通过相对位置预测能力改进腹侧视觉通路的无监督任务驱动模型
Improving Unsupervised Task-driven Models of Ventral Visual Stream via Relative Position Predictivity
AI总结：
本文针对腹侧视觉通路功能不仅限于物体识别的问题，提出将相对位置预测学习与对比学习相结合的无监督任务驱动建模方法，实验证明其能同时提升物体识别性能、RP预测能力和大脑相似性。
摘要：
基于腹侧视觉通路（VVS）主要服务于物体识别这一概念，当前的无监督任务驱动方法通过对比学习对VVS进行建模，并已取得良好的大脑相似性。然而，我们认为VVS的功能不仅限于物体识别。在本文中，我们引入了一项涉及VVS的额外功能，称为相对位置（RP）预测。我们首先从理论上解释对比学习可能无法赋予模型RP预测能力。受此启发，我们随后将RP学习与对比学习相结合，提出了一种新的无监督任务驱动方法来建模VVS，该方法更符合生物学现实。我们进行了大量实验，结果表明：（i）我们的方法在增强RP预测能力的同时，显著提升了物体识别的下游性能；（ii）RP预测能力普遍提高了模型的大脑相似性。我们的结果从计算角度为VVS参与位置感知（尤其是RP预测）提供了有力证据。
英文摘要：
Based on the concept that ventral visual stream (VVS) mainly functions for object recognition, current unsupervised task-driven methods model VVS by contrastive learning, and have achieved good brain similarity. However, we believe functions of VVS extend beyond just object recognition. In this paper, we introduce an additional function involving VVS, named relative position (RP) prediction. We first theoretically explain contrastive learning may be unable to yield the model capability of RP prediction. Motivated by this, we subsequently integrate RP learning with contrastive learning, and propose a new unsupervised task-driven method to model VVS, which is more inline with biological reality. We conduct extensive experiments, demonstrating that: (i) our method significantly improves downstream performance of object recognition while enhancing RP predictivity; (ii) RP predictivity generally improves the model brain similarity. Our results provide strong evidence for the involvement of VVS in location perception (especially RP prediction) from a computational perspective.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
