# Built-in Foreground/Background Prior for Weakly-Supervised Semantic Segmentation

arXiv: https://arxiv.org/abs/1609.00446 · HTML: https://mlsanity.com/paper/1609.00446/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Sep 2016.

## Built on by (most cited first, 21 of 21)

- [Mixed supervision for surface-defect detection: from weakly to fully supervised learning](https://mlsanity.com/paper/2104.06064/) (2021)
- [Weakly Supervised Semantic Segmentation by Pixel-to-Prototype Contrast](https://mlsanity.com/paper/2110.07110/) (2021)
- [Context Decoupling Augmentation for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2103.01795/) (2021)
- [A Survey on Autonomous Driving Datasets: Statistics, Annotation Quality, and a Future Outlook](https://mlsanity.com/paper/2401.01454/) (2024)
- [Regional Semantic Contrast and Aggregation for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2203.09653/) (2022)
- [Pseudo-mask Matters in Weakly-supervised Semantic Segmentation](https://mlsanity.com/paper/2108.12995/) (2021)
- [Background-Aware Pooling and Noise-Aware Loss for Weakly-Supervised Semantic Segmentation](https://mlsanity.com/paper/2104.00905/) (2021)
- [Uncertainty Estimation via Response Scaling for Pseudo-mask Noise Mitigation in Weakly-supervised Semantic Segmentation](https://mlsanity.com/paper/2112.07431/) (2021)
- [Learning Self-Supervised Low-Rank Network for Single-Stage Weakly and Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2203.10278/) (2022)
- [Saliency Guided Inter- and Intra-Class Relation Constraints for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2206.09554/) (2022)
- [Spatial Structure Constraints for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2401.11122/) (2024)
- [Multi-Granularity Denoising and Bidirectional Alignment for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2305.05154/) (2023)
- [Cross-Image Region Mining with Region Prototypical Network for Weakly Supervised Segmentation](https://mlsanity.com/paper/2108.07413/) (2021)
- [Knowledge Transfer with Simulated Inter-Image Erasing for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2407.02768/) (2024)
- [Point-supervised Single-cell Segmentation via Collaborative Knowledge Sharing](https://mlsanity.com/paper/2304.10671/) (2023)
- [Weakly Supervised Multi-Object Tracking and Segmentation](https://mlsanity.com/paper/2101.00667/) (2021)
- [ISIM: Iterative Self-Improved Model for Weakly Supervised Segmentation](https://mlsanity.com/paper/2211.12455/) (2022)
- [Masked Collaborative Contrast for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2305.08491/) (2023)
- [Object Preserving Siamese Network for Single Object Tracking on Point Clouds](https://mlsanity.com/paper/2301.12057/) (2023)
- [COMNet: Co-Occurrent Matching for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2309.16959/) (2023)
- [Image to Pseudo-Episode: Boosting Few-Shot Segmentation by Unlabeled Data](https://mlsanity.com/paper/2405.08765/) (2024)

## Abstract (arXiv)

Pixel-level annotations are expensive and time consuming to obtain. Hence, weak supervision using only image tags could have a significant impact in semantic segmentation. Recently, CNN-based methods have proposed to fine-tune pre-trained networks using image tags. Without additional information, this leads to poor localization accuracy. This problem, however, was alleviated by making use of objectness priors to generate foreground/background masks. Unfortunately these priors either require training pixel-level annotations/bounding boxes, or still yield inaccurate object boundaries. Here, we propose a novel method to extract markedly more accurate masks from the pre-trained network itself, forgoing external objectness modules. This is accomplished using the activations of the higher-level convolutional layers, smoothed by a dense CRF. We demonstrate that our method, based on these masks and a weakly-supervised loss, outperforms the state-of-the-art tag-based weakly-supervised semantic segmentation techniques. Furthermore, we introduce a new form of inexpensive weak supervision yielding an additional accuracy boost.