Feature context learning for human parsing

Parsing inconsistency, referring to the scatters and speckles in the parsing results as well as imprecise contours, is a long-standing problem in human parsing. It results from the fact that the pixel-wise classification loss independently considers each pixel. To address the inconsistency issue, we propose in this paper an end-to-end trainable, highly flexible and generic module called feature context module (FCM). FCM explores the correlation of adjacent pixels and aggregates the contextual information embedded in the real topology of the human body. Therefore, the feature representations are enhanced and thus quite robust in distinguishing semantically related parts. Extensive experiments are done with three different backbone models and four benchmark datasets, suggesting that FCM can be an effective and efficient plug-in to consistently improve the performance of existing algorithms without sacrificing the inference speed too much.