Papers › A Tri-Layer Plugin to Improve Occluded Detection

A Tri-Layer Plugin to Improve Occluded Detection

18 Oct 2022arXiv:2210.10046archive 2025-07-28

Guanqi Zhan, Weidi Xie, Andrew Zisserman

Detecting occluded objects still remains a challenge for state-of-the-art object detectors. The objective of this work is to improve the detection for such objects, and thereby improve the overall performance of a modern object detector. To this end we make the following four contributions: (1) We propose a simple 'plugin' module for the detection head of two-stage object detectors to improve the recall of partially occluded objects. The module predicts a tri-layer of segmentation masks for the target object, the occluder and the occludee, and by doing so is able to better predict the mask of the target object. (2) We propose a scalable pipeline for generating training data for the module by using amodal completion of existing object detection and instance segmentation training datasets to establish occlusion relationships. (3) We also establish a COCO evaluation dataset to measure the recall performance of partially occluded and separated objects. (4) We show that the plugin module inserted into a two-stage detector can boost the performance significantly, by only fine-tuning the detection head, and with additional improvements if the entire architecture is fine-tuned. COCO results are reported for Mask R-CNN with Swin-T or Swin-S backbones, and Cascade Mask R-CNN with a Swin-B backbone.

PaperPDFCode

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

Code

Championchess/Tri-Layer_Plugin_Occluded_Detection officialmentioned on GitHubpytorchApache-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 SegmentationObjectObject DetectionSemantic Segmentationobject-detection

Datasets

Introduced by this paper, per the archive.

Occluded COCOSeparated COCO

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Instance Segmentation COCO test-dev Swin-B + Cascade Mask R-CNN (tri-layer modelling) mask AP 45.9 #41 of 112 Archive leaderboard report
Instance Segmentation Occluded COCO Swin-B + Cascade Mask R-CNN (tri-layer modelling) Mean Recall 63.64 #1 of 6 Archive leaderboard report
Instance Segmentation Occluded COCO Swin-S + Mask R-CNN (tri-layer plugin) Mean Recall 62.58 #3 of 6 Archive leaderboard report
Instance Segmentation Occluded COCO Swin-T + Mask R-CNN (tri-layer plugin) Mean Recall 62.00 #4 of 6 Archive leaderboard report
Instance Segmentation Separated COCO Swin-B + Cascade Mask R-CNN (tri-layer modelling) Mean Recall 36.88 #1 of 6 Archive leaderboard report
Instance Segmentation Separated COCO Swin-S + Mask R-CNN (tri-layer plugin) Mean Recall 35.80 #3 of 6 Archive leaderboard report
Instance Segmentation Separated COCO Swin-T + Mask R-CNN (tri-layer plugin) Mean Recall 34.72 #4 of 6 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

Cascade Mask R-CNNConvolutionMask R-CNNRPNRoIAlignSoftmax

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