Back to Search
Start Over
Learning Single/Multi-Attribute of Object With Symmetry and Group.
- Source :
- IEEE Transactions on Pattern Analysis & Machine Intelligence; Dec2022, Vol. 44 Issue 12, p9043-9055, 13p
- Publication Year :
- 2022
-
Abstract
- Attributes and objects can compose diverse compositions. To model the compositional nature of these concepts, it is a good choice to learn them as transformations, e.g., coupling and decoupling. However, complex transformations need to satisfy specific principles to guarantee rationality. Here, 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, we propose a transformation framework inspired by group theory, i.e., SymNet. It consists of two modules: Coupling Network and Decoupling Network. We adopt deep neural networks to implement SymNet and train it in an end-to-end paradigm with the group axioms and symmetry as objectives. Then, we propose a Relative Moving Distance (RMD) based method to utilize the attribute change instead of the attribute pattern itself to classify attributes. Besides the compositions of single-attribute and object, our RMD is also suitable for complex compositions of multiple attributes and objects when incorporating attribute correlations. SymNet can be utilized for attribute learning, compositional zero-shot learning and outperforms the state-of-the-art on four widely-used benchmarks. Code is at https://github.com/DirtyHarryLYL/SymNet. [ABSTRACT FROM AUTHOR]
- Subjects :
- ARTIFICIAL neural networks
SYMMETRY groups
GROUP theory
Subjects
Details
- Language :
- English
- ISSN :
- 01628828
- Volume :
- 44
- Issue :
- 12
- Database :
- Complementary Index
- Journal :
- IEEE Transactions on Pattern Analysis & Machine Intelligence
- Publication Type :
- Academic Journal
- Accession number :
- 160650723
- Full Text :
- https://doi.org/10.1109/TPAMI.2021.3119406