Title | ||
---|---|---|
Learning Rich Part Hierarchies with Progressive Attention Networks for Fine-Grained Image Recognition. |
Abstract | ||
---|---|---|
We investigate the localization of subtle yet discriminative parts for fine-grained image recognition. Based on the observation that such parts typically exist within a hierarchical structure (e.g., from a coarse-scale “head” to a fine-scale “eye” when recognizing bird species), we propose a novel progressive-attention convolutional neural network (PA-CNN) to progressively localize parts at multiple scales. The PA-CNN localizes parts in two steps, where a part proposal network (PPN) generates multiple local attention maps, and a part rectification network (PRN) learns part-specific features from each proposal and provides the PPN with refined part locations. This coupling of the PPN and PRN allows them to be optimized in a mutually reinforcing manner, leading to improved pinpointing of fine-grained parts. Moreover, the convolutional parameters for a PPN at a finer scale can be inherited from the PRN at a coarser scale, enabling a rich part hierarchy (e.g., eye and beak in a bird's head) to be learned in a stacked fashion. Case studies show that PA-CNN can precisely identify parts without using bounding box/part annotations. In addition, quantitative evaluations demonstrate that PA-CNN yields state-of-the-art performance in three challenging fine-grained recognition tasks. i.e., CUB-2000-2011, FGVC-Aircraft, and Stanford Cars. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1109/TIP.2019.2921876 | IEEE transactions on image processing : a publication of the IEEE Signal Processing Society |
Keywords | Field | DocType |
Image recognition,Birds,Proposals,Feature extraction,Head,Convolutional neural networks,Beak | Computer vision,Pattern recognition,Quantitative Evaluations,Convolutional neural network,Feature extraction,Artificial intelligence,Hierarchy,Discriminative model,Mathematics,Minimum bounding box | Journal |
Volume | Issue | ISSN |
29 | 1 | 1057-7149 |
Citations | PageRank | References |
10 | 0.52 | 25 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Heliang Zheng | 1 | 25 | 2.03 |
Jianlong Fu | 2 | 195 | 22.47 |
Zheng-Jun Zha | 3 | 2822 | 152.79 |
Jiebo Luo | 4 | 6314 | 374.00 |
Tao Mei | 5 | 4702 | 288.54 |