AIParsing: Anchor-free Instance-level Human Parsing

• URL: http://arxiv.org/abs/2207.06854v1
• Date: Thu, 14 Jul 2022 12:19:32 GMT
• Title: AIParsing: Anchor-free Instance-level Human Parsing
• Authors: Sanyi Zhang, Xiaochun Cao, Guo-Jun Qi, Zhanjie Song, and Jie Zhou
• Abstract summary: 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. Our method achieves the best global-level and instance-level performance over state-of-the-art one-stage top-down alternatives.
• Score: 98.80740676794254
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• DROP: Decouple Re-Identification and Human Parsing with Task-specific Features for Occluded Person Re-identification [15.910080319118498]
  The paper introduces the Decouple Re-identificatiOn and human Parsing (DROP) method for occluded person re-identification (ReID) Unlike mainstream approaches using global features for simultaneous multi-task learning of ReID and human parsing, DROP argues that the inferior performance of the former is due to distinct requirements for ReID and human parsing features. Experimental results highlight the efficacy of DROP, especially achieving a Rank-1 accuracy of 76.8% on Occluded-Duke, surpassing two mainstream methods.
  arXiv  Detail & Related papers  (2024-01-31T17:54:43Z)
• COMICS: End-to-end Bi-grained Contrastive Learning for Multi-face Forgery Detection [56.7599217711363]
  Face forgery recognition methods can only process one face at a time. Most face forgery recognition methods can only process one face at a time. We propose COMICS, an end-to-end framework for multi-face forgery detection.
  arXiv  Detail & Related papers  (2023-08-03T03:37:13Z)
• Integrating Human Parsing and Pose Network for Human Action Recognition [12.308394270240463]
  We introduce human parsing feature map as a novel modality for action recognition. We propose Integrating Human Parsing and Pose Network (IPP-Net) for action recognition. IPP-Net is the first to leverage both skeletons and human parsing feature maps dualbranch approach.
  arXiv  Detail & Related papers  (2023-07-16T07:58:29Z)
• Technical Report: Disentangled Action Parsing Networks for Accurate Part-level Action Parsing [65.87931036949458]
  Part-level Action Parsing aims at part state parsing for boosting action recognition in videos. We present a simple yet effective approach, named disentangled action parsing (DAP)
  arXiv  Detail & Related papers  (2021-11-05T02:29:32Z)
• LabOR: Labeling Only if Required for Domain Adaptive Semantic Segmentation [79.96052264984469]
  We propose a human-in-the-loop approach to adaptively give scarce labels to points that a UDA model is uncertain about. We show the advantages of this new framework for domain adaptive semantic segmentation while minimizing human labor costs.
  arXiv  Detail & Related papers  (2021-08-12T07:35:40Z)
• Mining the Benefits of Two-stage and One-stage HOI Detection [26.919979955155664]
  Two-stage methods have dominated Human-Object Interaction (HOI) detection for several years. One-stage methods are challenging to make an appropriate trade-off on multi-task learning, i.e., object detection, and interaction classification. We propose a novel one-stage framework with disentangling human-object detection and interaction classification in a cascade manner.
  arXiv  Detail & Related papers  (2021-08-11T07:38:09Z)
• End-to-end One-shot Human Parsing [91.5113227694443]
  One-shot human parsing (OSHP) task requires parsing humans into an open set of classes defined by any test example. End-to-end One-shot human Parsing Network (EOP-Net) proposed. EOP-Net outperforms representative one-shot segmentation models by large margins.
  arXiv  Detail & Related papers  (2021-05-04T01:35:50Z)
• Differentiable Multi-Granularity Human Representation Learning for Instance-Aware Human Semantic Parsing [131.97475877877608]
  A new bottom-up regime is proposed to learn category-level human semantic segmentation and multi-person pose estimation in a joint and end-to-end manner. It is a compact, efficient and powerful framework that exploits structural information over different human granularities. Experiments on three instance-aware human datasets show that our model outperforms other bottom-up alternatives with much more efficient inference.
  arXiv  Detail & Related papers  (2021-03-08T06:55:00Z)
• Nondiscriminatory Treatment: a straightforward framework for multi-human parsing [14.254424142949741]
  Multi-human parsing aims to segment every body part of every human instance. We present an end-to-end and box-free pipeline from a new and more human-intuitive perspective. Experiments show that our network performs superiorly against state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-01-26T16:31:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.