Papers › Representation Compensation Networks for Continual Semantic Segmentation

Representation Compensation Networks for Continual Semantic Segmentation

10 Mar 2022CVPR 2022 1arXiv:2203.05402archive 2025-07-28

Chang-Bin Zhang, Jia-Wen Xiao, Xialei Liu, Ying-Cong Chen, Ming-Ming Cheng

In this work, we study the continual semantic segmentation problem, where the deep neural networks are required to incorporate new classes continually without catastrophic forgetting. We propose to use a structural re-parameterization mechanism, named representation compensation (RC) module, to decouple the representation learning of both old and new knowledge. The RC module consists of two dynamically evolved branches with one frozen and one trainable. Besides, we design a pooled cube knowledge distillation strategy on both spatial and channel dimensions to further enhance the plasticity and stability of the model. We conduct experiments on two challenging continual semantic segmentation scenarios, continual class segmentation and continual domain segmentation. Without any extra computational overhead and parameters during inference, our method outperforms state-of-the-art performance. The code is available at \url{https://github.com/zhangchbin/RCIL}.

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="2203.05402")

Code

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

By repository: official repository: 1 sample 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.

zhangchbin/rcil officialmentioned in papermentioned on GitHubpytorchMIT 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

1 sample harvested; 0 ran; 0 honoured the contract we drafted; 1 has no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1unverified

Licence: 0 of the 1 sample 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 zhangchbin/RCIL. “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.

ResidualBlock zhangchbin/RCIL/modules/residual.py official repository unverified MIT (permissive) · 453269dfbeac98dd · report

Tasks

Class Incremental LearningContinual LearningContinual Semantic SegmentationDisjoint 10-1Disjoint 15-1Disjoint 15-5Domain 1-1Domain 11-1Domain 11-5Knowledge DistillationOverlapped 10-1Overlapped 100-10Overlapped 100-5Overlapped 100-50Overlapped 15-1Overlapped 15-5Overlapped 50-50SegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Disjoint 10-1 PASCAL VOC 2012 RCNet-101 mIoU 18.2 #3 of 8 Archive leaderboard report
Disjoint 15-1 PASCAL VOC 2012 RCNet-101 mIoU 54.7 #4 of 9 Archive leaderboard report
Disjoint 15-5 PASCAL VOC 2012 RCNet-101 Mean IoU 67.3 #4 of 9 Archive leaderboard report
Overlapped 10-1 PASCAL VOC 2012 RCNet-101 mIoU 34.3 #8 of 13 Archive leaderboard report
Overlapped 100-10 ADE20K RCNet-101 Mean IoU (test) 32.1 #4 of 6 Archive leaderboard report
Overlapped 100-5 ADE20K RCNet-101 mIoU 29.6 #5 of 8 Archive leaderboard report
Overlapped 100-50 ADE20K RCNet-101 mIoU 34.5 #3 of 7 Archive leaderboard report
Overlapped 15-1 PASCAL VOC 2012 RCNet-101 mIoU 59.4 #8 of 13 Archive leaderboard report
Overlapped 15-5 PASCAL VOC 2012 RCNet-101 Mean IoU (val) 72.4 #5 of 13 Archive leaderboard report
Overlapped 50-50 ADE20K RCNet-101 mIoU 32.5 #3 of 7 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

Knowledge Distillation

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