动态学习类别专属阈值，提升部分标签下的多标签图像识别准确率
Learning Semantic-Aware Threshold for Multi-Label Image Recognition with Partial Labels
- 基于类别得分分布自适应计算阈值，取代固定阈值
- 在COCO和VG-200上实现显著性能提升，标签有限时优势更明显
- 适合标注不全的多标签图像识别场景，如真实世界数据集
带有部分标签的多标签图像识别（MLR-PL）旨在使用已知与未知标签混合的数据训练模型。传统方法依赖语义或特征相关性，通过预设阈值为未识别标签生成伪标签，但常忽略类别间得分分布差异，导致伪标签不准确、不完整，影响模型性能。本文提出语义感知阈值学习（SATL）算法，通过分析每类正负样本的得分分布，动态生成类别专属阈值，并在训练中持续更新。此外，引入差分排序损失，拉大正负样本得分分布差距，增强阈值判别力。在大规模多标签数据集Microsoft COCO和VG-200上的全面实验表明，该方法在标签稀疏场景下显著提升性能。
原文摘要 · Abstract (English)
Multi-label image recognition with partial labels (MLR-PL) is designed to train models using a mix of known and unknown labels. Traditional methods rely on semantic or feature correlations to create pseudo-labels for unidentified labels using pre-set thresholds. This approach often overlooks the varying score distributions across categories, resulting in inaccurate and incomplete pseudo-labels, thereby affecting performance. In our study, we introduce the Semantic-Aware Threshold Learning (SATL) algorithm. This innovative approach calculates the score distribution for both positive and negative samples within each category and determines category-specific thresholds based on these distributions. These distributions and thresholds are dynamically updated throughout the learning process. Additionally, we implement a differential ranking loss to establish a significant gap between the score distributions of positive and negative samples, enhancing the discrimination of the thresholds. Comprehensive experiments and analysis on large-scale multi-label datasets, such as Microsoft COCO and VG-200, demonstrate that our method significantly improves performance in scenarios with limited labels.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。