Methods › Computer Vision › Instance Segmentation Models › Cascade Mask R-CNN
Cascade Mask R-CNN
Introduced by Zhaowei Cai et al. in Cascade R-CNN: Delving into High Quality Object Detection
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Cascade Mask R-CNN extends Cascade R-CNN to instance segmentation, by adding a mask head to the cascade.
In the Mask R-CNN, the segmentation branch is inserted in parallel to the detection branch. However, the Cascade R-CNN has multiple detection branches. This raises the questions of 1) where to add the segmentation branch and 2) how many segmentation branches to add. The authors consider three strategies for mask prediction in the Cascade R-CNN. The first two strategies address the first question, adding a single mask prediction head at either the first or last stage of the Cascade R-CNN. Since the instances used to train the segmentation branch are the positives of the detection branch, their number varies in these two strategies. Placing the segmentation head later on the cascade leads to more examples. However, because segmentation is a pixel-wise operation, a large number of highly overlapping instances is not necessarily as helpful as for object detection, which is a patch-based operation. The third strategy addresses the second question, adding a segmentation branch to each cascade stage. This maximizes the diversity of samples used to learn the mask prediction task.
At inference time, all three strategies predict the segmentation masks on the patches produced by the final object detection stage, irrespective of the cascade stage on which the segmentation mask is implemented and how many segmentation branches there are.
In Syntology for a different name, 'Mask R-CNN', about another paper, arXiv:1703.06870: repository known, no verified implementation (declared_code; repositories: 5 listed of 179 in the graph, strongest link: mentioned in the paper). The lookup matched a different name in Syntology's graph, 'Mask R-CNN' (resolution: token_match); this answer is about that name. About another paper: this answer is about arXiv:1703.06870, while the archive credits arXiv:1712.00726.
Code Syntology holds under other names, as the lookup lists them (code_nearby); not a complete list, and none of them is this method.
- CASCADE · shares_name_tokens (shares name tokens with this name; a different method) · level V2 · retrieve with
get_reference_implementation(name='CASCADE') - Unleashing Mask · shares_name_tokens (shares name tokens with this name; a different method) · level V3 · retrieve with
get_reference_implementation(name='Unleashing Mask') - online cascade learning · shares_name_tokens (shares name tokens with this name; a different method) · level V2 · retrieve with
get_reference_implementation(name='online cascade learning')
Origin paper of this answer, arXiv:1703.06870 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 101 ran (of which 3 constructed an object rather than computing a result; 77 with no instrument failure: 2 honoured, 1 violated, 74 with no contract checked; 24 where Syntology's instrument failed) · 39 unverified (of 140 harvested samples) · 32 pointer-only (licence). The instrument figure counts failures of Syntology's instrument, not of the code. Ran means executed on a synthesized input, not that the code is correct.
Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.
What each level means, quoted from Syntology's server card: V0 “imports”; V1 “executes against a synthesized fixture and returns a value of the recorded type”; V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” The card adds: “No rung on this ladder compares the served code against the authors' implementation, so treat every level as evidence about runnability and internal agreement, not about matching the paper's results.” A level quoted in two parts is one definition the card writes as two clauses joined by a double hyphen, each clause quoted on its own (how these levels are quoted).
Papers archive 2025-07-28
archive papers tagged: 23 · with a code link: 13 · where Syntology ran a sample: 9 (8 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (9 of 23 tagged: 8 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 23 of 23, newest first by the archive's date (ties by slug), in archive order.
Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.
-
RipVIS: Rip Currents Video Instance Segmentation Benchmark for Beach Monitoring and Safety 1 Apr 2025 · 0 repositories · arXiv:2504.01128
-
OverLoCK: An Overview-first-Look-Closely-next ConvNet with Context-Mixing Dynamic Kernels 27 Feb 2025 · 1 repository · arXiv:2502.20087Syntology official (archive's flag): 2 ran · 2 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; 0 where Syntology's instrument failed) · 1 unverified (of 3 harvested samples)
-
Hierarchical Side-Tuning for Vision Transformers 9 Oct 2023 · 0 repositories · arXiv:2310.05393
-
DMKD: Improving Feature-based Knowledge Distillation for Object Detection Via Dual Masking Augmentation 6 Sep 2023 · 0 repositories · arXiv:2309.02719
-
Non-Hierarchical Transformers for Pedestrian Segmentation 11 Jul 2023 · 0 repositories · arXiv:2311.02506
-
BiViT: Extremely Compressed Binary Vision Transformers 1 Jan 2023 · 0 repositories
-
BiViT: Extremely Compressed Binary Vision Transformer 14 Nov 2022 · 0 repositories · arXiv:2211.07091
-
A Tri-Layer Plugin to Improve Occluded Detection 18 Oct 2022 · 1 repository · arXiv:2210.10046
-
FQ-ViT: Post-Training Quantization for Fully Quantized Vision Transformer 27 Nov 2021 · 1 repository · arXiv:2111.13824Syntology official (archive's flag): 2 ran · 3 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; 2 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples) · 1 pointer-only (licence)
-
VTLayout: Fusion of Visual and Text Features for Document Layout Analysis 12 Aug 2021 · 0 repositories · arXiv:2108.13297
-
K-Net: Towards Unified Image Segmentation 28 Jun 2021 · 1 repository · arXiv:2106.14855Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)
-
A2-FPN: Attention Aggregation Based Feature Pyramid Network for Instance Segmentation 19 Jun 2021 · 0 repositories
-
TNCR: Table Net Detection and Classification Dataset 19 Jun 2021 · 1 repository · arXiv:2106.15322
-
A^2-FPN: Attention Aggregation based Feature Pyramid Network for Instance Segmentation 7 May 2021 · 0 repositories · arXiv:2105.03186
-
Instances as Queries 5 May 2021 · 5 repositories · arXiv:2105.01928Syntology community repositories only · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 3 harvested samples) · 1 pointer-only (licence)
-
Object Detection for Understanding Assembly Instruction Using Context-aware Data Augmentation and Cascade Mask R-CNN 7 Jan 2021 · 0 repositories · arXiv:2101.02509
-
SCNet: Training Inference Sample Consistency for Instance Segmentation 18 Dec 2020 · 2 repositories · arXiv:2012.10150
-
Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation 13 Dec 2020 · 5 repositories · arXiv:2012.07177Syntology community repositories only · 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) · 0 unverified (of 2 harvested samples)
-
CascadeTabNet: An approach for end to end table detection and structure recognition from image-based documents 27 Apr 2020 · 3 repositories · arXiv:2004.12629Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 2 harvested samples)
-
CBNet: A Novel Composite Backbone Network Architecture for Object Detection 9 Sep 2019 · 6 repositories · arXiv:1909.03625Syntology official (archive's flag): 2 ran · 2 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; 0 where Syntology's instrument failed) · 2 unverified (of 4 harvested samples) · 1 pointer-only (licence)
-
GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond 25 Apr 2019 · 9 repositories · arXiv:1904.11492
-
Hybrid Task Cascade for Instance Segmentation 22 Jan 2019 · 5 repositories · arXiv:1901.07518Syntology community repositories only · 11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 11 harvested samples)
-
Cascade R-CNN: Delving into High Quality Object Detection 3 Dec 2017 · 8 repositories · arXiv:1712.00726Syntology official: no sample here; runs from other or unrecorded repositories · 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 (of 2 harvested samples) · 2 pointer-only (licence)
Tasks archive 2025-07-28
20 shown of 28 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
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
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