Papers › SOLO: Segmenting Objects by Locations

SOLO: Segmenting Objects by Locations

10 Dec 2019ECCV 2020 8arXiv:1912.04488archive 2025-07-28

Xinlong Wang, Tao Kong, Chunhua Shen, Yuning Jiang, Lei LI

We present a new, embarrassingly simple approach to instance segmentation in images. Compared to many other dense prediction tasks, e.g., semantic segmentation, it is the arbitrary number of instances that have made instance segmentation much more challenging. In order to predict a mask for each instance, mainstream approaches either follow the 'detect-thensegment' strategy as used by Mask R-CNN, or predict category masks first then use clustering techniques to group pixels into individual instances. We view the task of instance segmentation from a completely new perspective by introducing the notion of "instance categories", which assigns categories to each pixel within an instance according to the instance's location and size, thus nicely converting instance mask segmentation into a classification-solvable problem. Now instance segmentation is decomposed into two classification tasks. We demonstrate a much simpler and flexible instance segmentation framework with strong performance, achieving on par accuracy with Mask R-CNN and outperforming recent singleshot instance segmenters in accuracy. We hope that this very simple and strong framework can serve as a baseline for many instance-level recognition tasks besides instance segmentation.

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

24 repositories listed; official and paper-mentioned ones first.

Fei-dong/SOLO_SORT mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
MY-Swich/SOLO mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
MY-Swich/SOLO_my mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
MY-Swich/solo-len mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
MaiHon/Solo mentioned on GitHubpytorchSyntology: not harvested report
Pxtri2156/AdelaiDet_v2 mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Conditional Convolutions for Instance Segmentation (arXiv:2003.05664; that paper's own run record: 2 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; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
TengFeiHan0/Instance-Wise-Depth mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
WXinlong/SOLO mentioned on GitHubpaddleNOASSERTIONSyntology: not harvested report
XXXVincent/SOLO mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
aim-uofa/AdelaiDet mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
aim-uofa/adet mentioned on GitHubpytorchSyntology: not harvested report
blueardour/AdelaiDet mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
divyachandana/solo-semantic-segmentation mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
dqxiu/kassess mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to arXiv:2305.10519 (its page on Syntology; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
hades12580/solov2_mmdet mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
hukefei/SOLO-master mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to SOLOv2: Dynamic and Fast Instance Segmentation (arXiv:2003.10152; that paper's own run record: 23 ran (of which 4 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 0 violated, 12 with no contract checked; 10 where Syntology's instrument failed) · 15 unverified); nothing checks that they implement this paper's method. report
mvpzhangqiu/SOLOV2 mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
quanghona/SOLO_tf2 mentioned on GitHubtfMITSyntology: not harvested report
quangvy2703/ABCNet-ESRGAN-SRTEXT mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
trhieu310/customDataset mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
zhaozhijie1997/Unifed-Lane-and-Traffic-Sign-detection mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
zhubinQAQ/Ins mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
PaddlePaddle/PaddleDetection paddleSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to PP-YOLOE: An evolved version of YOLO (arXiv:2203.16250; that paper's own run record: 22 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 2 honoured, 0 violated, 17 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified); 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

ClusteringGeneral ClassificationInstance SegmentationSegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Instance Segmentation COCO test-dev SOLO(Res-DCN-101-FPN) AP50 62.7 #69 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev SOLO(Res-DCN-101-FPN) AP75 43.3 #69 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev SOLO(Res-DCN-101-FPN) APL 58.9 #69 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev SOLO(Res-DCN-101-FPN) APM 43.3 #69 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev SOLO(Res-DCN-101-FPN) APS 17.6 #69 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev SOLO(Res-DCN-101-FPN) mask AP 40.4 #69 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev SOLO (ResNet-DCN-101-FPN) AP50 62.7% #70 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev SOLO (ResNet-DCN-101-FPN) AP75 43.3% #70 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev SOLO (ResNet-DCN-101-FPN) APL 58.9% #70 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev SOLO (ResNet-DCN-101-FPN) APM 43.3% #70 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev SOLO (ResNet-DCN-101-FPN) APS 17.6% #70 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev SOLO (ResNet-DCN-101-FPN) mask AP 40.4% #70 of 112 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 InitializationMask R-CNNMax PoolingRPNReLUResidual BlockResidual ConnectionRoIAlignSoftmax

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