Abstract | ||
---|---|---|
Most state-of-the-art instance-level human parsing models adopt two-stage anchor-based detectors and, therefore, cannot avoid the heuristic anchor box design and the lack of analysis on a pixel level. To address these two issues, we have designed an instance-level human parsing network which is anchor-free and solvable on a pixel level. It consists of two simple sub-networks: an anchor-free detection head for bounding box predictions and an edge-guided parsing head for human segmentation. The anchor-free detector head inherits the pixel-like merits and effectively avoids the sensitivity of hyper-parameters as proved in object detection applications. By introducing the part-aware boundary clue, the edge-guided parsing head is capable to distinguish adjacent human parts from among each other up to 58 parts in a single human instance, even overlapping instances. Meanwhile, a refinement head integrating box-level score and part-level parsing quality is exploited to improve the quality of the parsing results. Experiments on two multiple human parsing datasets (i.e., CIHP and LV-MHP-v2.0) and one video instance-level human parsing dataset (i.e., VIP) show that our method achieves the best global-level and instance-level performance over state-of-the-art one-stage top-down alternatives. |
Year | DOI | Venue |
---|---|---|
2022 | 10.1109/TIP.2022.3192989 | IEEE TRANSACTIONS ON IMAGE PROCESSING |
Keywords | DocType | Volume |
Task analysis, Detectors, Image edge detection, Semantics, Head, Proposals, Object detection, Instance-level human parsing, anchor-free, edge-guided parsing, parsing refinement, video human parsing | Journal | 31 |
Issue | ISSN | Citations |
1 | 1057-7149 | 0 |
PageRank | References | Authors |
0.34 | 0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Sanyi Zhang | 1 | 0 | 1.01 |
Xiaochun Cao | 2 | 1986 | 131.55 |
Guo-Jun Qi | 3 | 2778 | 119.78 |
Zhanjie Song | 4 | 0 | 0.34 |
Jie Zhou | 5 | 2103 | 190.17 |