# Label-PEnet: Sequential Label Propagation and Enhancement Networks for Weakly Supervised Instance Segmentation

arXiv: https://arxiv.org/abs/1910.02624 · HTML: https://mlsanity.com/paper/1910.02624/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Oct 2019.

## Built on by (most cited first, 18 of 18)

- [BBAM: Bounding Box Attribution Map for Weakly Supervised Semantic and Instance Segmentation](https://mlsanity.com/paper/2103.08907/) (2021)
- [Open-Vocabulary Instance Segmentation via Robust Cross-Modal Pseudo-Labeling](https://mlsanity.com/paper/2111.12698/) (2021)
- [Pointly-Supervised Instance Segmentation](https://mlsanity.com/paper/2104.06404/) (2021)
- [A Survey on Label-efficient Deep Image Segmentation: Bridging the Gap between Weak Supervision and Dense Prediction](https://mlsanity.com/paper/2207.01223/) (2022)
- [Beyond Semantic to Instance Segmentation: Weakly-Supervised Instance Segmentation via Semantic Knowledge Transfer and Self-Refinement](https://mlsanity.com/paper/2109.09477/) (2021)
- [Weakly-supervised Instance Segmentation via Class-agnostic Learning with Salient Images](https://mlsanity.com/paper/2104.01526/) (2021)
- [Weakly Supervised Instance Segmentation for Videos with Temporal Mask Consistency](https://mlsanity.com/paper/2103.12886/) (2021)
- [Mask-free OVIS: Open-Vocabulary Instance Segmentation without Manual Mask Annotations](https://mlsanity.com/paper/2303.16891/) (2023)
- [Solve the Puzzle of Instance Segmentation in Videos: A Weakly Supervised Framework with Spatio-Temporal Collaboration](https://mlsanity.com/paper/2212.07592/) (2022)
- [WeakSAM: Segment Anything Meets Weakly-supervised Instance-level Recognition](https://mlsanity.com/paper/2402.14812/) (2024)
- [LWSIS: LiDAR-guided Weakly Supervised Instance Segmentation for Autonomous Driving](https://mlsanity.com/paper/2212.03504/) (2022)
- [Complete Instances Mining for Weakly Supervised Instance Segmentation](https://mlsanity.com/paper/2402.07633/) (2024)
- [Cyclic Learning: Bridging Image-level Labels and Nuclei Instance Segmentation](https://mlsanity.com/paper/2306.02691/) (2023)
- [MWSIS: Multimodal Weakly Supervised Instance Segmentation with 2D Box Annotations for Autonomous Driving](https://mlsanity.com/paper/2312.06988/) (2023)
- [EM-Paste: EM-guided Cut-Paste with DALL-E Augmentation for Image-level Weakly Supervised Instance Segmentation](https://mlsanity.com/paper/2212.07629/) (2022)
- [Boosting Box-supervised Instance Segmentation with Pseudo Depth](https://mlsanity.com/paper/2403.01214/) (2024)
- [P2Seg: Pointly-supervised Segmentation via Mutual Distillation](https://mlsanity.com/paper/2401.09709/) (2024)
- [Hybrid supervised instance segmentation by learning label noise suppression](https://mlsanity.com/paper/2610.20412/) (2026)

## Abstract (arXiv)

Weakly-supervised instance segmentation aims to detect and segment object instances precisely, given imagelevel labels only. Unlike previous methods which are composed of multiple offline stages, we propose Sequential Label Propagation and Enhancement Networks (referred as Label-PEnet) that progressively transform image-level labels to pixel-wise labels in a coarse-to-fine manner. We design four cascaded modules including multi-label classification, object detection, instance refinement and instance segmentation, which are implemented sequentially by sharing the same backbone. The cascaded pipeline is trained alternatively with a curriculum learning strategy that generalizes labels from high-level images to low-level pixels gradually with increasing accuracy. In addition, we design a proposal calibration module to explore the ability of classification networks to find key pixels that identify object parts, which serves as a post validation strategy running in the inverse order. We evaluate the efficiency of our Label-PEnet in mining instance masks on standard benchmarks: PASCAL VOC 2007 and 2012. Experimental results show that Label-PEnet outperforms the state-of-the-art algorithms by a clear margin, and obtains comparable performance even with the fully-supervised approaches.