Scholarlink

<p>Due to inherent variability and unpredictability in real-world environments, single gait recognition models struggle to handle diverse covariate factors such as complex backgrounds, occlusions, viewpoint changes, and noise, often facing a trade-off between robustness and generalization. While ensemble learning offers a potential solution by integrating multiple models, traditional approaches often fail to manage heterogeneous knowledge transfer and mitigate negative transfer between conflicting experts. To address these challenges, we propose MEMLA-Gait, a novel framework for principled heterogeneous knowledge integration. Our key insight is that effective integration requires simultaneously resolving three interdependent issues: isolation between experts, varying reliability of expert knowledge, and superficial mimicry in passive transfer. MEMLA-Gait introduces three mechanisms: (1) a Mutual Learning Strategy (MLS) for collaborative knowledge refinement, (2) an Expert Authority Factor (EAF) that dynamically weights knowledge transfer based on discriminative power, and (3) an Adversarial Learning (AL) mechanism to promote deep feature assimilation. Extensive experiments on four challenging datasets show that MEMLA-Gait significantly outperforms state-of-the-art methods. Ablation studies further validate our framework, demonstrating that the unified system achieves substantially higher performance than any individual component, confirming the necessity of addressing all three challenges in concert.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

MEMLA-Gait: robust gait recognition via synergistic integration of heterogeneous experts with mutual and adversarial learning

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年10月13日

查看全文
  • Hao Xi,
  • Chuanping Hu

摘要

Due to inherent variability and unpredictability in real-world environments, single gait recognition models struggle to handle diverse covariate factors such as complex backgrounds, occlusions, viewpoint changes, and noise, often facing a trade-off between robustness and generalization. While ensemble learning offers a potential solution by integrating multiple models, traditional approaches often fail to manage heterogeneous knowledge transfer and mitigate negative transfer between conflicting experts. To address these challenges, we propose MEMLA-Gait, a novel framework for principled heterogeneous knowledge integration. Our key insight is that effective integration requires simultaneously resolving three interdependent issues: isolation between experts, varying reliability of expert knowledge, and superficial mimicry in passive transfer. MEMLA-Gait introduces three mechanisms: (1) a Mutual Learning Strategy (MLS) for collaborative knowledge refinement, (2) an Expert Authority Factor (EAF) that dynamically weights knowledge transfer based on discriminative power, and (3) an Adversarial Learning (AL) mechanism to promote deep feature assimilation. Extensive experiments on four challenging datasets show that MEMLA-Gait significantly outperforms state-of-the-art methods. Ablation studies further validate our framework, demonstrating that the unified system achieves substantially higher performance than any individual component, confirming the necessity of addressing all three challenges in concert.