Fine-grained Few-shot Recognition by Deep Object Parsing
This work addresses the problem of recognizing fine-grained categories with limited data for computer vision applications, representing an incremental improvement over existing approaches.
The paper tackles fine-grained few-shot recognition by introducing a deep object parsing method that decomposes objects into parts with shared templates, achieving competitive performance with state-of-the-art methods while offering interpretability.
We propose a new method for fine-grained few-shot recognition via deep object parsing. In our framework, an object is made up of K distinct parts and for each part, we learn a dictionary of templates, which is shared across all instances and categories. An object is parsed by estimating the locations of these K parts and a set of active templates that can reconstruct the part features. We recognize test instances by comparing its active templates and the relative geometry of its part locations against those of the presented few-shot instances. Our method is end-to-end trainable to learn part templates on-top of a convolutional backbone. To combat visual distortions such as orientation, pose and size, we learn templates at multiple scales, and at test-time parse and match instances across these scales. We show that our method is competitive with the state-of-the-art, and by virtue of parsing enjoys interpretability as well.