Papers › SSUL: Semantic Segmentation with Unknown Label for Exemplar-based Class-Incremental Learning

SSUL: Semantic Segmentation with Unknown Label for Exemplar-based Class-Incremental Learning

22 Jun 2021NeurIPS 2021 12arXiv:2106.11562archive 2025-07-28

Sungmin Cha, Beomyoung Kim, Youngjoon Yoo, Taesup Moon

This paper introduces a solid state-of-the-art baseline for a class-incremental semantic segmentation (CISS) problem. While the recent CISS algorithms utilize variants of the knowledge distillation (KD) technique to tackle the problem, they failed to fully address the critical challenges in CISS causing the catastrophic forgetting; the semantic drift of the background class and the multi-label prediction issue. To better address these challenges, we propose a new method, dubbed SSUL-M (Semantic Segmentation with Unknown Label with Memory), by carefully combining techniques tailored for semantic segmentation. Specifically, we claim three main contributions. (1) defining unknown classes within the background class to help to learn future classes (help plasticity), (2) freezing backbone network and past classifiers with binary cross-entropy loss and pseudo-labeling to overcome catastrophic forgetting (help stability), and (3) utilizing tiny exemplar memory for the first time in CISS to improve both plasticity and stability. The extensively conducted experiments show the effectiveness of our method, achieving significantly better performance than the recent state-of-the-art baselines on the standard benchmark datasets. Furthermore, we justify our contributions with thorough ablation analyses and discuss different natures of the CISS problem compared to the traditional class-incremental learning targeting classification. The official code is available at https://github.com/clovaai/SSUL.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

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

Syntology 12 code samples harvested from 1 repository linked to this paper: 6 ran (of which 6 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified; every one of the 6 samples that ran constructed an object rather than computing a result. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 12 samples from 1 repository, 6 ran (6 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.

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

clovaai/SSUL officialmentioned in papermentioned on GitHubpytorchSyntology: 12 samples, 6 ran (0 instrument-failed) · 6 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

12 samples harvested: 6 ran (of which 6 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified; every one of the 6 samples that ran constructed an object rather than computing a result. “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.

6ran
6unverified

Licence: 12 of the 12 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 clovaai/SSUL. “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”. For 5 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.

clovaai/SSUL official repository 12 samples, 6 ran (0 instrument-failed) · 6 unverified
ASPP in 23 papers network/modeling.py ran · metamorphic tier: deterministic fingerprinted licence not identified · pointer only · ca5a01506bf190fc · report fixture: returned ASPP · level recorded 2026-09-22
ASPPConv in 9 papers network/modeling.py ran · metamorphic tier: deterministic fingerprinted licence not identified · pointer only · 3704384e62d46e83 · report fixture: returned ASPPConv · level recorded 2026-09-22
ASPPPooling in 6 papers network/modeling.py ran · metamorphic tier: deterministic fingerprinted licence not identified · pointer only · 58aa3ee6bb3dd9a4 · report fixture: returned ASPPPooling · level recorded 2026-09-22
DeepLabHead network/modeling.py ran · metamorphic tier: deterministic licence not identified · pointer only · 9917e2638ee6fb29 · report fixture: returned DeepLabHead · level recorded 2026-09-22
IntermediateLayerGetter network/modeling.py ran · metamorphic tier: deterministic fingerprinted licence not identified · pointer only · 8d2daac3bc9124e6 · report fixture: returned IntermediateLayerGetter · level recorded 2026-09-22
_SimpleSegmentationModel network/modeling.py ran · metamorphic tier: deterministic fingerprinted licence not identified · pointer only · 96c800659dca7d1e · report fixture: returned _SimpleSegmentationModel · level recorded 2026-09-22
DeepLabHeadV3Plus network/modeling.py unverified licence not identified · pointer only · 3cab456d98fae710 · report
DeepLabV3 in 7 papers network/modeling.py unverified licence not identified · pointer only · aefeef7f716ecb9d · report
_load_model network/modeling.py unverified licence not identified · pointer only · c09c3bf8b03dab46 · report
_segm_mobilenet network/modeling.py unverified licence not identified · pointer only · 3abf7e51960c13a7 · report
_segm_resnet network/modeling.py unverified licence not identified · pointer only · 3187feb03a45e3a4 · report
deeplabv3plus_resnet50 network/modeling.py unverified licence not identified · pointer only · 0c67be585d1b2be6 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for SSUL-M (graph method: SSUL-M). 12 bricks; individually on a fixture: 6 ran (of which 6 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified; every one of the 6 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

