让目标检测器在测试时自动调节图像分辨率，提升对不同大小物体的识别能力。
Visual Accommodation: Rethinking Image Scale as a Learnable Variable for Object Detection
- 引入轻量级尺度预测器，动态调整测试时图像分辨率。
- 通过损失驱动优化，使模型自适应选择最佳输入尺度。
- 无需多尺度推理，实现高效单次推理，适合实际部署场景。
我们提出Ciliary-DETR（原名Elastic-DETR），一种类比生物视觉调节的测试时分辨率自适应框架。尽管多尺度数据增强能提升对尺度变化的鲁棒性，但现代检测器在推理时仍采用固定分辨率，限制了灵活性与鲁棒性。类似睫状肌，我们引入一个轻量级尺度预测器，可在广泛输入尺度下动态估计测试时的尺度因子。核心挑战在于标准训练设置下最优输入尺度无法观测。为此，我们提出参数化的目标缩放行为形式，导出由损失驱动的优化目标，指导尺度选择。整体上，该方法实现了灵活高效的单次推理，弥合了训练时鲁棒性与测试时适应性的差距。
原文摘要 · Abstract (English)
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.
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。