视觉调节：重新考虑图像尺度作为可学习变量用于目标检测
Visual Accommodation: Rethinking Image Scale as a Learnable Variable for Object Detection
AI总结：
本文提出Ciliary-DETR框架，通过动态估计测试时的尺度因子提升目标检测的灵活性和鲁棒性，解决了传统固定分辨率检测器的局限。
摘要：
我们提出了Ciliary-DETR（此前名称：Elastic-DETR），一种类似于生物调节的测试时间分辨率调整框架。尽管多尺度数据增强提高了对尺度变化的鲁棒性，现代检测器依赖于固定推理分辨率，可能限制了灵活性和鲁棒性。类似睫状肌，我们引入了一个轻量级的尺度预测器，能够在广泛的输入尺度上动态估计测试时的尺度因子。核心挑战是标准训练设置下最优输入尺度本质上是不可观测的。为了解决这一挑战，我们引入了期望缩放行为的参数化形式，导致以损失驱动的目标，引导缩放优化。总体而言，我们的方法实现了灵活且高效的单次推理，弥合了训练时鲁棒性和测试时适应性之间的差距。
英文摘要：
We propose Ciliary-DETR (previous name: Elastic-DETR), a framework for test-time resolution adjustment analogous to biological accommodation. While multi-scale data augmentation improves robustness to scale variation, modern detectors rely on fixed inference resolutions, potentially limiting flexibility and robustness. Similar to the ciliary muscle, we introduce a lightweight scale predictor that dynamically estimates test-time scale factors across a wide range of input scales. The core challenge is that the optimal input scale is inherently unobservable under standard training setups. To address this challenge, we introduce a parametric formulation of desired scaling behavior, leading to loss-driven objectives that guide scale optimization. Overall, our method enables flexible and efficient single-pass inference, bridging the gap between training-time robustness and test-time adaptation.
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。
