# Weakly Supervised Scene Parsing with Point-based Distance Metric Learning

arXiv: https://arxiv.org/abs/1811.02233 · HTML: https://mlsanity.com/paper/1811.02233/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Nov 2018.

## Built on by (most cited first, 30 of 33)

- [ReCo: Retrieve and Co-segment for Zero-shot Transfer](https://mlsanity.com/paper/2206.07045/) (2022)
- [Pointly-Supervised Instance Segmentation](https://mlsanity.com/paper/2104.06404/) (2021)
- [Points as Queries: Weakly Semi-supervised Object Detection by Points](https://mlsanity.com/paper/2104.07434/) (2021)
- [DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervision](https://mlsanity.com/paper/2105.06464/) (2021)
- [Mapping Degeneration Meets Label Evolution: Learning Infrared Small Target Detection with Single Point Supervision](https://mlsanity.com/paper/2304.01484/) (2023)
- [Tree Energy Loss: Towards Sparsely Annotated Semantic Segmentation](https://mlsanity.com/paper/2203.10739/) (2022)
- [Incremental Learning in Semantic Segmentation from Image Labels](https://mlsanity.com/paper/2112.01882/) (2021)
- [All you need are a few pixels: semantic segmentation with PixelPick](https://mlsanity.com/paper/2104.06394/) (2021)
- [Weakly-Supervised Salient Object Detection Using Point Supervision](https://mlsanity.com/paper/2203.11652/) (2022)
- [Pointly-Supervised Panoptic Segmentation](https://mlsanity.com/paper/2210.13950/) (2022)
- [Active Pointly-Supervised Instance Segmentation](https://mlsanity.com/paper/2207.11493/) (2022)
- [Seminar Learning for Click-Level Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2108.13393/) (2021)
- [Constraint and Union for Partially-Supervised Temporal Sentence Grounding](https://mlsanity.com/paper/2302.09850/) (2023)
- [Weakly Supervised Video Salient Object Detection via Point Supervision](https://mlsanity.com/paper/2207.07269/) (2022)
- [From Easy to Hard: Progressive Active Learning Framework for Infrared Small Target Detection with Single Point Supervision](https://mlsanity.com/paper/2412.11154/) (2024)
- [MFNet: Multi-class Few-shot Segmentation Network with Pixel-wise Metric Learning](https://mlsanity.com/paper/2111.00232/) (2021)
- [STRAP: Structured Object Affordance Segmentation with Point Supervision](https://mlsanity.com/paper/2304.08492/) (2023)
- [BoNuS: Boundary Mining for Nuclei Segmentation with Partial Point Labels](https://mlsanity.com/paper/2401.07437/) (2024)
- [Pointly-supervised 3D Scene Parsing with Viewpoint Bottleneck](https://mlsanity.com/paper/2109.08553/) (2021)
- [Learning Remote Sensing Object Detection with Single Point Supervision](https://mlsanity.com/paper/2305.14141/) (2023)
- [SASFormer: Transformers for Sparsely Annotated Semantic Segmentation](https://mlsanity.com/paper/2212.02019/) (2022)
- [RaSP: Relation-aware Semantic Prior for Weakly Supervised Incremental Segmentation](https://mlsanity.com/paper/2305.19879/) (2023)
- [Bayesian Active Learning for Semantic Segmentation](https://mlsanity.com/paper/2408.01694/) (2024)
- [Annotation by Clicks: A Point-Supervised Contrastive Variance Method for Medical Semantic Segmentation](https://mlsanity.com/paper/2212.08774/) (2022)
- [DPF: Learning Dense Prediction Fields with Weak Supervision](https://mlsanity.com/paper/2303.16890/) (2023)
- [Segment Anything Model for automated image data annotation: empirical studies using text prompts from Grounding DINO](https://mlsanity.com/paper/2406.19057/) (2024)
- [Hybrid Mask Generation for Infrared Small Target Detection with Single-Point Supervision](https://mlsanity.com/paper/2409.04011/) (2024)
- [Modeling the Background for Incremental and Weakly-Supervised Semantic Segmentation](https://mlsanity.com/paper/2201.13338/) (2022)
- [Boosting Weakly-Supervised Image Segmentation via Representation, Transform, and Compensator](https://mlsanity.com/paper/2309.00871/) (2023)
- [Weakly Supervised Visual-Auditory Fixation Prediction with Multigranularity Perception](https://mlsanity.com/paper/2112.13697/) (2021)

## Abstract (arXiv)

Semantic scene parsing is suffering from the fact that pixel-level annotations are hard to be collected. To tackle this issue, we propose a Point-based Distance Metric Learning (PDML) in this paper. PDML does not require dense annotated masks and only leverages several labeled points that are much easier to obtain to guide the training process. Concretely, we leverage semantic relationship among the annotated points by encouraging the feature representations of the intra- and inter-category points to keep consistent, i.e. points within the same category should have more similar feature representations compared to those from different categories. We formulate such a characteristic into a simple distance metric loss, which collaborates with the point-wise cross-entropy loss to optimize the deep neural networks. Furthermore, to fully exploit the limited annotations, distance metric learning is conducted across different training images instead of simply adopting an image-dependent manner. We conduct extensive experiments on two challenging scene parsing benchmarks of PASCAL-Context and ADE 20K to validate the effectiveness of our PDML, and competitive mIoU scores are achieved.