Affinity Derivation and Graph Merge for Instance Segmentation
This work addresses instance segmentation for computer vision applications, presenting an incremental improvement with a novel method for a known bottleneck.
The paper tackles instance segmentation by using pixel affinity information and a graph merge algorithm to cluster pixels into instances, achieving 27.3 AP on the Cityscapes test set.
We present an instance segmentation scheme based on pixel affinity information, which is the relationship of two pixels belonging to a same instance. In our scheme, we use two neural networks with similar structure. One is to predict pixel level semantic score and the other is designed to derive pixel affinities. Regarding pixels as the vertexes and affinities as edges, we then propose a simple yet effective graph merge algorithm to cluster pixels into instances. Experimental results show that our scheme can generate fine-grained instance mask. With Cityscapes training data, the proposed scheme achieves 27.3 AP on test set.