仅用少量数据即可精准预测个体眼动轨迹，无需测试时微调。
Few-shot Personalized Scanpath Prediction
- 通过主体嵌入网络提取个体独特眼动特征
- 在多个数据集上实现少样本个性化预测，零测试微调
- 适合需要快速适配新用户的视觉行为研究
个性化眼动轨迹预测模型能揭示个体的视觉偏好与注意力模式。然而，现有方法训练需大量数据，难以在仅有少量样本时有效个性化新个体。本文提出少样本个性化眼动轨迹预测任务（FS-PSP）及新方法，旨在仅用极少目标个体的眼动数据预测其完整轨迹。核心是主体嵌入网络（SE-Net），专门捕捉每位受试者独特的扫描路径表示，使不同主体间差异显著、同一主体内路径变化最小。个性化模型基于这些嵌入生成精准预测结果。多组眼动数据集实验表明，本方法在FS-PSP设置下表现优异，且测试时无需任何微调。代码已开源：https://github.com/cvlab-stonybrook/few-shot-scanpath
原文摘要 · Abstract (English)
A personalized model for scanpath prediction provides insights into the visual preferences and attention patterns of individual subjects. However, existing methods for training scanpath prediction models are data-intensive and cannot be effectively personalized to new individuals with only a few available examples. In this paper, we propose few-shot personalized scanpath prediction task (FS-PSP) and a novel method to address it, which aims to predict scanpaths for an unseen subject using minimal support data of that subject's scanpath behavior. The key to our method's adaptability is the Subject-Embedding Network (SE-Net), specifically designed to capture unique, individualized representations for each subject's scanpaths. SE-Net generates subject embeddings that effectively distinguish between subjects while minimizing variability among scanpaths from the same individual. The personalized scanpath prediction model is then conditioned on these subject embeddings to produce accurate, personalized results. Experiments on multiple eye-tracking datasets demonstrate that our method excels in FS-PSP settings and does not require any fine-tuning steps at test time. Code is available at: https://github.com/cvlab-stonybrook/few-shot-scanpath
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。