Learning to Model Pixel-Embedded Affinity for Homogeneous Instance Segmentation
Keywords:Computer Vision (CV)
AbstractHomogeneous instance segmentation aims to identify each instance in an image where all interested instances belong to the same category, such as plant leaves and microscopic cells. Recently, proposal-free methods, which straightforwardly generate instance-aware information to group pixels into different instances, have received increasing attention due to their efficient pipeline. However, they often fail to distinguish adjacent instances due to similar appearances, dense distribution and ambiguous boundaries of instances in homogeneous images. In this paper, we propose a pixel-embedded affinity modeling method for homogeneous instance segmentation, which is able to preserve the semantic information of instances and improve the distinguishability of adjacent instances. Instead of predicting affinity directly, we propose a self-correlation module to explicitly model the pairwise relationships between pixels, by estimating the similarity between embeddings generated from the input image through CNNs. Based on the self-correlation module, we further design a cross-correlation module to maintain the semantic consistency between instances. Specifically, we map the transformed input images with different views and appearances into the same embedding space, and then mutually estimate the pairwise relationships of embeddings generated from the original input and its transformed variants. In addition, to integrate the global instance information, we introduce an embedding pyramid module to model affinity on different scales. Extensive experiments demonstrate the versatile and superior performance of our method on three representative datasets. Code and models are available at https://github.com/weih527/Pixel-Embedded-Affinity.
How to Cite
Huang, W., Deng, S., Chen, C., Fu, X., & Xiong, Z. (2022). Learning to Model Pixel-Embedded Affinity for Homogeneous Instance Segmentation. Proceedings of the AAAI Conference on Artificial Intelligence, 36(1), 1007-1015. https://doi.org/10.1609/aaai.v36i1.19984
AAAI Technical Track on Computer Vision I