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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1901.07518")

Code

Syntology Ran 0 of 11 code samples harvested from 1 repository linked to this paper; 11 have no recorded run.

By repository: community (archive-listed): 11 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

open-mmlab/mmdetection officialmentioned in paperpytorchApache-2.0 report
amirassov/kaggle-imaterialist mentioned on GitHubpytorchMIT report
zhaozhen2333/iflytek2021 mentioned 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

11 samples harvested; 0 ran; 0 honoured the contract we drafted; 11 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

11unverified

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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

calc_iou amirassov/kaggle-imaterialist/src/metric.py community (archive-listed) unverified MIT (permissive) · 5c1c9209733e8eee · report
calc_score_per_class amirassov/kaggle-imaterialist/src/metric.py community (archive-listed) unverified MIT (permissive) · cd1b403bf92fd010 · report
check_overlaps amirassov/kaggle-imaterialist/src/utils.py community (archive-listed) unverified MIT (permissive) · 539349d8cda29622 · report
coco_rle_encode amirassov/kaggle-imaterialist/src/rle.py community (archive-listed) unverified MIT (permissive) · b291d504cabbb9d7 · report
create_labeled_mask amirassov/kaggle-imaterialist/src/utils.py community (archive-listed) unverified MIT (permissive) · 788ec14ec90e920b · report
draw_masks amirassov/kaggle-imaterialist/src/eda.py community (archive-listed) unverified MIT (permissive) · 5c7e2e28ee4a2a70 · report
get_spaced_colors amirassov/kaggle-imaterialist/src/draw.py community (archive-listed) unverified MIT (permissive) · 009e3118940f9f68 · report
kaggle_rle_decode amirassov/kaggle-imaterialist/src/rle.py community (archive-listed) unverified MIT (permissive) · 2573e54c215b3242 · report
kaggle_rle_encode amirassov/kaggle-imaterialist/src/rle.py community (archive-listed) unverified MIT (permissive) · 3163dc95d76aef7a · report
precision_at amirassov/kaggle-imaterialist/src/metric.py community (archive-listed) unverified MIT (permissive) · 2ac465835acc2a38 · report
put_text amirassov/kaggle-imaterialist/src/draw.py community (archive-listed) unverified MIT (permissive) · f7f918c6e2c8756c · report

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