In this work, we aim at building a simple, direct, and fast instance segmentation framework with strong performance.
We follow the principle of the SOLO
Importantly, we take one step further by dynamically learning the mask head of the object segmenter such that the mask head is conditioned on the location.
Specifically, the mask branch is decoupled into a mask kernel branch and mask feature branch,
which are responsible for learning the convolution kernel and the convolved features respectively.
Moreover, we propose Matrix NMS (non maximum suppression) to significantly reduce the inference time overhead due to NMS of masks.
Our Matrix NMS performs NMS with parallel matrix operations in one shot, and yields better results.