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 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="2106.11562")

Code

Syntology Ran 6 of 12 code samples harvested from 1 repository linked to this paper; 6 have no recorded run. Of those that ran: 6 ran with no contract checked.

By repository: official repository: 12 samples from 1 repository, 6 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

clovaai/SSUL officialmentioned in papermentioned on GitHubpytorch 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; 0 honoured the contract we drafted; 6 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.

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. “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.

ASPP clovaai/SSUL/network/modeling.py official repository ran · metamorphic tier: deterministic fingerprinted licence not identified · pointer only · ca5a01506bf190fc · report
ASPPConv clovaai/SSUL/network/modeling.py official repository ran · metamorphic tier: deterministic fingerprinted licence not identified · pointer only · 3704384e62d46e83 · report
ASPPPooling clovaai/SSUL/network/modeling.py official repository ran · metamorphic tier: deterministic fingerprinted licence not identified · pointer only · 58aa3ee6bb3dd9a4 · report
DeepLabHead clovaai/SSUL/network/modeling.py official repository ran · metamorphic tier: deterministic licence not identified · pointer only · 9917e2638ee6fb29 · report
IntermediateLayerGetter clovaai/SSUL/network/modeling.py official repository ran · metamorphic tier: deterministic fingerprinted licence not identified · pointer only · 8d2daac3bc9124e6 · report
_SimpleSegmentationModel clovaai/SSUL/network/modeling.py official repository ran · metamorphic tier: deterministic fingerprinted licence not identified · pointer only · 96c800659dca7d1e · report
DeepLabHeadV3Plus clovaai/SSUL/network/modeling.py official repository unverified licence not identified · pointer only · 3cab456d98fae710 · report
DeepLabV3 clovaai/SSUL/network/modeling.py official repository unverified licence not identified · pointer only · aefeef7f716ecb9d · report
_load_model clovaai/SSUL/network/modeling.py official repository unverified licence not identified · pointer only · c09c3bf8b03dab46 · report
_segm_mobilenet clovaai/SSUL/network/modeling.py official repository unverified licence not identified · pointer only · 3abf7e51960c13a7 · report
_segm_resnet clovaai/SSUL/network/modeling.py official repository unverified licence not identified · pointer only · 3187feb03a45e3a4 · report
deeplabv3plus_resnet50 clovaai/SSUL/network/modeling.py official repository unverified licence not identified · pointer only · 0c67be585d1b2be6 · report

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