Test-Time Amendment with a Coarse Classifier for Fine-Grained Classification
This addresses the challenge of fine-grained classification for domains requiring expert annotation by leveraging human-like coarse classification to improve model performance.
The paper tackles the problem of reducing mistake severity in fine-grained classification by using coarse-grained predictions at test-time, achieving new state-of-the-art top-1 accuracy on iNaturalist-19 and tieredImageNet-H datasets.
We investigate the problem of reducing mistake severity for fine-grained classification. Fine-grained classification can be challenging, mainly due to the requirement of domain expertise for accurate annotation. However, humans are particularly adept at performing coarse classification as it requires relatively low levels of expertise. To this end, we present a novel approach for Post-Hoc Correction called Hierarchical Ensembles (HiE) that utilizes label hierarchy to improve the performance of fine-grained classification at test-time using the coarse-grained predictions. By only requiring the parents of leaf nodes, our method significantly reduces avg. mistake severity while improving top-1 accuracy on the iNaturalist-19 and tieredImageNet-H datasets, achieving a new state-of-the-art on both benchmarks. We also investigate the efficacy of our approach in the semi-supervised setting. Our approach brings notable gains in top-1 accuracy while significantly decreasing the severity of mistakes as training data decreases for the fine-grained classes. The simplicity and post-hoc nature of HiE renders it practical to be used with any off-the-shelf trained model to improve its predictions further.