Papers › Relieving Long-tailed Instance Segmentation via Pairwise Class Balance

Relieving Long-tailed Instance Segmentation via Pairwise Class Balance

8 Jan 2022CVPR 2022 1arXiv:2201.02784archive 2025-07-28

Yin-Yin He, Peizhen Zhang, Xiu-Shen Wei, Xiangyu Zhang, Jian Sun

Long-tailed instance segmentation is a challenging task due to the extreme imbalance of training samples among classes. It causes severe biases of the head classes (with majority samples) against the tailed ones. This renders "how to appropriately define and alleviate the bias" one of the most important issues. Prior works mainly use label distribution or mean score information to indicate a coarse-grained bias. In this paper, we explore to excavate the confusion matrix, which carries the fine-grained misclassification details, to relieve the pairwise biases, generalizing the coarse one. To this end, we propose a novel Pairwise Class Balance (PCB) method, built upon a confusion matrix which is updated during training to accumulate the ongoing prediction preferences. PCB generates fightback soft labels for regularization during training. Besides, an iterative learning paradigm is developed to support a progressive and smooth regularization in such debiasing. PCB can be plugged and played to any existing method as a complement. Experimental results on LVIS demonstrate that our method achieves state-of-the-art performance without bells and whistles. Superior results across various architectures show the generalization ability. The code and trained models are available at https://github.com/megvii-research/PCB.

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

The archive's official repository (megvii-research/pcb) was not harvested; the 11 samples below come from 1 community repository.

Syntology 11 code samples harvested from 1 repository linked to this paper: 10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 11 samples from 1 repository, 10 ran (9 with no instrument failure; 1 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.

Levels written between 2026-09-24 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

megvii-research/pcb officialmentioned in papermentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
2023-MindSpore-1/ms-code-105 mindsporeMITSyntology: 11 samples, 10 ran (1 instrument-failed) · 1 unverified 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: 10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · our draft was wrong
9ran
1unverified

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 2023-MindSpore-1/ms-code-105. “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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

2023-MindSpore-1/ms-code-105 community (archive-listed) 11 samples, 10 ran (1 instrument-failed) · 1 unverified
a_cosine_learning_rate in 5 papers src/lr_schedule.py ran MIT (permissive) · 316fb42e9e6ed79e · report fixture: signature current_step:int/0/int, base_lr:float/0/float, warmup_steps:int/0/int, decay_steps:int/0/int · returned float · level recorded 2026-09-24
accuracy in 872 papers
census: 8 implementations from 7 papers, 7 distinct outputs across 6 buckets, one shared input per bucket
src/maskrcnn/accuracy.py ran MIT (permissive) · a0d4d553d4b95e53 · report fixture: signature pred:Tensor/2/float, target:Tensor/1/int, topk:int/0/int, thresh:NoneType/0/? · returned Tensor · level recorded 2026-09-24
bbox2result_1image src/util.py ran MIT (permissive) · 58e8ebdfdf3e7c34 · report fixture: signature bboxes:Tensor/2/float, labels:Tensor/1/int, num_classes:int/0/int · returned list · level recorded 2026-09-24
dynamic_lr in 7 papers src/lr_schedule.py ran MIT (permissive) · 0fd930bb273bb598 · report fixture: signature config:Config/0/?, rank_size:int/0/int, start_steps:int/0/int · returned list · level recorded 2026-09-24
get_img_size in 5 papers postprocess.py ran MIT (permissive) · b13acc0922dade5c · report fixture: signature file_name:str/0/str · returned tuple · level recorded 2026-09-24
get_resize_ratio postprocess.py ran MIT (permissive) · 99e18a5cd3724f31 · report fixture: signature img_size:tuple/1/int · returned float · level recorded 2026-09-24
linear_warmup_learning_rate in 8 papers src/lr_schedule.py ran fingerprinted MIT (permissive) · d6a99ec714147ac1 · report fixture: signature current_step:int/0/int, warmup_steps:int/0/int, base_lr:float/0/float, init_lr:float/0/float · returned float · level recorded 2026-09-24
rescale_with_factor src/dataset.py ran fingerprinted MIT (permissive) · 81dd949ea3cb5b13 · report fixture: signature img:ndarray/3/int, scale_factor:float/0/float · returned ndarray · level recorded 2026-09-24
rescale_with_tuple src/dataset.py ran MIT (permissive) · 8178d0257544aab2 · report fixture: signature img:ndarray/3/int, scale:tuple/1/int · returned tuple · level recorded 2026-09-24
xyxy2xywh in 19 papers src/util.py ran · our draft was wrong MIT (permissive) · 141b13358e6b0894 · report fixture: signature bbox:Tensor/1/float · returned list · level recorded 2026-09-25
bbox_overlaps in 20 papers src/dataset.py unverified MIT (permissive) · 48b4b7f4e22caf1d · report

Tasks

Instance SegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

PCB

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