Papers › Hybrid Task Cascade for Instance Segmentation

Hybrid Task Cascade for Instance Segmentation

22 Jan 2019CVPR 2019 6arXiv:1901.07518archive 2025-07-28

Kai Chen, Jiangmiao Pang, Jiaqi Wang, Yu Xiong, Xiaoxiao Li, Shuyang Sun, Wansen Feng, Ziwei Liu, Jianping Shi, Wanli Ouyang, Chen Change Loy, Dahua Lin

Cascade is a classic yet powerful architecture that has boosted performance on various tasks. However, how to introduce cascade to instance segmentation remains an open question. A simple combination of Cascade R-CNN and Mask R-CNN only brings limited gain. In exploring a more effective approach, we find that the key to a successful instance segmentation cascade is to fully leverage the reciprocal relationship between detection and segmentation. In this work, we propose a new framework, Hybrid Task Cascade (HTC), which differs in two important aspects: (1) instead of performing cascaded refinement on these two tasks separately, it interweaves them for a joint multi-stage processing; (2) it adopts a fully convolutional branch to provide spatial context, which can help distinguishing hard foreground from cluttered background. Overall, this framework can learn more discriminative features progressively while integrating complementary features together in each stage. Without bells and whistles, a single HTC obtains 38.4 and 1.5 improvement over a strong Cascade Mask R-CNN baseline on MSCOCO dataset. Moreover, our overall system achieves 48.6 mask AP on the test-challenge split, ranking 1st in the COCO 2018 Challenge Object Detection Task. Code is available at: https://github.com/open-mmlab/mmdetection.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

No sample from the archive's official repository (open-mmlab/mmdetection) is linked to this paper; the 11 samples below come from 1 community repository. Syntology harvested code from open-mmlab/mmdetection for another paper.

open-mmlab/mmdetection: Syntology's graph links these samples to An Open and Comprehensive Pipeline for Unified Object Grounding and Detection (arXiv:2401.02361; that paper's own run record: 4 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; 2 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method.

Syntology 11 code samples harvested from 1 repository linked to this paper: 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. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 11 samples from 1 repository, 11 ran (11 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 3 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

open-mmlab/mmdetection officialmentioned in paperpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to An Open and Comprehensive Pipeline for Unified Object Grounding and Detection (arXiv:2401.02361; that paper's own run record: 4 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; 2 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
amirassov/kaggle-imaterialist mentioned on GitHubpytorchMITSyntology: 11 samples, 11 ran (0 instrument-failed) · 0 unverified report
zhaozhen2333/iflytek2021 mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
Burf/tfdetection tfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks (arXiv:1506.01497; that paper's own run record: 79 ran (of which 9 constructed an object rather than computing a result; 47 with no instrument failure: 18 honoured, 5 violated, 24 with no contract checked; 32 where Syntology's instrument failed) · 45 unverified), Wide Residual Networks (arXiv:1605.07146; that paper's own run record: 66 ran (of which 31 constructed an object rather than computing a result; 47 with no instrument failure: 0 honoured, 0 violated, 47 with no contract checked; 19 where Syntology's instrument failed) · 30 unverified), Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation (arXiv:1802.02611; that paper's own run record: 44 ran (of which 17 constructed an object rather than computing a result; 28 with no instrument failure: 2 honoured, 0 violated, 26 with no contract checked; 16 where Syntology's instrument failed) · 28 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
PaddlePaddle/PaddleDetection paddleSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to PP-YOLOE: An evolved version of YOLO (arXiv:2203.16250; that paper's own run record: 22 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 2 honoured, 0 violated, 17 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

11 samples harvested: 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. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

11ran

Licence: 0 of the 11 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from amirassov/kaggle-imaterialist. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

