# PCAMs: Weakly Supervised Semantic Segmentation Using Point Supervision

arXiv: https://arxiv.org/abs/2007.05615 · HTML: https://mlsanity.com/paper/2007.05615/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Jul 2020.

## Built on by (most cited first, 15 of 15)

- [Learning Action Completeness from Points for Weakly-supervised Temporal Action Localization](https://mlsanity.com/paper/2108.05029/) (2021)
- [EarthMarker: A Visual Prompting Multi-modal Large Language Model for Remote Sensing](https://mlsanity.com/paper/2407.13596/) (2024)
- [SATS: Self-Attention Transfer for Continual Semantic Segmentation](https://mlsanity.com/paper/2203.07667/) (2022)
- [From colouring-in to pointillism: revisiting semantic segmentation supervision](https://mlsanity.com/paper/2210.14142/) (2022)
- [Monte Carlo Linear Clustering with Single-Point Supervision is Enough for Infrared Small Target Detection](https://mlsanity.com/paper/2304.04442/) (2023)
- [Generative Transformer for Accurate and Reliable Salient Object Detection](https://mlsanity.com/paper/2104.10127/) (2021)
- [LiDAR-Camera Panoptic Segmentation via Geometry-Consistent and Semantic-Aware Alignment](https://mlsanity.com/paper/2308.01686/) (2023)
- [Challenges for machine learning in clinical translation of big data imaging studies](https://mlsanity.com/paper/2107.05630/) (2021)
- [STRAP: Structured Object Affordance Segmentation with Point Supervision](https://mlsanity.com/paper/2304.08492/) (2023)
- [Context-Driven Detection of Invertebrate Species in Deep-Sea Video](https://mlsanity.com/paper/2206.00718/) (2022)
- [Learning from the Web: Language Drives Weakly-Supervised Incremental Learning for Semantic Segmentation](https://mlsanity.com/paper/2407.13363/) (2024)
- [SL3D: Self-supervised-Self-labeled 3D Recognition](https://mlsanity.com/paper/2210.16810/) (2022)
- [Learning Class-Agnostic Pseudo Mask Generation for Box-Supervised Semantic Segmentation](https://mlsanity.com/paper/2103.05463/) (2021)
- [Semantic Segmentation by Semantic Proportions](https://mlsanity.com/paper/2305.15608/) (2023)
- [Ensemble Foreground Management for Unsupervised Object Discovery](https://mlsanity.com/paper/2507.20860/) (2025)

## Abstract (arXiv)

Current state of the art methods for generating semantic segmentation rely heavily on a large set of images that have each pixel labeled with a class of interest label or background. Coming up with such labels, especially in domains that require an expert to do annotations, comes at a heavy cost in time and money. Several methods have shown that we can learn semantic segmentation from less expensive image-level labels, but the effectiveness of point level labels, a healthy compromise between all pixels labelled and none, still remains largely unexplored. This paper presents a novel procedure for producing semantic segmentation from images given some point level annotations. This method includes point annotations in the training of a convolutional neural network (CNN) for producing improved localization and class activation maps. Then, we use another CNN for predicting semantic affinities in order to propagate rough class labels and create pseudo semantic segmentation labels. Finally, we propose training a CNN that is normally fully supervised using our pseudo labels in place of ground truth labels, which further improves performance and simplifies the inference process by requiring just one CNN during inference rather than two. Our method achieves state of the art results for point supervised semantic segmentation on the PASCAL VOC 2012 dataset citeeveringham2010pascal, even outperforming state of the art methods for stronger bounding box and squiggle supervision.