# Decoupled Multi-task Learning with Cyclical Self-Regulation for Face Parsing

arXiv: https://arxiv.org/abs/2203.14448 · HTML: https://mlsanity.com/paper/2203.14448/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 50 references that are in the map.
- First posted on arXiv 28 Mar 2022.

## Builds on (most cited first, 29 of 29)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [Pyramid Scene Parsing Network](https://mlsanity.com/paper/1612.01105/) (2016)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics](https://mlsanity.com/paper/1705.07115/) (2017)
- [Multi-Scale Context Aggregation by Dilated Convolutions](https://mlsanity.com/paper/1511.07122/) (2015)
- [MaskGAN: Towards Diverse and Interactive Facial Image Manipulation](https://mlsanity.com/paper/1907.11922/) (2019)
- [Cross-stitch Networks for Multi-task Learning](https://mlsanity.com/paper/1604.03539/) (2016)
- [Rethinking Pre-training and Self-training](https://mlsanity.com/paper/2006.06882/) (2020)
- [FSGAN: Subject Agnostic Face Swapping and Reenactment](https://mlsanity.com/paper/1908.05932/) (2019)
- [Billion-scale semi-supervised learning for image classification](https://mlsanity.com/paper/1905.00546/) (2019)
- [UberNet: Training a `Universal' Convolutional Neural Network for Low-, Mid-, and High-Level Vision using Diverse Datasets and Limited Memory](https://mlsanity.com/paper/1609.02132/) (2016)
- [Self-Correction for Human Parsing](https://mlsanity.com/paper/1910.09777/) (2019)
- [MultiNet: Real-time Joint Semantic Reasoning for Autonomous Driving](https://mlsanity.com/paper/1612.07695/) (2016)
- [In-Place Activated BatchNorm for Memory-Optimized Training of DNNs](https://mlsanity.com/paper/1712.02616/) (2017)
- [Devil in the Details: Towards Accurate Single and Multiple Human Parsing](https://mlsanity.com/paper/1809.05996/) (2018)
- [Dual Graph Convolutional Network for Semantic Segmentation](https://mlsanity.com/paper/1909.06121/) (2019)
- [Naive-Student: Leveraging Semi-Supervised Learning in Video Sequences for Urban Scene Segmentation](https://mlsanity.com/paper/2005.10266/) (2020)
- [Face Parsing with RoI Tanh-Warping](https://mlsanity.com/paper/1906.01342/) (2019)
- [Edge-aware Graph Representation Learning and Reasoning for Face Parsing](https://mlsanity.com/paper/2007.11240/) (2020)
- [RoI Tanh-polar Transformer Network for Face Parsing in the Wild](https://mlsanity.com/paper/2102.02717/) (2021)
- [Interlinked Convolutional Neural Networks for Face Parsing](https://mlsanity.com/paper/1806.02479/) (2018)
- [Face Parsing via Recurrent Propagation](https://mlsanity.com/paper/1708.01936/) (2017)
- [Fast Scene Understanding for Autonomous Driving](https://mlsanity.com/paper/1708.02550/) (2017)
- [A CNN Cascade for Landmark Guided Semantic Part Segmentation](https://mlsanity.com/paper/1609.09642/) (2016)
- [Face Parsing via a Fully-Convolutional Continuous CRF Neural Network](https://mlsanity.com/paper/1708.03736/) (2017)

