Core-Structures-Guided Multi-Modal Classification Neural Architecture Search
Authors: Pinhan Fu,Xinyan Liang,Tingjin Luo,Qian Guo,Yayu Zhang,Yuhua Qian
Abstract:
Most existing NAS-based multi-modal classification (MMC-NAS) methods are optimized using the classification accuracy. They can not simultaneously provide multiple models with diverse perferences such as model complex and classification performance for meeting different users' demands.Combining NAS-MMC with multi-objective optimization is a nature way for this issue. However, the challenge problem of this solution is the high computation cost. For multi-objective optimization, the computing bottleneck is pareto front search. Some higher-quality MMC models (namely core structures, CSs) consisting of high-quality features and fusion operators are easier to identify. We find that CSs have a close relation with the pareto front (PF), i.e., the individuals lying in PF contain the CSs. Based on the finding, we propose an efficient multi-objective neural architecture search for multi-modal classification by applying CSs to guide the PF search (CoMO-NAS). In conclusion, experimental results thoroughly demonstrate the effectiveness of our CoMO-NAS. Compared to state-of-the-art competitors on benchmark multi-modal tasks, we achieve comparable performance with lower model complexity in shorter search time.
Keywords：
0440.pdf
Thu Apr 18 11:20:00 CST 2024