Fine-Grained Categorization via CNN-Based Automatic Extraction and Integration of Object-Level and Part-Level Features
It addresses the problem of costly manual annotations in fine-grained visual categorization for researchers and practitioners, offering an incremental improvement by leveraging existing CNN features more ingeniously.
The paper tackles fine-grained categorization by automatically extracting and integrating object-level and part-level features from CNN hierarchical features without needing manual part annotations, achieving superior or comparable state-of-the-art performance on datasets like Caltech-UCSD Birds-200-2011, FGVC-Aircraft, Cars, and Stanford dogs.
Fine-grained categorization can benefit from part-based features which reveal subtle visual differences between object categories. Handcrafted features have been widely used for part detection and classification. Although a recent trend seeks to learn such features automatically using powerful deep learning models such as convolutional neural networks (CNN), their training and possibly also testing require manually provided annotations which are costly to obtain. To relax these requirements, we assume in this study a general problem setting in which the raw images are only provided with object-level class labels for model training with no other side information needed. Specifically, by extracting and interpreting the hierarchical hidden layer features learned by a CNN, we propose an elaborate CNN-based system for fine-grained categorization. When evaluated on the Caltech-UCSD Birds-200-2011, FGVC-Aircraft, Cars and Stanford dogs datasets under the setting that only object-level class labels are used for training and no other annotations are available for both training and testing, our method achieves impressive performance that is superior or comparable to the state of the art. Moreover, it sheds some light on ingenious use of the hierarchical features learned by CNN which has wide applicability well beyond the current fine-grained categorization task.