Class-Incremental Semantic Segmentation

9 papers with code • 0 benchmarks • 0 datasets

Semantic segmentation with continous increments of classes.

Most implemented papers

SSUL: Semantic Segmentation with Unknown Label for Exemplar-based Class-Incremental Learning

clovaai/SSUL NeurIPS 2021

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 16 Sep 2022

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.

Decomposed Knowledge Distillation for Class-Incremental Semantic Segmentation

cvlab-yonsei/dkd 12 Oct 2022

We introduce a CISS framework that alleviates the forgetting problem and facilitates learning novel classes effectively.

Attribution-aware Weight Transfer: A Warm-Start Initialization for Class-Incremental Semantic Segmentation

dfki-av/awt-for-ciss 13 Oct 2022

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

zkzhang98/microseg 13 Nov 2022

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

zhihelu/ending_iss 3 Jun 2023

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

chasonjiang/fscilss 5 Aug 2023

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.