TY - GEN
T1 - Cognitive Predictive Coding Network
T2 - 33rd ACM International Conference on Multimedia, MM 2025
AU - Zhang, Xinyu
AU - Zhang, Lingling
AU - Wu, Yanrui
AU - Huang, Muye
AU - Liu, Jun
N1 - Publisher Copyright:
© 2025 ACM.
PY - 2025/10/27
Y1 - 2025/10/27
N2 - Abstract visual reasoning, exemplified by Raven's Progressive Matrices (RPM), remains a significant challenge in artificial intelligence. A critical difficulty lies in disentangling abstract relational rules from image-specific features, as these rules operate independently of visual appearances. To address this challenge, we propose the Cognitive Predictive Coding Network (CPCN), inspired by predictive coding theory from cognitive science. CPCN features a three-component architecture: a Relation Disentangler that separates abstract rules from image-specific features through prediction error minimization; Stacked Free Energy Minimizers (FEMs) that leverage energy minimization principles to progressively reduce uncertainty during hierarchical abstraction; and a classifier for solution identification. Unlike previous approaches, our model employs mutual information constraints to explicitly separate relation-relevant and relation-irrelevant features, enabling more robust pattern recognition. Our novel FEMs provide a principled approach to uncertainty reduction through iterative refinement of pattern understanding. Experiments demonstrate PAH's superior performance across multiple benchmarks (such as 98.9% on RAVEN-Fair) with state-of-the-art 59.7% average accuracy across all PGM subtasks.
AB - Abstract visual reasoning, exemplified by Raven's Progressive Matrices (RPM), remains a significant challenge in artificial intelligence. A critical difficulty lies in disentangling abstract relational rules from image-specific features, as these rules operate independently of visual appearances. To address this challenge, we propose the Cognitive Predictive Coding Network (CPCN), inspired by predictive coding theory from cognitive science. CPCN features a three-component architecture: a Relation Disentangler that separates abstract rules from image-specific features through prediction error minimization; Stacked Free Energy Minimizers (FEMs) that leverage energy minimization principles to progressively reduce uncertainty during hierarchical abstraction; and a classifier for solution identification. Unlike previous approaches, our model employs mutual information constraints to explicitly separate relation-relevant and relation-irrelevant features, enabling more robust pattern recognition. Our novel FEMs provide a principled approach to uncertainty reduction through iterative refinement of pattern understanding. Experiments demonstrate PAH's superior performance across multiple benchmarks (such as 98.9% on RAVEN-Fair) with state-of-the-art 59.7% average accuracy across all PGM subtasks.
KW - cognitive predictive coding
KW - raven's problem matrices
KW - visual analogical reasoning
UR - https://www.scopus.com/pages/publications/105024074590
U2 - 10.1145/3746027.3755313
DO - 10.1145/3746027.3755313
M3 - 会议稿件
AN - SCOPUS:105024074590
T3 - MM 2025 - Proceedings of the 33rd ACM International Conference on Multimedia, Co-Located with MM 2025
SP - 4097
EP - 4106
BT - MM 2025 - Proceedings of the 33rd ACM International Conference on Multimedia, Co-Located with MM 2025
PB - Association for Computing Machinery, Inc
Y2 - 27 October 2025 through 31 October 2025
ER -