Review for NeurIPS paper: Fine-Grained Dynamic Head for Object Detection

Summary and Contributions: The paper proposes a novel fine-grained dynamic routing mechanism for object detection where it conditionally selects features from multiple FPN scales for each pixel-level sub-region of an instance by using the data-dependent spatial gates. To reduce computational complexity, spatially sparse convolution is used in combination with a newly proposed activation function based on restricted tanh. Depth path uses bottleneck module with residual connection. Scale paths use common topology except for the bilinear operation. Output of the spatial gate is the gating factor, which is continuous, representing an estimate of probability of path being enabled.