Pairwise Confusion for Fine-Grained Visual Classification
This addresses the challenge of small sample sizes and high similarity between classes in FGVC, which is crucial for applications like species identification, but the approach is incremental as it builds on existing neural network training methods.
The paper tackles the problem of inter-class similarity in Fine-Grained Visual Classification (FGVC) by introducing Pairwise Confusion (PC), a regularization method that reduces overfitting by intentionally confusing activations, achieving state-of-the-art performance on six widely-used FGVC datasets.
Fine-Grained Visual Classification (FGVC) datasets contain small sample sizes, along with significant intra-class variation and inter-class similarity. While prior work has addressed intra-class variation using localization and segmentation techniques, inter-class similarity may also affect feature learning and reduce classification performance. In this work, we address this problem using a novel optimization procedure for the end-to-end neural network training on FGVC tasks. Our procedure, called Pairwise Confusion (PC) reduces overfitting by intentionally {introducing confusion} in the activations. With PC regularization, we obtain state-of-the-art performance on six of the most widely-used FGVC datasets and demonstrate improved localization ability. {PC} is easy to implement, does not need excessive hyperparameter tuning during training, and does not add significant overhead during test time.