Abstract | ||
---|---|---|
•We re-investigate the pipeline of fine-grained visual categorization (FGVC) techniques from the view of human visual recognition system, and propose a novel Attention-Shift based Deep Neural Network (AS-DNN) for automatic parts locating and semantic correlation learning.•We propose an end-to-end trainable sub-network structure Csft to simulate the attention-shift process. Csft locates the discriminative regions automatically and encodes and decodes the semantic relations among diverse discriminative parts iteratively.•Comprehensive experiments show that AS-DNN achieves state-of-the-art performances in three widely used challenging datasets. Moreover, the visualization of located discriminative parts proves the robustness of AS-DNN in complex backgrounds and postures. |
Year | DOI | Venue |
---|---|---|
2021 | 10.1016/j.patcog.2021.107947 | Pattern Recognition |
Keywords | DocType | Volume |
Fine-grained visual categorization,Deep neural network,Human perception mechanism,Attention-shift,Encoder-decoder | Journal | 116 |
Issue | ISSN | Citations |
1 | 0031-3203 | 0 |
PageRank | References | Authors |
0.34 | 0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yi Niu | 1 | 46 | 19.65 |
Yang Jiao | 2 | 0 | 1.35 |
Guangming Shi | 3 | 2663 | 184.81 |