Learning Rich Part Hierarchies With Progressive Attention Networks for Fine-Grained Image Recognition

By Heliang Zheng, Jianlong Fu, Zhengjun Zha, Jiebo Luo, Tao Mei. 2020

111 citations recorded by the source corpus.

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.

Subfields: Aerospace Engineering, 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 Aerospace Engineering

1. Yuxin Peng
2. Yi-Zhe Song
3. Jianxin Wu
4. Xiu-Shen Wei
5. Oisin Mac Aodha
6. Quanfu Fan
7. Serge J. Belongie
8. Jian Yang

In Artificial Intelligence

1. Rameswar Panda
2. Chun-Fu Chen
3. Quanfu Fan
4. Xiu-Shen Wei
5. Jian Yang
6. Jianxin Wu
7. Jinhui Tang
8. Yi-Zhe Song

In Computer Vision and Pattern Recognition

1. Luc Van Gool
2. Dacheng Tao
3. Xiaogang Wang
4. Ming-Hsuan Yang
5. Yi Yang
6. Chunhua Shen
7. Alan L. Yuille
8. Yu Qiao

Citations in the corpus

• This Looks Like That, Because ... Explaining Prototypes for Interpretable Image Recognition (2020, neutral): “[46, 48, 49].”
• RegionViT: Regional-to-Local Attention for Vision Transformers (2021, methodology): “Few works use attention approach to define the regional of interest for the fine-grained visual recognition (Zheng et al., 2020; Ding et al., 2021; Wharton et al., 2021).”
• Delving Deep Into Label Smoothing (2020, unknown): “The fine-grained image classifi-cation task [60], [61], [62], [63], [64] focuses on distinguishing [18] 102 2040 6149 Cars [20] 196 8144 8041 Aircrafts [21] 90 6667 3333 subordinate categories within entry-level categories [27], [65], [66], [67].”
• Fine-Grained Image Analysis With Deep Learning: A Survey (2021, background): “[88] proposed multi-level attention models to obtain hierarchical attention information (i.”