Symmetry and Group in Attribute-Object Compositions
arXiv:2004.00587
Abstract
Attributes and objects can compose diverse compositions. To model the compositional nature of these general concepts, it is a good choice to learn them through transformations, such as coupling and decoupling. However, complex transformations need to satisfy specific principles to guarantee the rationality. In this paper, we first propose a previously ignored principle of attribute-object transformation: Symmetry. For example, coupling peeled-apple with attribute peeled should result in peeled-apple, and decoupling peeled from apple should still output apple. Incorporating the symmetry principle, a transformation framework inspired by group theory is built, i.e. SymNet. SymNet consists of two modules, Coupling Network and Decoupling Network. With the group axioms and symmetry property as objectives, we adopt Deep Neural Networks to implement SymNet and train it in an end-to-end paradigm. Moreover, we propose a Relative Moving Distance (RMD) based recognition method to utilize the attribute change instead of the attribute pattern itself to classify attributes. Our symmetry learning can be utilized for the Compositional Zero-Shot Learning task and outperforms the state-of-the-art on widely-used benchmarks. Code is available at https://github.com/DirtyHarryLYL/SymNet.
Accepted to CVPR 2020, supplementary materials included, code available:https://github.com/DirtyHarryLYL/SymNet
References in corpus (6)
- Efficient Estimation of Word Representations in Vector Space
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild
- Improving Person Re-identification by Attribute and Identity Learning
- HAKE: Human Activity Knowledge Engine
- Beyond Holistic Object Recognition: Enriching Image Understanding with Part States