Papers › Label-PEnet: Sequential Label Propagation and Enhancement Networks for Weakly...

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

7 Oct 2019ICCV 2019 10arXiv:1910.02624archive 2025-07-28

Weifeng Ge, Sheng Guo, Weilin Huang, Matthew R. Scott

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.

PaperPDFConference PDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

General ClassificationImage-level Supervised Instance SegmentationInstance SegmentationMUlTI-LABEL-ClASSIFICATIONMulti-Label ClassificationObjectObject DetectionSemantic SegmentationWeakly-supervised instance segmentationobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image-level Supervised Instance Segmentation PASCAL VOC 2012 val Label-PEnet mAP@0.25 49.2 #11 of 13 Archive leaderboard report
Image-level Supervised Instance Segmentation PASCAL VOC 2012 val Label-PEnet mAP@0.5 30.2 #11 of 13 Archive leaderboard report
Image-level Supervised Instance Segmentation PASCAL VOC 2012 val Label-PEnet mAP@0.75 12.9 #11 of 13 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections