Attention Convolutional Binary Neural Tree for Fine-Grained Visual Categorization
Preprint
Abstract
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.Keywords
All Related Versions
This publication has 29 references indexed in Scilit:
- Fine-Grained Classification via Hierarchical Bilinear Pooling With Aggregated Slack MaskIEEE Access, 2019
- Fine-Grained Classification of Cervical Cells Using Morphological and Appearance Based Convolutional Neural NetworksIEEE Access, 2019
- CBAM: Convolutional Block Attention Module2018
- Pairwise Confusion for Fine-Grained Visual Classification2018
- Multi-Attention Multi-Class Constraint for Fine-grained Image Recognition2018
- Mining Discriminative Triplets of Patches for Fine-Grained Classification2016
- Part-Stacked CNN for Fine-Grained Visual Categorization2016
- SPDA-CNN: Unifying Semantic Part Detection and Abstraction for Fine-Grained Recognition2016
- Fine-grained recognition without part annotations2015
- Part-Based R-CNNs for Fine-Grained Category Detection2014