Learning Features and Parts for Fine-Grained Recognition

By Jonathan Krause, Timnit Gebru, Jia Deng, Li-Jia Li, Li Fei-Fei. 2014

124 citations recorded by the source corpus.

Subfields: Aerospace Engineering, 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. Feng Zhou
2. Yuanqing Lin
3. Shuicheng Yan
4. Errui Ding
5. Ming Sun
6. Yuchen Yuan
7. Li Fei-Fei
8. Jonathan Krause

In Computer Vision and Pattern Recognition

1. Luc Van Gool
2. Ming-Hsuan Yang
3. Dacheng Tao
4. Yi Yang
5. Xiaogang Wang
6. Jiashi Feng
7. Trevor Darrell
8. Andrew Zisserman

Citations in the corpus

• Recent advances in convolutional neural networks (2015, methodology): “[109] use the ensemble of localized learned feature representations for fine-grained classification,”
• The Unreasonable Effectiveness of Noisy Data for Fine-Grained Recognition (2015, methodology): “While methods following this approach have shown some success [5,75,36,28], their performance and scalability is constrained by the paucity”
• Diversified Visual Attention Networks for Fine-Grained Object Classification (2016, methodology): “ELLF [42] uses the stacked CNN features which are pooled in the detected part regions as the final representation, obtaining 73.9% classification accuracy.”
• SPDA-CNN: Unifying Semantic Part Detection and Abstraction for Fine-Grained Recognition (2016, unknown): “Other unsupervised methods [24, 25, 39, 34] could generate multiple object parts, but they are not guaranteed to produce small parts with semantic meanings.”
• Multi-Attention Multi-Class Constraint for Fine-grained Image Recognition (2018, methodology): “A straightforward way is supervised learning with manual object part annotations, which has shown promising results in classifying birds [9,3,10,11], dogs [18,5,6,10], and cars [19,4,20].”
• Fine-grained recognition without part annotations (2015, result): “Our method is able to greatly outperform all previously-reported results [13, 27, 46, 26], setting a new state-of-the-art by 18.”
• WILDCAT: Weakly Supervised Learning of Deep ConvNets for Image Classification, Pointwise Localization and Segmentation (2017, unknown): “For fine-grained recognition, multi-feature detection has been tackled in the fully supervised setting [67, 40, 68], and in WSL [33].”
• Fine-Grained Image Classification by Exploring Bipartite-Graph Labels (2015, methodology): “This number was beaten by ELLF [28] by learning more discriminative features using CNN.”