Fine-Grained Visual Classification via Progressive Multi-Granularity Training of Jigsaw Patches
By Ruoyi Du, Dongliang Chang, Ayan Kumar Bhunia, Jiyang Xie, Yi-Zhe Song, Zhanyu Ma, Jun Guo. European Conference on Computer Vision, 2020
375 citations recorded by the source corpus.
Fine-grained visual classification (FGVC) is much more challenging than traditional classification tasks due to the inherently subtle intra-class object variations. Recent works mainly tackle this problem by focusing on how to locate the most discriminative parts, more complementary parts, and parts of various granularities. However, less effort has been placed to which granularities are the most discriminative and how to fuse information cross multi-granularity. In this work, we propose a novel framework for fine-grained visual classification to tackle these problems. In particular, we propose: (i) a progressive training strategy that effectively fuses features from different granularities, and (ii) a random jigsaw patch generator that encourages the network to learn features at specific granularities. We obtain state-of-the-art performances on several standard FGVC benchmark datasets, where the proposed method consistently outperforms existing methods or delivers competitive results. The code will be available at this https URL.
Subfields: Computer Vision and Pattern Recognition, Geology
View Paper: https://www.semanticscholar.org/paper/293ed5672bc3f86051af38ad58b4e09fe2d1aa92
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Dacheng Tao
- Ming-Hsuan Yang
- Alan L. Yuille
- Yi Yang
- Xiaogang Wang
- Yong Jae Lee
- Trevor Darrell
In Geology
Citations in the corpus
- Fine-Grained Image Analysis With Deep Learning: A Survey (2021, background): “6% PMG [115] ECCV 2020 ResNet-50 448× 448 89.”
- TransFG: A Transformer Architecture for Fine-grained Recognition (2021, methodology): “Our method outperforms most existing methods while performs worse than PMG (Du et al. 2020) and API-Net (Zhuang, Wang, and Qiao 2020) with small margin.”
- Contrastive Learning for Diverse Disentangled Foreground Generation (2022, methodology): “We train a fine-grained classification model [9] on the CUB dataset [46] as our known factor feature extractor.”