Interpretable and Accurate Fine-grained Recognition via Region Grouping

Abstract

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.

arXiv commentAccepted to CVPR 2020 (Oral)

References in corpus (6)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Axiomatic Attribution for Deep Networks
• Towards Robust Interpretability with Self-Explaining Neural Networks
• RISE: Randomized Input Sampling for Explanation of Black-box Models
• Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNet
• Fully Convolutional Attention Networks for Fine-Grained Recognition