  1. deeplabv3plus_resnet50 entry · level 0 · unverified · 0c67be585d1b2be6
  2. _load_model helper · level 0 · unverified · c09c3bf8b03dab46
  3. _segm_mobilenet helper · level 0 · unverified · 3abf7e51960c13a7
  4. _segm_resnet helper · level 0 · unverified · 3187feb03a45e3a4
  5. DeepLabHead helper · level 1 · ran · 9917e2638ee6fb29
  6. DeepLabHeadV3Plus model · level 0 · unverified · 3cab456d98fae710
  7. DeepLabV3 helper · level 0 · unverified · aefeef7f716ecb9d
  8. IntermediateLayerGetter helper · level 1 · ran · 8d2daac3bc9124e6
  9. ASPP model · level 1 · ran · ca5a01506bf190fc
  10. _SimpleSegmentationModel helper · level 1 · ran · 96c800659dca7d1e
  11. ASPPConv helper · level 1 · ran · 3704384e62d46e83
  12. ASPPPooling helper · level 1 · ran · 58aa3ee6bb3dd9a4

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2106.11562") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Class Incremental LearningClass-Incremental Semantic SegmentationContinual Semantic SegmentationDisjoint 10-1Disjoint 15-1Disjoint 15-5Incremental LearningKnowledge DistillationOverlapped 10-1Overlapped 100-5Overlapped 100-50Overlapped 15-1Overlapped 15-5Overlapped 50-50SegmentationSemantic Segmentationclass-incremental learning

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Disjoint 10-1 PASCAL VOC 2012 SSUL-M mIoU 53.50 #1 of 8 Archive leaderboard report
Disjoint 10-1 PASCAL VOC 2012 SSUL mIoU 50.87 #2 of 8 Archive leaderboard report
Disjoint 15-1 PASCAL VOC 2012 SSUL-M mIoU 68.58 #2 of 9 Archive leaderboard report
Disjoint 15-1 PASCAL VOC 2012 SSUL mIoU 64.01 #3 of 9 Archive leaderboard report
Disjoint 15-5 PASCAL VOC 2012 SSUL-M Mean IoU 69.83 #2 of 9 Archive leaderboard report
Disjoint 15-5 PASCAL VOC 2012 SSUL Mean IoU 69.10 #3 of 9 Archive leaderboard report
Overlapped 10-1 PASCAL VOC 2012 SSUL-M mIoU 64.12 #3 of 13 Archive leaderboard report
Overlapped 10-1 PASCAL VOC 2012 SSUL mIoU 59.25 #6 of 13 Archive leaderboard report
Overlapped 100-5 ADE20K SSUL-M mIoU 34.56 #2 of 8 Archive leaderboard report
Overlapped 100-5 ADE20K SSUL mIoU 32.48 #3 of 8 Archive leaderboard report
Overlapped 100-50 ADE20K SSUL-M mIoU 34.37 #4 of 7 Archive leaderboard report
Overlapped 100-50 ADE20K SSUL mIoU 33.58 #5 of 7 Archive leaderboard report
Overlapped 15-1 PASCAL VOC 2012 SSUL-M mIoU 71.37 #4 of 13 Archive leaderboard report
Overlapped 15-1 PASCAL VOC 2012 SSUL mIoU 67.61 #5 of 13 Archive leaderboard report
Overlapped 15-5 PASCAL VOC 2012 SSUL-M Mean IoU (val) 73.02 #4 of 13 Archive leaderboard report
Overlapped 15-5 PASCAL VOC 2012 SSUL Mean IoU (val) 71.22 #7 of 13 Archive leaderboard report
Overlapped 50-50 ADE20K SSUL-M mIoU 29.77 #5 of 7 Archive leaderboard report
Overlapped 50-50 ADE20K SSUL mIoU 29.56 #6 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