amirassov/kaggle-imaterialist community (archive-listed) 11 samples, 11 ran (0 instrument-failed) · 0 unverified
calc_iou in 17 papers src/metric.py ran MIT (permissive) · 5c1c9209733e8eee · report fixture: signature y_true:ndarray/2/int, y_prediction:ndarray/2/int · returned ndarray · level recorded 2026-09-24
calc_score_per_class src/metric.py ran fingerprinted MIT (permissive) · cd1b403bf92fd010 · report fixture: signature y_true:ndarray/2/int, y_prediction:ndarray/2/int · returned float64 · level recorded 2026-09-24
check_overlaps src/utils.py ran MIT (permissive) · 539349d8cda29622 · report fixture: signature mask:ndarray/3/int · returned bool · level recorded 2026-09-24
coco_rle_encode src/rle.py ran fingerprinted MIT (permissive) · b291d504cabbb9d7 · report fixture: signature mask:ndarray/2/int · returned dict · level recorded 2026-09-24
create_labeled_mask src/utils.py ran fingerprinted MIT (permissive) · 788ec14ec90e920b · report fixture: signature mask:ndarray/3/float · returned ndarray · level recorded 2026-09-24
draw_masks src/eda.py ran MIT (permissive) · 5c7e2e28ee4a2a70 · report fixture: signature img:ndarray/3/int, masks:ndarray/3/bool · returned ndarray · level recorded 2026-09-24
get_spaced_colors src/draw.py ran MIT (permissive) · 009e3118940f9f68 · report fixture: signature n:int/0/int, start_color:tuple/1/int · returned ndarray · level recorded 2026-09-24
kaggle_rle_decode src/rle.py ran MIT (permissive) · 2573e54c215b3242 · report fixture: signature rle:list/1/int, h:int/0/int, w:int/0/int · returned ndarray · level recorded 2026-09-24
kaggle_rle_encode src/rle.py ran MIT (permissive) · 3163dc95d76aef7a · report fixture: signature mask:ndarray/2/int · returned list · level recorded 2026-09-24
precision_at src/metric.py ran MIT (permissive) · 2ac465835acc2a38 · report fixture: signature threshold:float/0/float, iou:ndarray/2/float · returned tuple · level recorded 2026-09-24
put_text src/draw.py ran MIT (permissive) · f7f918c6e2c8756c · report fixture: signature img:ndarray/3/int, color:tuple/1/float, text:str/0/str, i:int/0/int, x_shift:int/0/int, y_shift:int/0/int · returned ndarray · level recorded 2026-09-24

Tasks

Instance SegmentationObject DetectionOpen-Ended Question AnsweringSegmentationSemantic Segmentationobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Instance Segmentation COCO minival HTC (ResNet-50) mask AP 38.2 #81 of 93 Archive leaderboard report
Instance Segmentation COCO test-dev HTC + ResNeXt-101-FPN + DCN mask AP 41.2 #63 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev HTC + ResNeXt-101-FPN mask AP 41.2% #64 of 112 Archive leaderboard report
Object Detection COCO minival HTC (cascade) AP50 59.4 #143 of 220 Archive leaderboard report
Object Detection COCO minival HTC (cascade) AP75 40.7 #143 of 220 Archive leaderboard report
Object Detection COCO minival HTC (cascade) APL 52.3 #143 of 220 Archive leaderboard report
Object Detection COCO minival HTC (cascade) APM 40.9 #143 of 220 Archive leaderboard report
Object Detection COCO minival HTC (cascade) APS 20.3 #143 of 220 Archive leaderboard report
Object Detection COCO minival HTC (cascade) box AP 43.2 #143 of 220 Archive leaderboard report
Object Detection COCO test-dev HTC (ResNeXt-101-FPN) AP50 63.9 #120 of 225 Archive leaderboard report
Object Detection COCO test-dev HTC (ResNeXt-101-FPN) AP75 44.7 #120 of 225 Archive leaderboard report
Object Detection COCO test-dev HTC (ResNeXt-101-FPN) APL 54.6 #120 of 225 Archive leaderboard report
Object Detection COCO test-dev HTC (ResNeXt-101-FPN) APM 43.9 #120 of 225 Archive leaderboard report
Object Detection COCO test-dev HTC (ResNeXt-101-FPN) APS 22.8 #120 of 225 Archive leaderboard report
Object Detection COCO test-dev HTC (ResNeXt-101-FPN) box mAP 47.1 #120 of 225 Archive leaderboard report
Object Detection COCO-O HTC (ResNet-50) Average mAP 19.1 #32 of 45 Archive leaderboard report
Object Detection COCO-O HTC (ResNet-50) Effective Robustness 0.08 #32 of 45 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 BlockBottom-up Path AugmentationCascade Mask R-CNNCascade R-CNNConvolutionDeformable ConvolutionDense ConnectionsFPNGlobal Average PoolingGlobal Convolutional NetworkGrouped ConvolutionHTCKaiming InitializationMax PoolingPAFPNPrecise RoI PoolingRPNReLUResNeXtResNeXt BlockResidual BlockResidual ConnectionRoIAlignSENetSigmoid ActivationSoft-NMSSoftmaxSqueeze-and-Excitation Block

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