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

Code

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

Fei-dong/SOLO_SORT mentioned on GitHubpytorchNOASSERTION report
MY-Swich/SOLO mentioned on GitHubpytorchNOASSERTION report
MY-Swich/SOLO_my mentioned on GitHubpytorchNOASSERTION report
MY-Swich/solo-len mentioned on GitHubpytorchNOASSERTION report
MaiHon/Solo mentioned on GitHubpytorch report
Pxtri2156/AdelaiDet_v2 mentioned on GitHubpytorch report
TengFeiHan0/Instance-Wise-Depth mentioned on GitHubpytorchNOASSERTION report
WXinlong/SOLO mentioned on GitHubpaddleNOASSERTION report
XXXVincent/SOLO mentioned on GitHubpytorchApache-2.0 report
aim-uofa/AdelaiDet mentioned on GitHubpytorchNOASSERTION report
aim-uofa/adet mentioned on GitHubpytorch report
blueardour/AdelaiDet mentioned on GitHubpytorchNOASSERTION report
divyachandana/solo-semantic-segmentation mentioned on GitHubpytorchNOASSERTION report
dqxiu/kassess mentioned on GitHubpytorch report
hades12580/solov2_mmdet mentioned on GitHubpytorchNOASSERTION report
hukefei/SOLO-master mentioned on GitHubpytorch report
mvpzhangqiu/SOLOV2 mentioned on GitHubpytorchNOASSERTION report
quanghona/SOLO_tf2 mentioned on GitHubtfMIT report
quangvy2703/ABCNet-ESRGAN-SRTEXT mentioned on GitHubpytorchNOASSERTION report
trhieu310/customDataset mentioned on GitHubpytorchNOASSERTION report
zhaozhijie1997/Unifed-Lane-and-Traffic-Sign-detection mentioned on GitHubpytorchNOASSERTION report
zhubinQAQ/Ins mentioned on GitHubpytorchNOASSERTION report
open-mmlab/mmdetection pytorchApache-2.0 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

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