Triple-CFN: Separating Concepts and Features Enhances Machine Abstract Reasoning Ability
This work addresses challenges in abstract reasoning for deep learning models, offering incremental improvements with domain-specific applications.
The paper tackled the problem of visual abstract reasoning by separating concept and feature extraction, resulting in improved reasoning accuracy on Raven's Progressive Matrices through frameworks like Triple-CFN and Meta Triple-CFN.
This paper introduces innovative frameworks for visual abstract reasoning, aiming to boost deep learning model performance. It emphasizes the importance of separating abstract concept and reasoning feature extraction processes. The effectiveness of the Cross-Feature Network (CFN) and its enhanced version, Triple-CFN, validates this approach. Challenges in visual abstract reasoning arise from complex pattern induction and conflicts in low-dimensional representations. To address these, a dual Expectation-Maximization (EM) process is introduced during CFN training, optimizing module parameters to synthesize non-conflicting concepts. However, the dual EM process may overfit, so mutual and decorrelation supervisions are designed to assist feature extraction, with decorrelation supervision proving effective. Leveraging metadata in Raven's Progressive Matrices (RPM), the paper proposes Meta Triple-CFN, improving reasoning accuracy and interpretability. Additionally, a Re-space layer is designed for feature space construction, further enhancing Triple-CFN's reasoning accuracy. These innovative designs provide effective solutions for abstract reasoning problem solvers, benefiting multiple deep learning domains. Codes are available at: https://github.com/Yuanbeiming/Triple-CFN-Separating-Concepts-and-Features-Enhances-Machine-Abstract-Reasoning-Ability.