Papers › L2G: A Simple Local-to-Global Knowledge Transfer Framework for Weakly Supervised...

L2G: A Simple Local-to-Global Knowledge Transfer Framework for Weakly Supervised Semantic Segmentation

7 Apr 2022CVPR 2022 1arXiv:2204.03206archive 2025-07-28

Peng-Tao Jiang, YuQi Yang, Qibin Hou, Yunchao Wei

Mining precise class-aware attention maps, a.k.a, class activation maps, is essential for weakly supervised semantic segmentation. In this paper, we present L2G, a simple online local-to-global knowledge transfer framework for high-quality object attention mining. We observe that classification models can discover object regions with more details when replacing the input image with its local patches. Taking this into account, we first leverage a local classification network to extract attentions from multiple local patches randomly cropped from the input image. Then, we utilize a global network to learn complementary attention knowledge across multiple local attention maps online. Our framework conducts the global network to learn the captured rich object detail knowledge from a global view and thereby produces high-quality attention maps that can be directly used as pseudo annotations for semantic segmentation networks. Experiments show that our method attains 72.1% and 44.2% mIoU scores on the validation set of PASCAL VOC 2012 and MS COCO 2014, respectively, setting new state-of-the-art records. Code is available at https://github.com/PengtaoJiang/L2G.

PaperPDFConference PDFCode

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

Code

pengtaojiang/l2g officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

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

Tasks

ObjectSemantic SegmentationTransfer LearningWeakly supervised Semantic SegmentationWeakly-Supervised Semantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Weakly-Supervised Semantic Segmentation COCO 2014 val L2G (DeepLabV2-ResNet101) mIoU 44.2 #19 of 39 Archive leaderboard report
Weakly-Supervised Semantic Segmentation PASCAL VOC 2012 test L2G (ResNet101, DeepLab-LargeFOV) Mean IoU 73.0 #17 of 60 Archive leaderboard report
Weakly-Supervised Semantic Segmentation PASCAL VOC 2012 val L2G (ResNet101, DeepLab-v2) Mean IoU 72.1 #20 of 73 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