Papers › Per-Pixel Classification is Not All You Need for Semantic Segmentation

Per-Pixel Classification is Not All You Need for Semantic Segmentation

13 Jul 2021NeurIPS 2021 12arXiv:2107.06278archive 2025-07-28

Bowen Cheng, Alexander G. Schwing, Alexander Kirillov

Modern approaches typically formulate semantic segmentation as a per-pixel classification task, while instance-level segmentation is handled with an alternative mask classification. Our key insight: mask classification is sufficiently general to solve both semantic- and instance-level segmentation tasks in a unified manner using the exact same model, loss, and training procedure. Following this observation, we propose MaskFormer, a simple mask classification model which predicts a set of binary masks, each associated with a single global class label prediction. Overall, the proposed mask classification-based method simplifies the landscape of effective approaches to semantic and panoptic segmentation tasks and shows excellent empirical results. In particular, we observe that MaskFormer outperforms per-pixel classification baselines when the number of classes is large. Our mask classification-based method outperforms both current state-of-the-art semantic (55.6 mIoU on ADE20K) and panoptic segmentation (52.7 PQ on COCO) models.

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

facebookresearch/MaskFormer officialmentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
huggingface/transformers mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Attention Is All You Need (arXiv:1706.03762; that paper's own run record: 610 ran (of which 293 constructed an object rather than computing a result; 529 with no instrument failure: 45 honoured, 15 violated, 469 with no contract checked; 81 where Syntology's instrument failed) · 336 unverified), HuggingFace's Transformers: State-of-the-art Natural Language Processing (arXiv:1910.03771; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified), DeBERTa: Decoding-enhanced BERT with Disentangled Attention (arXiv:2006.03654; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 9 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
open-mmlab/mmdetection pytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to An Open and Comprehensive Pipeline for Unified Object Grounding and Detection (arXiv:2401.02361; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. 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

AllClassificationPanoptic SegmentationSegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Panoptic Segmentation ADE20K val MaskFormer (R101 + 6 Enc) PQ 35.7 #24 of 25 Archive leaderboard report
Panoptic Segmentation COCO minival MaskFormer (single-scale) PQ 52.7 #21 of 31 Archive leaderboard report
Panoptic Segmentation COCO minival MaskFormer (single-scale) PQst 44.0 #21 of 31 Archive leaderboard report
Panoptic Segmentation COCO minival MaskFormer (single-scale) PQth 58.5 #21 of 31 Archive leaderboard report
Panoptic Segmentation COCO minival MaskFormer (single-scale) RQ 63.5 #21 of 31 Archive leaderboard report
Panoptic Segmentation COCO minival MaskFormer (single-scale) SQ 81.8 #21 of 31 Archive leaderboard report
Panoptic Segmentation COCO test-dev MaskFormer (Swin-L) PQ 53.3 #9 of 38 Archive leaderboard report
Panoptic Segmentation COCO test-dev MaskFormer (Swin-L) PQst 44.5 #9 of 38 Archive leaderboard report
Panoptic Segmentation COCO test-dev MaskFormer (Swin-L) PQth 59.1 #9 of 38 Archive leaderboard report
Semantic Segmentation ADE20K MaskFormer(Swin-B) Validation mIoU 53.8 #73 of 235 Archive leaderboard report
Semantic Segmentation ADE20K MaskFormer(ResNet-101) Validation mIoU 48.1 #153 of 235 Archive leaderboard report
Semantic Segmentation ADE20K val MaskFormer (Swin-L, ImageNet-22k pretrain) mIoU 55.6 #28 of 95 Archive leaderboard report
Semantic Segmentation Mapillary val MaskFormer (ResNet-50) mIoU 55.4 #4 of 8 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