Continual 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.

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. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

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

Most implemented papers archive 2025-07-28

17 shown of 17 papers with code (34 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Tackling Catastrophic Forgetting and Background Shift in Continual Semantic Segmentation
  29 Jun 2021 2 repositories listed
  classes predicted by the old model to deal with background shift and avoid catastrophic forgetting of the old classes.
• PLOP: Learning without Forgetting for Continual Semantic Segmentation
  23 Nov 2020 2 repositories listed
  classes predicted by the old model to deal with background shift and avoid catastrophic forgetting of the old classes.
• Beyond Background Shift: Rethinking Instance Replay in Continual Semantic Segmentation
  28 Mar 2025 1 repository listed
  In 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.
• Strike a Balance in Continual Panoptic Segmentation
  23 Jul 2024 1 repository listed
  First, we introduce past-class backtrace distillation to balance the stability of existing knowledge with the adaptability to new information.
• Learning at a Glance: Towards Interpretable Data-limited Continual Semantic Segmentation via Semantic-Invariance Modelling
  22 Jul 2024 1 repository listed
  Concretely, the proposed decoupling manner includes two ways, i.
• Mitigating Background Shift in Class-Incremental Semantic Segmentation
  16 Jul 2024 1 repository listed
  Additionally, 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.
• BACS: Background Aware Continual Semantic Segmentation
  19 Apr 2024 1 repository listed
  Besides 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…
• Privacy-Preserving Synthetic Continual Semantic Segmentation for Robotic Surgery
  8 Feb 2024 1 repository listed
  The 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…
• A Survey on Continual Semantic Segmentation: Theory, Challenge, Method and Application
  22 Oct 2023 1 repository listed
  In 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.
• SegViTv2: Exploring Efficient and Continual Semantic Segmentation with Plain Vision Transformers
  9 Jun 2023 1 repository listed
  This paper investigates the capability of plain Vision Transformers (ViTs) for semantic segmentation using the encoder-decoder framework and introduces \textbf{SegViTv2}.
• Label-Guided Knowledge Distillation for Continual Semantic Segmentation on 2D Images and 3D Point Clouds
  1 Jan 2023 1 repository listed
  To 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…
• Improving Replay-Based Continual Semantic Segmentation with Smart Data Selection
  20 Sep 2022 1 repository listed
  Continual 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.
• SATS: Self-Attention Transfer for Continual Semantic Segmentation
  15 Mar 2022 1 repository listed
  Considering 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…
• Representation Compensation Networks for Continual Semantic Segmentation
  10 Mar 2022 1 repository listed Syntology ran 0 of 1 samples · 1 unverified
  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.
• Adversarial Continual Learning for Multi-Domain Hippocampal Segmentation
  19 Jul 2021 1 repository listed
  Deep learning for medical imaging suffers from temporal and privacy-related restrictions on data availability.
• SSUL: Semantic Segmentation with Unknown Label for Exemplar-based Class-Incremental Learning
  22 Jun 2021 1 repository listed Syntology ran 6 of 12 samples · 6 unverified · 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…
• Unsupervised Model Adaptation for Continual Semantic Segmentation
  26 Sep 2020 1 repository listed Syntology ran 0 of 13 samples · 13 unverified
  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.

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. Read from the graph 2026-09-24.