</> Code with Papers by Syntology

Methods › Computer Vision › Object Detection Models › Mask R-CNN

Mask R-CNN

420 papers tagged archive 2025-07-28

Introduced by Kaiming He et al. in Mask R-CNN

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

Mask R-CNN extends Faster R-CNN to solve instance segmentation tasks. It achieves this by adding a branch for predicting an object mask in parallel with the existing branch for bounding box recognition. In principle, Mask R-CNN is an intuitive extension of Faster R-CNN, but constructing the mask branch properly is critical for good results.

Most importantly, Faster R-CNN was not designed for pixel-to-pixel alignment between network inputs and outputs. This is evident in how RoIPool, the de facto core operation for attending to instances, performs coarse spatial quantization for feature extraction. To fix the misalignment, Mask R-CNN utilises a simple, quantization-free layer, called RoIAlign, that faithfully preserves exact spatial locations.

Secondly, Mask R-CNN decouples mask and class prediction: it predicts a binary mask for each class independently, without competition among classes, and relies on the network's RoI classification branch to predict the category. In contrast, an FCN usually perform per-pixel multi-class categorization, which couples segmentation and classification.

PaperSourceSee Code · facebookresearch/detectron2

Papers archive 2025-07-28

30 shown of 420, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

Tasks archive 2025-07-28

20 shown of 308 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Semantic Segmentation197
Instance Segmentation177
Object Detection139
Segmentation135
object-detection121
Object76
Image Classification27
Transfer Learning22
Image Segmentation16
Pose Estimation16
Data Augmentation15
General Classification14
Panoptic Segmentation14
image-classification14
Region Proposal12
Deep Learning11
Autonomous Driving9
Clustering9
Decoder9
Object Recognition9

Usage over time archive 2025-07-28

Papers per year tagged with Mask R-CNN: 2017 to 2025, peak 95 95 0 2017: 7 papers 2017 2018: 27 papers 2018 2019: 74 papers 2019 2020: 85 papers 2020 2021: 95 papers 2021 2022: 38 papers 2022 2023: 46 papers 2023 2024: 30 papers 2024 2025: 18 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (420 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Object Detection ModelsInstance Segmentation Models

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