Browse State-of-the-Art › Continual Semantic Segmentation
Continual Semantic Segmentation
17 papers with code · 3 benchmarks · 2 datasets archive 2025-07-28
Continual learning in semantic segmentation.
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
3 leaderboard tables shown for this task, 3 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.
| Dataset | Best model (first row in archive order) | Paper | Code | Syntology | Compare |
|---|---|---|---|---|---|
| ADE20K (2 rows) | LGKD | Label-Guided Knowledge Distillation for Continual Semantic... | code | — | Compare |
| PASCAL VOC 2012 (1 row) | LGKD | Label-Guided Knowledge Distillation for Continual Semantic... | code | — | Compare |
| ScanNet (1 row) | LGKD | Label-Guided Knowledge Distillation for Continual Semantic... | code | — | Compare |
Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Libraries
Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.
Datasets archive 2025-07-28
2 datasets whose archive record lists this task, ordered by the archive's paper count.
Subtasks archive 2025-07-28
2 subtasks in the archive's task tree.
Parent tasks archive 2025-07-28
Papers archive 2025-07-28
archive papers tagged: 34 · with a code link: 17 · where Syntology ran a sample: 2 (2 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (2 of 34 tagged: 2 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 34 of 34, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.
-
29 Jun 2021 2 repositories listedclasses predicted by the old model to deal with background shift and avoid catastrophic forgetting of the old classes.
-
23 Nov 2020 2 repositories listedclasses predicted by the old model to deal with background shift and avoid catastrophic forgetting of the old classes.
-
28 Mar 2025 1 repository listedIn this work, we focus on continual semantic segmentation (CSS), where segmentation networks are required to continuously learn new classes without erasing knowledge of previously learned ones.
-
23 Jul 2024 1 repository listedFirst, we introduce past-class backtrace distillation to balance the stability of existing knowledge with the adaptability to new information.
-
22 Jul 2024 1 repository listedConcretely, the proposed decoupling manner includes two ways, i. e., channel-wise decoupling and spatial-level neuron-relevant semantic consistency.
-
16 Jul 2024 1 repository listedAdditionally, in the case of the second approach, initializing the new class classifier with background knowledge triggers a similar background shift issue, but towards the new classes.
-
19 Apr 2024 1 repository listedBesides the common problem of classical catastrophic forgetting in the continual learning setting, CSS suffers from the inherent ambiguity of the background, a phenomenon we refer to as the "background shift'', since…
-
8 Feb 2024 1 repository listedThe problem becomes worse when it limits releasing the dataset of the old instruments for the old model due to privacy concerns and the unavailability of the data for the new or updated version of the instruments for…
-
22 Oct 2023 1 repository listedIn this paper, we present a review of CSS, committing to building a comprehensive survey on problem formulations, primary challenges, universal datasets, neoteric theories and multifarious applications.
-
9 Jun 2023 1 repository listedThis paper investigates the capability of plain Vision Transformers (ViTs) for semantic segmentation using the encoder-decoder framework and introduces SegViTv2.
-
1 Jan 2023 1 repository listedTo address this issue, we propose a new label-guided knowledge distillation (LGKD) loss, where the old model output is expanded and transplanted (with the guidance of the ground truth label) to form a semantically…
-
20 Sep 2022 1 repository listedContinual learning for Semantic Segmentation (CSS) is a rapidly emerging field, in which the capabilities of the segmentation model are incrementally improved by learning new classes or new domains.
-
15 Mar 2022 1 repository listedConsidering that pixels belonging to the same class in each image often share similar visual properties, a class-specific region pooling is applied to provide more efficient relationship information for knowledge…
-
10 Mar 2022 1 repository listed Syntology official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample)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.
-
19 Jul 2021 1 repository listedDeep learning for medical imaging suffers from temporal and privacy-related restrictions on data availability.
-
22 Jun 2021 1 repository listed Syntology official (archive's flag): 6 ran · 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 (of 12 harvested samples) · 12 pointer-only (licence)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…
-
26 Sep 2020 1 repository listed Syntology 10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified (of 13 harvested samples)We develop an algorithm for adapting a semantic segmentation model that is trained using a labeled source domain to generalize well in an unlabeled target domain.
-
Low-Rank Continual Pyramid Vision Transformer: Incrementally Segment Whole-Body Organs in CT with Light-Weighted Adaptation7 Oct 2024 0 repositories listedDeep segmentation networks achieve high performance when trained on specific datasets.
-
Taxonomy-Aware Continual Semantic Segmentation in Hyperbolic Spaces for Open-World Perception25 Jul 2024 0 repositories listedSemantic segmentation models are typically trained on a fixed set of classes, limiting their applicability in open-world scenarios.
-
ConSept: Continual Semantic Segmentation via Adapter-based Vision Transformer26 Feb 2024 0 repositories listedIn this paper, we delve into the realm of vision transformers for continual semantic segmentation, a problem that has not been sufficiently explored in previous literature.
-
FALCON: Fairness Learning via Contrastive Attention Approach to Continual Semantic Scene Understanding27 Nov 2023 0 repositories listedContinual Learning in semantic scene segmentation aims to continually learn new unseen classes in dynamic environments while maintaining previously learned knowledge.
-
Rethinking Exemplars for Continual Semantic Segmentation in Endoscopy Scenes: Entropy-based Mini-Batch Pseudo-Replay27 Aug 2023 0 repositories listedEndoscopy is a widely used technique for the early detection of diseases or robotic-assisted minimally invasive surgery (RMIS).
-
Fairness Continual Learning Approach to Semantic Scene Understanding in Open-World Environments25 May 2023 0 repositories listedContinual semantic segmentation aims to learn new classes while maintaining the information from the previous classes.
-
Continual Semantic Segmentation with Automatic Memory Sample Selection11 Apr 2023 0 repositories listedContinual Semantic Segmentation (CSS) extends static semantic segmentation by incrementally introducing new classes for training.
-
Effects of Architectures on Continual Semantic Segmentation21 Feb 2023 0 repositories listedResearch in the field of Continual Semantic Segmentation is mainly investigating novel learning algorithms to overcome catastrophic forgetting of neural networks.
-
Continual Segment: Towards a Single, Unified and Accessible Continual Segmentation Model of 143 Whole-body Organs in CT Scans1 Feb 2023 0 repositories listedDeep learning empowers the mainstream medical image segmentation methods.
-
Continual Segment: Towards a Single, Unified and Non-forgetting Continual Segmentation Model of 143 Whole-body Organs in CT Scans1 Jan 2023 0 repositories listedDeep learning empowers the mainstream medical image segmentation methods.
-
Preparing the Future for Continual Semantic Segmentation1 Jan 2023 0 repositories listedIn this study, we focus on Continual Semantic Segmentation (CSS) and present a novel approach to tackle the issue of existing methods struggling to learn new classes.
-
25 Nov 2022 0 repositories listedContinual learning for segmentation has recently seen increasing interest.
-
Learning with Style: Continual Semantic Segmentation Across Tasks and Domains13 Oct 2022 0 repositories listedDeep learning models dealing with image understanding in real-world settings must be able to adapt to a wide variety of tasks across different domains.
-
Continual Learning for Class- and Domain-Incremental Semantic Segmentation16 Sep 2022 0 repositories listed
-
RBC: Rectifying the Biased Context in Continual Semantic Segmentation16 Mar 2022 0 repositories listed
-
Class Similarity Weighted Knowledge Distillation for Continual Semantic Segmentation1 Jan 2022 0 repositories listed
-
10 Mar 2021 0 repositories listed
Syntology lines on 3 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
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