Recognizing Part Attributes with Insufficient Data
This addresses the challenge of part attribute recognition for computer vision applications where data is scarce and part annotations are expensive, though it is incremental as it builds on existing methods.
The paper tackles the problem of recognizing part attributes in computer vision with insufficient training data by introducing a Concept Sharing Network (CSN), which learns part location and appearance patterns separately to handle attributes with few or zero samples, achieving effectiveness on datasets like CUB-200-2011 and CelebA.
Recognizing attributes of objects and their parts is important to many computer vision applications. Although great progress has been made to apply object-level recognition, recognizing the attributes of parts remains less applicable since the training data for part attributes recognition is usually scarce especially for internet-scale applications. Furthermore, most existing part attribute recognition methods rely on the part annotation which is more expensive to obtain. To solve the data insufficiency problem and get rid of dependence on the part annotation, we introduce a novel Concept Sharing Network (CSN) for part attribute recognition. A great advantage of CSN is its capability of recognizing the part attribute (a combination of part location and appearance pattern) that has insufficient or zero training data, by learning the part location and appearance pattern respectively from the training data that usually mix them in a single label. Extensive experiments on CUB-200-2011 [51], CelebA [35] and a newly proposed human attribute dataset demonstrate the effectiveness of CSN and its advantages over other methods, especially for the attributes with few training samples. Further experiments show that CSN can also perform zero-shot part attribute recognition. The code will be made available at https://github.com/Zhaoxiangyun/Concept-Sharing-Network.