# AIParsing: Anchor-free Instance-level Human Parsing

Source: [AIParsing: Anchor-free Instance-level Human Parsing](<https://www.sota2.com/research/paper/68fa6d651e209131cea3977d>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T00:32:23.745Z

Authors: Sanyi Zhang, Xiaochun Cao, Guo-Jun Qi, Zhanjie Song, Jie Zhou

Published: 2022-07-14T12:19:32.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Human Parsing on MHP v2.0 (val)](<https://www.sota2.com/research/sota/human-parsing-on-mhp-v2-0-val.md>): Human Parsing; MHP v2.0 (val); APp50: 43.2.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2207.06854>)

[PDF](<https://arxiv.org/pdf/2207.06854.pdf>)