用概率推理提升残差网络多标签图像分类精度
Supervised Multilabel Image Classification Using Residual Networks with Probabilistic Reasoning
- 在残差网络中引入概率推理，建模标签间依赖与不确定性
- 在COCO-2014上达到0.794 mAP，优于ResNet-SRN和ViT基线
- 适合关注多标签分类与模型可解释性的研究者
多标签图像分类因广泛的应用前景受到关注。本文提出一种基于改进的ResNet-101架构与COCO-2014数据集的新方法，通过模拟标签间的依赖关系与不确定性，采用概率推理提升预测准确率。大量实验表明，该模型性能超越以往技术，接近当前最优水平。在精确率-召回率等指标下评估，mAP达0.794，显著优于ResNet-SRN（0.771）和视觉变换器基线（0.785）。其创新性在于将概率推理融入深度学习模型，有效应对多标签场景下的复杂挑战。
原文摘要 · Abstract (English)
Multilabel image categorization has drawn interest recently because of its numerous computer vision applications. The proposed work introduces a novel method for classifying multilabel images using the COCO-2014 dataset and a modified ResNet-101 architecture. By simulating label dependencies and uncertainties, the approach uses probabilistic reasoning to improve prediction accuracy. Extensive tests show that the model outperforms earlier techniques and approaches to state-of-the-art outcomes in multilabel categorization. The work also thoroughly assesses the model's performance using metrics like precision-recall score and achieves 0.794 mAP on COCO-2014, outperforming ResNet-SRN (0.771) and Vision Transformer baselines (0.785). The novelty of the work lies in integrating probabilistic reasoning into deep learning models to effectively address the challenges presented by multilabel scenarios.
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。