Work

Cosine Prompt-Based Class Incremental Semantic Segmentation for Point Clouds

Year: 2025

Type: article

Abstract: Although current 3D semantic segmentation methods have achieved significant success, they suffer from catastrophic forgetting when confronted with dynamic, open environments. To address this issue, class incremental learning is introduced to update models while maintaining a balance between plasticity and stability. In this work, we propose CosPrompt, a rehearsal-free approach for class incremental semantic segmentation. Specifically, we freeze the prompts for existing classes and incrementally expand and fine-tune the prompts for new classes, thereby generating discriminative and customized features. We employ clamping operations to regulate backward propagation, ensuring smooth training. Furthermore, we utilize the learning without forgetting loss and pseudo-label generation to further mitigate catastrophic forgetting. We conduct comparative and ablation experiments on the S3DIS dataset and ScanNet v2 dataset, demonstrating the effectiveness and feasibility of our method.

Source: Algorithms

DOI: 10.3390/a18100648

Authors: Lei Guo, Hongye Li, Min Pang, Kaowei Liu, Xie Han, Fengguang Xiong

Institution: North University of China

Language: English

Topic: 3D Shape Modeling and Analysis

Subfield: Computational Mechanics

Field: Engineering

Domain: Physical Sciences

Open Access status: gold

Estimated APC paid: $1,930

Funders: National Natural Science Foundation of China, Natural Science Foundation of Shanxi Province