## Built on by (most cited first, 26 of 26)

- [LayoutDiffuse: Adapting Foundational Diffusion Models for Layout-to-Image Generation](https://mlsanity.com/paper/2302.08908/) (2023)
- [3D Face Reconstruction with the Geometric Guidance of Facial Part Segmentation](https://mlsanity.com/paper/2312.00311/) (2023)
- [FaceXFormer: A Unified Transformer for Facial Analysis](https://mlsanity.com/paper/2403.12960/) (2024)
- [FaceXBench: Evaluating Multimodal LLMs on Face Understanding](https://mlsanity.com/paper/2501.10360/) (2025)
- [HiFace: High-Fidelity 3D Face Reconstruction by Learning Static and Dynamic Details](https://mlsanity.com/paper/2303.11225/) (2023)
- [WaveFace: Authentic Face Restoration with Efficient Frequency Recovery](https://mlsanity.com/paper/2403.12760/) (2024)
- [15M Multimodal Facial Image-Text Dataset](https://mlsanity.com/paper/2407.08515/) (2024)
- [Automatic Animation of Hair Blowing in Still Portrait Photos](https://mlsanity.com/paper/2309.14207/) (2023)
- [Faceptor: A Generalist Model for Face Perception](https://mlsanity.com/paper/2403.09500/) (2024)
- [Toward High Quality Facial Representation Learning](https://mlsanity.com/paper/2309.03575/) (2023)
- [Parameter Efficient Local Implicit Image Function Network for Face Segmentation](https://mlsanity.com/paper/2303.15122/) (2023)
- [ReliableSwap: Boosting General Face Swapping Via Reliable Supervision](https://mlsanity.com/paper/2306.05356/) (2023)
- [Symmetrical Flow Matching: Unified Image Generation, Segmentation, and Classification with Score-Based Generative Models](https://mlsanity.com/paper/2506.10634/) (2025)
- [When Multi-Task Learning Meets Partial Supervision: A Computer Vision Review](https://mlsanity.com/paper/2307.14382/) (2023)
- [S2TD-Face: Reconstruct a Detailed 3D Face with Controllable Texture from a Single Sketch](https://mlsanity.com/paper/2408.01218/) (2024)
- [Dual-Head Knowledge Distillation: Enhancing Logits Utilization with an Auxiliary Head](https://mlsanity.com/paper/2411.08937/) (2024)
- [M3Face: A Unified Multi-Modal Multilingual Framework for Human Face Generation and Editing](https://mlsanity.com/paper/2402.02369/) (2024)
- [Quality-guided Skin Tone Enhancement for Portrait Photography](https://mlsanity.com/paper/2406.15848/) (2024)
- [High-Quality Facial Albedo Generation for 3D Face Reconstruction from a Single Image using a Coarse-to-Fine Approach](https://mlsanity.com/paper/2506.13233/) (2025)
- [Unlocking the Potential of Diffusion Priors in Blind Face Restoration](https://mlsanity.com/paper/2508.08556/) (2025)
- [Fake-in-Facext: Towards Fine-Grained Explainable DeepFake Analysis](https://mlsanity.com/paper/2510.20531/) (2025)
- [SynthForge: Synthesizing High-Quality Face Dataset with Controllable 3D Generative Models](https://mlsanity.com/paper/2406.07840/) (2024)
- [Monocular Avatar Reconstruction via Cascaded Diffusion Priors and UV-Space Differentiable Shading](https://mlsanity.com/paper/2606.28144/) (2026)
- [S3POT: Contrast-Driven Face Occlusion Segmentation via Self-Supervised Prompt Learning](https://mlsanity.com/paper/2602.00635/) (2026)
- [A Backbone Benchmarking Study on Self-supervised Learning as a Auxiliary Task with Texture-based Local Descriptors for Face Analysis](https://mlsanity.com/paper/2603.22190/) (2026)
- [DIME: Scaling Facial Representation Learning via Differential Masked Autoencoding](https://mlsanity.com/paper/2610.17015/) (2026)

## Abstract (arXiv)

This paper probes intrinsic factors behind typical failure cases (e.g. spatial inconsistency and boundary confusion) produced by the existing state-of-the-art method in face parsing. To tackle these problems, we propose a novel Decoupled Multi-task Learning with Cyclical Self-Regulation (DML-CSR) for face parsing. Specifically, DML-CSR designs a multi-task model which comprises face parsing, binary edge, and category edge detection. These tasks only share low-level encoder weights without high-level interactions between each other, enabling to decouple auxiliary modules from the whole network at the inference stage. To address spatial inconsistency, we develop a dynamic dual graph convolutional network to capture global contextual information without using any extra pooling operation. To handle boundary confusion in both single and multiple face scenarios, we exploit binary and category edge detection to jointly obtain generic geometric structure and fine-grained semantic clues of human faces. Besides, to prevent noisy labels from degrading model generalization during training, cyclical self-regulation is proposed to self-ensemble several model instances to get a new model and the resulting model then is used to self-distill subsequent models, through alternating iterations. Experiments show that our method achieves the new state-of-the-art performance on the Helen, CelebAMask-HQ, and Lapa datasets. The source code is available at https://github.com/deepinsight/insightface/tree/master/parsing/dml_csr.