Papers › Intra-Batch Supervision for Panoptic Segmentation on High-Resolution Images

Intra-Batch Supervision for Panoptic Segmentation on High-Resolution Images

17 Apr 2023IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2023 1arXiv:2304.08222archive 2025-07-28

Daan de Geus, Gijs Dubbelman

Unified panoptic segmentation methods are achieving state-of-the-art results on several datasets. To achieve these results on high-resolution datasets, these methods apply crop-based training. In this work, we find that, although crop-based training is advantageous in general, it also has a harmful side-effect. Specifically, it limits the ability of unified networks to discriminate between large object instances, causing them to make predictions that are confused between multiple instances. To solve this, we propose Intra-Batch Supervision (IBS), which improves a network's ability to discriminate between instances by introducing additional supervision using multiple images from the same batch. We show that, with our IBS, we successfully address the confusion problem and consistently improve the performance of unified networks. For the high-resolution Cityscapes and Mapillary Vistas datasets, we achieve improvements of up to +2.5 on the Panoptic Quality for thing classes, and even more considerable gains of up to +5.8 on both the pixel accuracy and pixel precision, which we identify as better metrics to capture the confusion problem.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

DdeGeus/Mask2Former-IBS pytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Masked-attention Mask Transformer for Universal Image Segmentation (arXiv:2112.01527; that paper's own run record: 7 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 6 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
DdeGeus/PanopticFCN-IBS pytorchSyntology: not harvested 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

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

Tasks

Panoptic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Panoptic Segmentation Cityscapes val Mask2Former + Intra-Batch Supervision (ResNet-50) PQ 62.4 #19 of 37 Archive leaderboard report
Panoptic Segmentation Cityscapes val Mask2Former + Intra-Batch Supervision (ResNet-50) PQst 67.3 #19 of 37 Archive leaderboard report
Panoptic Segmentation Cityscapes val Mask2Former + Intra-Batch Supervision (ResNet-50) PQth 54.7 #19 of 37 Archive leaderboard report
Panoptic Segmentation Mapillary val Mask2Former + Intra-Batch Supervision (ResNet-50) PQ 42.2 #5 of 13 Archive leaderboard report
Panoptic Segmentation Mapillary val Mask2Former + Intra-Batch Supervision (ResNet-50) PQst 52.0 #5 of 13 Archive leaderboard report
Panoptic Segmentation Mapillary val Mask2Former + Intra-Batch Supervision (ResNet-50) PQth 34.9 #5 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