论文标题
有条件的卷积
Conditional Convolutions for Instance Segmentation
论文作者
论文摘要
我们提出了一个简单而有效的实例分割框架，称为condinst（例如分割）。最佳实例分割方法（例如蒙版R-CNN）依赖ROI操作（通常是Roipool或Roialign）来获得最终实例掩码。相比之下，我们建议从新的角度解决实例分割。我们没有使用实例ROI作为固定权重网络的输入，而是采用以实例为条件的动态实例感知网络。 Condinst具有两个优势：1）实例分段是通过完全卷积的网络来解决的，从而消除了对ROI种植和特征对齐的需求。 2）由于动态生成的条件卷积的能力大大提高，掩盖头可能非常紧凑（例如3个转换层，每个层只有8个通道），从而导致推断速度明显更快。我们演示了一种更简单的实例分割方法，该方法可以在准确性和推理速度方面提高性能。在可可数据集上，我们的表现均优于最近的一些方法，包括精心调整的蒙版RCNN基准，而无需更长的培训时间表。 可用代码：https：//github.com/aim-uofa/adet
We propose a simple yet effective instance segmentation framework, termed CondInst (conditional convolutions for instance segmentation). Top-performing instance segmentation methods such as Mask R-CNN rely on ROI operations (typically ROIPool or ROIAlign) to obtain the final instance masks. In contrast, we propose to solve instance segmentation from a new perspective. Instead of using instance-wise ROIs as inputs to a network of fixed weights, we employ dynamic instance-aware networks, conditioned on instances. CondInst enjoys two advantages: 1) Instance segmentation is solved by a fully convolutional network, eliminating the need for ROI cropping and feature alignment. 2) Due to the much improved capacity of dynamically-generated conditional convolutions, the mask head can be very compact (e.g., 3 conv. layers, each having only 8 channels), leading to significantly faster inference. We demonstrate a simpler instance segmentation method that can achieve improved performance in both accuracy and inference speed. On the COCO dataset, we outperform a few recent methods including well-tuned Mask RCNN baselines, without longer training schedules needed. Code is available: https://github.com/aim-uofa/adet
