CIGMO: Categorical invariant representations in a deep generative framework
This work addresses the challenge of disentangling categorical and view factors in object recognition for computer vision applications, representing an incremental improvement over existing deep generative models.
The authors tackled the problem of learning categorical, shape, and view factors from object image data, which existing deep generative models often fail to capture simultaneously, and showed that their CIGMO model effectively discovers object shape categories despite view variations and quantitatively outperforms previous methods, including state-of-the-art invariant clustering.
Data of general object images have two most common structures: (1) each object of a given shape can be rendered in multiple different views, and (2) shapes of objects can be categorized in such a way that the diversity of shapes is much larger across categories than within a category. Existing deep generative models can typically capture either structure, but not both. In this work, we introduce a novel deep generative model, called CIGMO, that can learn to represent category, shape, and view factors from image data. The model is comprised of multiple modules of shape representations that are each specialized to a particular category and disentangled from view representation, and can be learned using a group-based weakly supervised learning method. By empirical investigation, we show that our model can effectively discover categories of object shapes despite large view variation and quantitatively supersede various previous methods including the state-of-the-art invariant clustering algorithm. Further, we show that our approach using category-specialization can enhance the learned shape representation to better perform down-stream tasks such as one-shot object identification as well as shape-view disentanglement.