Class-Incremental Semantic Segmentation

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

No benchmark for this task in the archive.

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

No dataset record in the archive lists this task.

Subtasks archive 2025-07-28

12 subtasks in the archive's task tree.

Parent tasks archive 2025-07-28

Most implemented papers archive 2025-07-28

16 shown of 16 papers with code (31 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.

• IPSeg: Image Posterior Mitigates Semantic Drift in Class-Incremental Segmentation
  7 Feb 2025 1 repository listed
  IPSeg introduces two key mechanisms: (1) leveraging image posterior probabilities to align optimization across stages and mitigate the effects of separate optimization, and (2) employing semantics decoupling to handle…
• Adaptive Prototype Replay for Class Incremental Semantic Segmentation
  17 Dec 2024 1 repository listed
  However, they overlook a critical issue: in CISS, the representation of class knowledge is updated continuously through incremental learning, whereas prototype replay methods maintain fixed prototypes.
• SegACIL: Solving the Stability-Plasticity Dilemma in Class-Incremental Semantic Segmentation
  14 Dec 2024 1 repository listed
  Extensive experiments on the Pascal VOC2012 dataset show that SegACIL achieves superior performance in the sequential, disjoint, and overlap settings, offering a robust solution to the challenges of class-incremental…
• CIT: Rethinking Class-incremental Semantic Segmentation with a Class Independent Transformation
  5 Nov 2024 1 repository listed
  Class-incremental semantic segmentation (CSS) requires that a model learn to segment new classes without forgetting how to segment previous ones: this is typically achieved by distilling the current knowledge and…
• Early Preparation Pays Off: New Classifier Pre-tuning for Class Incremental Semantic Segmentation
  19 Jul 2024 1 repository listed Syntology ran 6 of 6 samples · 0 unverified · 6 pointer-only (licence)
  In this paper, we propose a new classifier pre-tuning~(NeST) method applied before the formal training process, learning a transformation from old classifiers to generate new classifiers for initialization rather than…
• 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.
• Towards Realistic Incremental Scenario in Class Incremental Semantic Segmentation
  16 May 2024 1 repository listed
  This efficiently addresses the issue above while meeting the requirement of CISS scenario, such as capturing the background shifts.
• CoinSeg: Contrast Inter- and Intra- Class Representations for Incremental Segmentation
  10 Oct 2023 1 repository listed Syntology ran 10 of 15 samples · 5 unverified · 15 pointer-only (licence)
  However, most state-of-the-art methods use the freeze strategy for stability, which compromises the model's plasticity.
• Few-shot Class-Incremental Semantic Segmentation via Pseudo-Labeling and Knowledge Distillation
  5 Aug 2023 1 repository listed
  Given only one or a few images labeled with the novel classes and a much larger set of unlabeled images, we transfer the knowledge from labeled images to unlabeled images with a coarse-to-fine pseudo-labeling approach…
• Evolving Knowledge Mining for Class Incremental Segmentation
  3 Jun 2023 1 repository listed
  In this paper, we for the first time investigate the efficient multi-grained knowledge reuse for CISS, and propose a novel method, Evolving kNowleDge minING (ENDING), employing a frozen backbone.
• Geometry and Uncertainty-Aware 3D Point Cloud Class-Incremental Semantic Segmentation
  1 Jan 2023 1 repository listed
  Despite the significant recent progress made on 3D point cloud semantic segmentation, the current methods require training data for all classes at once, and are not suitable for real-life scenarios where new categories…
• Mining Unseen Classes via Regional Objectness: A Simple Baseline for Incremental Segmentation
  13 Nov 2022 1 repository listed
  Our MicroSeg is based on the assumption that background regions with strong objectness possibly belong to those concepts in the historical or future stages.
• Attribution-aware Weight Transfer: A Warm-Start Initialization for Class-Incremental Semantic Segmentation
  13 Oct 2022 1 repository listed Syntology ran 1 of 8 samples · 7 unverified
  In class-incremental semantic segmentation (CISS), deep learning architectures suffer from the critical problems of catastrophic forgetting and semantic background shift.
• Decomposed Knowledge Distillation for Class-Incremental Semantic Segmentation
  12 Oct 2022 1 repository listed Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
  We introduce a CISS framework that alleviates the forgetting problem and facilitates learning novel classes effectively.
• Causes of Catastrophic Forgetting in Class-Incremental Semantic Segmentation
  16 Sep 2022 1 repository listed
  Therefore, in a set of experiments and representational analyses, we demonstrate that the semantic shift of the background class and a bias towards new classes are the major causes of forgetting in CiSS.
• 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…

Syntology lines on 5 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.