# Gated CRF Loss for Weakly Supervised Semantic Image Segmentation

arXiv: https://arxiv.org/abs/1906.04651 · HTML: https://mlsanity.com/paper/1906.04651/

## Key facts

- Cited by 40 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Jun 2019.

## Built on by (most cited first, 30 of 40)

- [Tree Energy Loss: Towards Sparsely Annotated Semantic Segmentation](https://mlsanity.com/paper/2203.10739/) (2022)
- [Weakly-Supervised Camouflaged Object Detection with Scribble Annotations](https://mlsanity.com/paper/2207.14083/) (2022)
- [Weak-Mamba-UNet: Visual Mamba Makes CNN and ViT Work Better for Scribble-based Medical Image Segmentation](https://mlsanity.com/paper/2402.10887/) (2024)
- [Weakly-Supervised Salient Object Detection Using Point Supervision](https://mlsanity.com/paper/2203.11652/) (2022)
- [Generative Transformer for Accurate and Reliable Salient Object Detection](https://mlsanity.com/paper/2104.10127/) (2021)
- [S2ME: Spatial-Spectral Mutual Teaching and Ensemble Learning for Scribble-supervised Polyp Segmentation](https://mlsanity.com/paper/2306.00451/) (2023)
- [Seminar Learning for Click-Level Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2108.13393/) (2021)
- [PyMIC: A deep learning toolkit for annotation-efficient medical image segmentation](https://mlsanity.com/paper/2208.09350/) (2022)
- [Fully and Weakly Supervised Referring Expression Segmentation with End-to-End Learning](https://mlsanity.com/paper/2212.10278/) (2022)
- [Weakly Supervised Video Salient Object Detection via Point Supervision](https://mlsanity.com/paper/2207.07269/) (2022)
- [Learning Camouflaged Object Detection from Noisy Pseudo Label](https://mlsanity.com/paper/2407.13157/) (2024)
- [STRAP: Structured Object Affordance Segmentation with Point Supervision](https://mlsanity.com/paper/2304.08492/) (2023)
- [Ultrasound Nodule Segmentation Using Asymmetric Learning with Simple Clinical Annotation](https://mlsanity.com/paper/2404.14852/) (2024)
- [ZScribbleSeg: Zen and the Art of Scribble Supervised Medical Image Segmentation](https://mlsanity.com/paper/2301.04882/) (2023)
- [Scribble-based 3D Multiple Abdominal Organ Segmentation via Triple-branch Multi-dilated Network with Pixel- and Class-wise Consistency](https://mlsanity.com/paper/2309.09730/) (2023)
- [Label-efficient Segmentation via Affinity Propagation](https://mlsanity.com/paper/2310.10533/) (2023)
- [SAM-Driven Weakly Supervised Nodule Segmentation with Uncertainty-Aware Cross Teaching](https://mlsanity.com/paper/2407.13553/) (2024)
- [Dynamic Feature Regularized Loss for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2108.01296/) (2021)
- [Segmenting across places: The need for fair transfer learning with satellite imagery](https://mlsanity.com/paper/2204.04358/) (2022)
- [3SD: Self-Supervised Saliency Detection With No Labels](https://mlsanity.com/paper/2203.04478/) (2022)
- [WeClick: Weakly-Supervised Video Semantic Segmentation with Click Annotations](https://mlsanity.com/paper/2107.03088/) (2021)
- [Annotation by Clicks: A Point-Supervised Contrastive Variance Method for Medical Semantic Segmentation](https://mlsanity.com/paper/2212.08774/) (2022)
- [Unifying and Personalizing Weakly-supervised Federated Medical Image Segmentation via Adaptive Representation and Aggregation](https://mlsanity.com/paper/2304.05635/) (2023)
- [Semantic Connectivity-Driven Pseudo-labeling for Cross-domain Segmentation](https://mlsanity.com/paper/2312.06331/) (2023)
- [ProCNS: Progressive Prototype Calibration and Noise Suppression for Weakly-Supervised Medical Image Segmentation](https://mlsanity.com/paper/2401.14074/) (2024)
- [HarmonySeg: Tubular Structure Segmentation with Deep-Shallow Feature Fusion and Growth-Suppression Balanced Loss](https://mlsanity.com/paper/2504.07827/) (2025)
- [Beyond Fully Supervised Pixel Annotations: Scribble-Driven Weakly-Supervised Framework for Image Manipulation Localization](https://mlsanity.com/paper/2507.13018/) (2025)
- [SA-MixNet: Structure-aware Mixup and Invariance Learning for Scribble-supervised Road Extraction in Remote Sensing Images](https://mlsanity.com/paper/2403.01381/) (2024)
- [ScribbleVS: Scribble-Supervised Medical Image Segmentation via Dynamic Competitive Pseudo Label Selection](https://mlsanity.com/paper/2411.10237/) (2024)
- [Synthesize Boundaries: A Boundary-aware Self-consistent Framework for Weakly Supervised Salient Object Detection](https://mlsanity.com/paper/2212.01764/) (2022)

## Abstract (arXiv)

State-of-the-art approaches for semantic segmentation rely on deep convolutional neural networks trained on fully annotated datasets, that have been shown to be notoriously expensive to collect, both in terms of time and money. To remedy this situation, weakly supervised methods leverage other forms of supervision that require substantially less annotation effort, but they typically present an inability to predict precise object boundaries due to approximate nature of the supervisory signals in those regions. While great progress has been made in improving the performance, many of these weakly supervised methods are highly tailored to their own specific settings. This raises challenges in reusing algorithms and making steady progress. In this paper, we intentionally avoid such practices when tackling weakly supervised semantic segmentation. In particular, we train standard neural networks with partial cross-entropy loss function for the labeled pixels and our proposed Gated CRF loss for the unlabeled pixels. The Gated CRF loss is designed to deliver several important assets: 1) it enables flexibility in the kernel construction to mask out influence from undesired pixel positions; 2) it offloads learning contextual relations to CNN and concentrates on semantic boundaries; 3) it does not rely on high-dimensional filtering and thus has a simple implementation. Throughout the paper we present the advantages of the loss function, analyze several aspects of weakly supervised training, and show that our `purist' approach achieves state-of-the-art performance for both click-based and scribble-based annotations.