Interpretable and Accurate Fine-grained Recognition via Region Grouping
This work addresses the problem of interpretable and accurate fine-grained recognition for computer vision applications, representing an incremental improvement over existing methods.
The authors tackled fine-grained visual recognition by integrating region-based part discovery and attribution into a deep neural network, achieving results that compare favorably to state-of-the-art methods on classification tasks and outperform previous approaches on object part localization.
We present an interpretable deep model for fine-grained visual recognition. At the core of our method lies the integration of region-based part discovery and attribution within a deep neural network. Our model is trained using image-level object labels, and provides an interpretation of its results via the segmentation of object parts and the identification of their contributions towards classification. To facilitate the learning of object parts without direct supervision, we explore a simple prior of the occurrence of object parts. We demonstrate that this prior, when combined with our region-based part discovery and attribution, leads to an interpretable model that remains highly accurate. Our model is evaluated on major fine-grained recognition datasets, including CUB-200, CelebA and iNaturalist. Our results compare favorably to state-of-the-art methods on classification tasks, and our method outperforms previous approaches on the localization of object parts.