</> Code with Papers by Syntology

Papers › Learning to Fuse Things and Stuff

Learning to Fuse Things and Stuff

4 Dec 2018arXiv:1812.01192archive 2025-07-28

Jie Li, Allan Raventos, Arjun Bhargava, Takaaki Tagawa, Adrien Gaidon

We propose an end-to-end learning approach for panoptic segmentation, a novel task unifying instance (things) and semantic (stuff) segmentation. Our model, TASCNet, uses feature maps from a shared backbone network to predict in a single feed-forward pass both things and stuff segmentations. We explicitly constrain these two output distributions through a global things and stuff binary mask to enforce cross-task consistency. Our proposed unified network is competitive with the state of the art on several benchmarks for panoptic segmentation as well as on the individual semantic and instance segmentation tasks.

PaperPDF

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

Instance SegmentationPanoptic SegmentationSegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Panoptic Segmentation COCO test-dev TASCNet PQ 40.7 #33 of 38 Archive leaderboard report
Panoptic Segmentation COCO test-dev TASCNet PQst 31.0 #33 of 38 Archive leaderboard report
Panoptic Segmentation COCO test-dev TASCNet PQth 47.0 #33 of 38 Archive leaderboard report
Panoptic Segmentation Cityscapes val TASCNet (ResNet-50, multi-scale) AP 39 #27 of 37 Archive leaderboard report
Panoptic Segmentation Cityscapes val TASCNet (ResNet-50, multi-scale) PQ 60.4 #27 of 37 Archive leaderboard report
Panoptic Segmentation Cityscapes val TASCNet (ResNet-50, multi-scale) PQst 63.3 #27 of 37 Archive leaderboard report
Panoptic Segmentation Cityscapes val TASCNet (ResNet-50, multi-scale) PQth 56.1 #27 of 37 Archive leaderboard report
Panoptic Segmentation Cityscapes val TASCNet (ResNet-50, multi-scale) mIoU 78 #27 of 37 Archive leaderboard report
Panoptic Segmentation Cityscapes val TASCNet (ResNet-50) AP 37.6 #29 of 37 Archive leaderboard report
Panoptic Segmentation Cityscapes val TASCNet (ResNet-50) PQ 59.2 #29 of 37 Archive leaderboard report
Panoptic Segmentation Cityscapes val TASCNet (ResNet-50) PQst 61.5 #29 of 37 Archive leaderboard report
Panoptic Segmentation Cityscapes val TASCNet (ResNet-50) PQth 56 #29 of 37 Archive leaderboard report
Panoptic Segmentation Cityscapes val TASCNet (ResNet-50) mIoU 77.8 #29 of 37 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.

Methods

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionGlobal Average PoolingKaiming InitializationMax PoolingReLUResidual BlockResidual Connection

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