Part-based R-CNNs for Fine-grained Category Detection
This addresses the problem of fine-grained categorization for computer vision applications, offering an incremental improvement by eliminating the need for bounding boxes.
The paper tackles fine-grained category detection by proposing a model that learns whole-object and part detectors with geometric constraints, achieving state-of-the-art performance on the Caltech-UCSD bird dataset without requiring bounding box annotations at test time.
Semantic part localization can facilitate fine-grained categorization by explicitly isolating subtle appearance differences associated with specific object parts. Methods for pose-normalized representations have been proposed, but generally presume bounding box annotations at test time due to the difficulty of object detection. We propose a model for fine-grained categorization that overcomes these limitations by leveraging deep convolutional features computed on bottom-up region proposals. Our method learns whole-object and part detectors, enforces learned geometric constraints between them, and predicts a fine-grained category from a pose-normalized representation. Experiments on the Caltech-UCSD bird dataset confirm that our method outperforms state-of-the-art fine-grained categorization methods in an end-to-end evaluation without requiring a bounding box at test time.