tree structure to facilitate coarse-to-fine hierarchical fine-grained feature learning.”