Improving CNN classifiers by estimating test-time priors
This addresses the issue of class prior mismatch for fine-grained image classification, but it is incremental as it builds on existing estimation methods.
The paper tackles the problem of different training and test set class priors in CNN classifiers by proposing a Maximum a Posteriori approach to estimate test-time priors, resulting in accuracy improvements of up to 4.0% on fine-grained datasets and enabling a single model to outperform a competition-winning ensemble.
The problem of different training and test set class priors is addressed in the context of CNN classifiers. We compare two different approaches to estimating the new priors: an existing Maximum Likelihood Estimation approach (optimized by an EM algorithm or by projected gradient descend) and a proposed Maximum a Posteriori approach, which increases the stability of the estimate by introducing a Dirichlet hyper-prior on the class prior probabilities. Experimental results show a significant improvement on the fine-grained classification tasks using known evaluation-time priors, increasing the top-1 accuracy by 4.0% on the FGVC iNaturalist 2018 validation set and by 3.9% on the FGVCx Fungi 2018 validation set. Estimation of the unknown test set priors noticeably increases the accuracy on the PlantCLEF dataset, allowing a single CNN model to achieve state-of-the-art results and outperform the competition-winning ensemble of 12 CNNs. The proposed Maximum a Posteriori estimation increases the prediction accuracy by 2.8% on PlantCLEF 2017 and by 1.8% on FGVCx Fungi, where the existing MLE method would lead to a decrease accuracy.