Self-Correction for Human Parsing

By Peike Li, Yunqiu Xu, Yunchao Wei, Yezhou Yang. 2019

445 citations recorded by the source corpus.

Labeling pixel-level masks for fine-grained semantic segmentation tasks, e.g., human parsing, remains a challenging task. The ambiguous boundary between different semantic parts and those categories with similar appearances are usually confusing for annotators, leading to incorrect labels in ground-truth masks. These label noises will inevitably harm the training process and decrease the performance of the learned models. To tackle this issue, we introduce a noise-tolerant method in this work, called Self-Correction for Human Parsing (SCHP), to progressively promote the reliability of the supervised labels as well as the learned models. In particular, starting from a model trained with inaccurate annotations as initialization, we design a cyclically learning scheduler to infer more reliable pseudo masks by iteratively aggregating the current learned model with the former sub-optimal one in an online manner. Besides, those correspondingly corrected labels can in turn to further boost the model performance. In this way, the models and the labels will reciprocally become more robust and accurate during the self-correction learning cycles. Our SCHP is model-agnostic and can be applied to any human parsing models for further enhancing their performance. Extensive experiments on four human parsing models, including Deeplab V3+, CE2P, OCR and CE2P+, well demonstrate the effectiveness of the proposed SCHP. We achieve the new state-of-the-art results on 6 benchmarks, including LIP, Pascal-Person-Part and ATR for single human parsing, CIHP and MHP for multi-person human parsing and VIP for video human parsing tasks. In addition, benefiting the superiority of SCHP, we achieved the 1st place on all the three human parsing tracks in the 3rd Look Into Person Challenge. The code is available at https://github.com/PeikeLi/Self-Correction-Human-Parsing.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Oron Ashual
2. Lior Wolf
3. Zhiwei Liu
4. Ming Tang
5. Haiyun Guo
6. Jinqiao Wang
7. Kuan Zhu
8. Oran Gafni

In Computer Vision and Pattern Recognition

1. Oron Ashual
2. Oran Gafni
3. Jinqiao Wang
4. Ming Tang
5. Lior Wolf
6. Zhiwei Liu
7. Haiyun Guo
8. Kuan Zhu

Citations in the corpus

• Make-A-Scene: Scene-Based Text-to-Image Generation with Human Priors (2022, neutral): “…outputs of VQ-SEG are m channels, representing the number of classes for all semantic segmentation groups m = m p + m h + m f + 1 , where m p , m h , m f are the number of categories for the panoptic segmentation [63], human segmentation [35], and face segmentation extracted with [5] respectively.”
• Consistent Structural Relation Learning for Zero-Shot Segmentation (2020, unknown): “Generalized Zero-shot Semantic Segmentation Semantic segmentation under fully supervised paradigm [34, 35, 36, 37, 38, 39] and domain adaptation scheme [40, 41, 42] are extensively studied.”
• Single-Shot Freestyle Dance Reenactment (2020, methodology): “(vi) A human parsing network HP [24] is used to extract the body in the target image.”
• Identity-Guided Human Semantic Parsing for Person Re-Identification (2020, methodology): “First, we visualize our pseudo-part-labels under different K and show the comparison with SCHP [21] in Figure 4, which validates that ISP can recognize the personal belongings (e.g. backpacks and reticule) as one human part while the pre-trained parsing model cannot.”