Improving Fine-Grained Visual Classification using Pairwise Confusion

93 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Fine-Grained Visual Classification via Progressive Multi-Granularity Training of Jigsaw Patches (2020, methodology): “9 PC (ECCV18) [10] DenseNet161 86.”
The Devil is in the Channels: Mutual-Channel Loss for Fine-Grained Image Classification (2020, methodology): “Authors in [10] presented a new procedure, called pairwise confusion (PC), in order to improve the generalization for fine-grained image classification task by encouraging confusion in the output activations and forcing the model to focus”
Kervolutional Neural Networks (2019, background): “Table 3 lists the performance of KNN and baselines from [20, 25, 13].”
See Better Before Looking Closer: Weakly Supervised Data Augmentation Network for Fine-Grained Visual Classification (2019, background): “proposed PC [4] to combine the pairwise confusion loss with cross entropy loss to learn features with greater generalization, thereby preventing overfitting.”
Multi-branch and Multi-scale Attention Learning for Fine-Grained Visual Categorization (2020, unknown): “0 PC [23] 86.”
Fine-Grained Image Analysis With Deep Learning: A Survey (2021, background): “ing the natural prediction confidence scores for fine-grained categories [107], [108].”