CoNPL: Consistency training framework with noise-aware pseudo labeling for dense pose estimation

Abstract

Dense pose estimation faces hurdles due to the lack of costly precise pixel-level IUV labels. Existing methods aim to overcome it by regularizing model outputs or interpolating pseudo labels. However, conventional geometric transformations often fall short, and pseudo labels may introduce unwanted noise, leading to continued challenges in rectifying inaccurate estimations. We introduced a novel Consistency training framework with Noise-aware Pseudo Labeling (CoNPL) to tackle problems in learning from unlabeled pixels. CoNPL employs both weak and strong augmentations in a shared model to enhance robustness against aggressive transformations. To address noisy pseudo labels, CoNPL integrates a Noise-aware Pseudo Labeling (NPL) module, which consists of a Noise-Aware Module (NAM), and Noise-Resistant Learning (NRL) modules. NAM identifies misclassifications and incorrect UV coordinates using binary classification and regression, while NRL dynamically adjusts loss weights to filter out uncertain samples, thereby stabilizing learning from pseudo labels. Our method demonstrates a + 2.0% improvement in AP on the DensePose-COCO benchmark across different networks, achieving state-of-the-art performance. On the Ultrapose and DensePose-Chimps benchmark, our method also demonstrates a + 2.7% and + 3.0% improvement in AP.