Class-Incremental Semantic Segmentation
8 papers with code • 0 benchmarks • 0 datasets
Semantic segmentation with continous increments of classes.
Benchmarks
These leaderboards are used to track progress in Class-Incremental Semantic Segmentation
Subtasks
Most implemented papers
SSUL: Semantic Segmentation with Unknown Label for Exemplar-based Class-Incremental Learning
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.
Causes of Catastrophic Forgetting in Class-Incremental Semantic Segmentation
mmasana/FACIL
•
•
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.
Attribution-aware Weight Transfer: A Warm-Start Initialization for Class-Incremental Semantic Segmentation
In class-incremental semantic segmentation (CISS), deep learning architectures suffer from the critical problems of catastrophic forgetting and semantic background shift.
Mining Unseen Classes via Regional Objectness: A Simple Baseline for Incremental Segmentation
Our MicroSeg is based on the assumption that background regions with strong objectness possibly belong to those concepts in the historical or future stages.
Geometry and Uncertainty-Aware 3D Point Cloud Class-Incremental Semantic Segmentation
leolyj/3dpc-ciss
•
•
CVPR 2023
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 are being continuously discovered.
Evolving Knowledge Mining for Class Incremental Segmentation
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.
Few-shot Class-Incremental Semantic Segmentation via Pseudo-Labeling and Knowledge Distillation
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 in two steps.
CoinSeg: Contrast Inter- and Intra- Class Representations for Incremental Segmentation
zkzhang98/coinseg
•
•
ICCV 2023
However, most state-of-the-art methods use the freeze strategy for stability, which compromises the model's plasticity. In contrast, releasing parameter training for plasticity could lead to the best performance for all categories, but this requires discriminative feature representation. Therefore, we prioritize the model's plasticity and propose the Contrast inter- and intra-class representations for Incremental Segmentation (CoinSeg), which pursues discriminative representations for flexible parameter tuning.
