Papers › A novel Region of Interest Extraction Layer for Instance Segmentation

A novel Region of Interest Extraction Layer for Instance Segmentation

28 Apr 2020arXiv:2004.13665archive 2025-07-28

Leonardo Rossi, Akbar Karimi, Andrea Prati

Given the wide diffusion of deep neural network architectures for computer vision tasks, several new applications are nowadays more and more feasible. Among them, a particular attention has been recently given to instance segmentation, by exploiting the results achievable by two-stage networks (such as Mask R-CNN or Faster R-CNN), derived from R-CNN. In these complex architectures, a crucial role is played by the Region of Interest (RoI) extraction layer, devoted to extracting a coherent subset of features from a single Feature Pyramid Network (FPN) layer attached on top of a backbone. This paper is motivated by the need to overcome the limitations of existing RoI extractors which select only one (the best) layer from FPN. Our intuition is that all the layers of FPN retain useful information. Therefore, the proposed layer (called Generic RoI Extractor - GRoIE) introduces non-local building blocks and attention mechanisms to boost the performance. A comprehensive ablation study at component level is conducted to find the best set of algorithms and parameters for the GRoIE layer. Moreover, GRoIE can be integrated seamlessly with every two-stage architecture for both object detection and instance segmentation tasks. Therefore, the improvements brought about by the use of GRoIE in different state-of-the-art architectures are also evaluated. The proposed layer leads up to gain a 1.1% AP improvement on bounding box detection and 1.7% AP improvement on instance segmentation. The code is publicly available on GitHub repository at https://github.com/IMPLabUniPr/mmdetection/tree/groie_dev

PaperPDFCode

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

Code

open-mmlab/mmdetection officialpytorch report
IMPLabUniPr/mmdetection mentioned in paperpytorch report
IMPLabUniPr/mmdetection-groie mentioned in paperpytorchApache-2.0 report
Gugan0905/steel-defect-detection mentioned on GitHubpytorchApache-2.0 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

Instance SegmentationObject DetectionSegmentationSemantic Segmentationobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Instance Segmentation COCO minival GCnet (ResNet-50-FPN, GRoIE) AP50 59.3 #84 of 93 Archive leaderboard report
Instance Segmentation COCO minival GCnet (ResNet-50-FPN, GRoIE) AP75 39.8 #84 of 93 Archive leaderboard report
Instance Segmentation COCO minival GCnet (ResNet-50-FPN, GRoIE) APL 51.2 #84 of 93 Archive leaderboard report
Instance Segmentation COCO minival GCnet (ResNet-50-FPN, GRoIE) APM 41 #84 of 93 Archive leaderboard report
Instance Segmentation COCO minival GCnet (ResNet-50-FPN, GRoIE) APS 20.2 #84 of 93 Archive leaderboard report
Instance Segmentation COCO minival GCnet (ResNet-50-FPN, GRoIE) mask AP 37.2 #84 of 93 Archive leaderboard report
Instance Segmentation COCO minival Mask R-CNN (ResNet-50-FPN, GRoIE) AP50 57.1 #88 of 93 Archive leaderboard report
Instance Segmentation COCO minival Mask R-CNN (ResNet-50-FPN, GRoIE) AP75 38.0 #88 of 93 Archive leaderboard report
Instance Segmentation COCO minival Mask R-CNN (ResNet-50-FPN, GRoIE) APL 48.7 #88 of 93 Archive leaderboard report
Instance Segmentation COCO minival Mask R-CNN (ResNet-50-FPN, GRoIE) APM 39 #88 of 93 Archive leaderboard report
Instance Segmentation COCO minival Mask R-CNN (ResNet-50-FPN, GRoIE) APS 19.1 #88 of 93 Archive leaderboard report
Instance Segmentation COCO minival Mask R-CNN (ResNet-50-FPN, GRoIE) mask AP 35.8 #88 of 93 Archive leaderboard report
Object Detection COCO minival Mask R-CNN (ResNet-50-FPN, GRoIE) AP50 59.9 #196 of 220 Archive leaderboard report
Object Detection COCO minival Mask R-CNN (ResNet-50-FPN, GRoIE) AP75 41.7 #196 of 220 Archive leaderboard report
Object Detection COCO minival Mask R-CNN (ResNet-50-FPN, GRoIE) APL 49.7 #196 of 220 Archive leaderboard report
Object Detection COCO minival Mask R-CNN (ResNet-50-FPN, GRoIE) APM 42.1 #196 of 220 Archive leaderboard report
Object Detection COCO minival Mask R-CNN (ResNet-50-FPN, GRoIE) APS 22.9 #196 of 220 Archive leaderboard report
Object Detection COCO minival Mask R-CNN (ResNet-50-FPN, GRoIE) box AP 38.4 #196 of 220 Archive leaderboard report
Object Detection COCO minival Faster R-CNN (ResNet-50-FPN, GRoIE) AP50 59.2 #203 of 220 Archive leaderboard report
Object Detection COCO minival Faster R-CNN (ResNet-50-FPN, GRoIE) AP75 40.6 #203 of 220 Archive leaderboard report
Object Detection COCO minival Faster R-CNN (ResNet-50-FPN, GRoIE) APL 47.8 #203 of 220 Archive leaderboard report
Object Detection COCO minival Faster R-CNN (ResNet-50-FPN, GRoIE) APM 41.5 #203 of 220 Archive leaderboard report
Object Detection COCO minival Faster R-CNN (ResNet-50-FPN, GRoIE) APS 22.3 #203 of 220 Archive leaderboard report
Object Detection COCO minival Faster R-CNN (ResNet-50-FPN, GRoIE) box AP 37.5 #203 of 220 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

Introduced by this paper: GRoIE

1x1 ConvolutionConvolutionFPNGRoIEMask R-CNNNon-Local BlockNon-Local OperationRPNResidual 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