提出可动态调整感受野形状的卷积方法，提升模型对复杂图像结构的适应能力。
Region-Aware Deformable Convolutions
- 用四个边界偏移定义灵活矩形感受野，突破传统固定四边形采样限制。
- 1×1小核即可捕捉局部细节与长程依赖，实现高效且精确的特征提取。
- 兼具注意力机制的灵活性与标准卷积的计算效率，适合视觉任务建模。
我们提出区域感知可变形卷积（RAD-Conv），一种新型卷积算子，增强神经网络对复杂图像结构的适应能力。不同于传统可变形卷积仅限于固定四边形采样区域，RAD-Conv为每个核元素引入四个边界偏移，构建可动态调整大小和形状的灵活矩形区域。该方法实现了对感受野宽高尺寸的精确控制，即使使用小型1×1核，也能有效捕获局部细节与长程依赖。通过将感受野形状与核结构解耦，RAD-Conv结合了注意力机制的适应性与标准卷积的高效性。这一创新设计为构建更表达力强且高效的视觉模型提供了实用方案，弥合了刚性卷积架构与计算成本高昂的注意力方法之间的差距。
原文摘要 · Abstract (English)
We introduce Region-Aware Deformable Convolution (RAD-Conv), a new convolutional operator that enhances neural networks' ability to adapt to complex image structures. Unlike traditional deformable convolutions, which are limited to fixed quadrilateral sampling areas, RAD-Conv uses four boundary offsets per kernel element to create flexible, rectangular regions that dynamically adjust their size and shape to match image content. This approach allows precise control over the receptive field's width and height, enabling the capture of both local details and long-range dependencies, even with small 1x1 kernels. By decoupling the receptive field's shape from the kernel's structure, RAD-Conv combines the adaptability of attention mechanisms with the efficiency of standard convolutions. This innovative design offers a practical solution for building more expressive and efficient vision models, bridging the gap between rigid convolutional architectures and computationally costly attention-based methods.
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。