Deep learning based human parsing methods usually require a large amount of training data to reach high performance. However, it is costly and time-consuming to obtain manually annotated high quality labels for a large scale dataset. To alleviate annotation efforts, we propose a new semi-supervised human parsing method for which we only need a small number of labels for training. First, we generate high quality pseudo labels on unlabeled images using a hierarchical information passing network (HIPN), which reasons human part segmentation in a coarse to fine manner. Furthermore, we develop a noise-tolerant hybrid learning method, which takes advantage of positive and negative learning to better handle noisy pseudo labels. When evaluated on standard human parsing benchmarks, our HIPN achieves a new state-of-the-art performance. Moreover, our noise-tolerant hybrid learning method further improves the performance and outperforms the state-of-the-art semi-supervised method (i.e. GRN) by 4.47 points w.r.t mIoU on the LIP dataset.
|Title of host publication||35th AAAI Conference on Artificial Intelligence, AAAI 2021|
|Number of pages||9|
|ISBN (Print)||9781577358664 |
|Publication status||Published - 18 May 2021|
|Name||Proceedings of the AAAI Conference on Artificial Intelligence|
|Name||AAAI-21/ IAAI-21/ EAAI-21 Proceedings|