Geometry and uncertainty-aware 3d point cloud class-incremental semantic segmentation
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 …
current methods require training data for all classes at once, and are not suitable for real-life …
Continual learning on 3D point clouds with random compressed rehearsal
Contemporary deep neural networks offer state-of-the-art results when applied to visual
reasoning, eg, in the context of 3D point cloud data. Point clouds are an important data type …
reasoning, eg, in the context of 3D point cloud data. Point clouds are an important data type …
Cross-Domain Incremental Feature Learning for ALS Point Cloud Semantic Segmentation with Few Samples
M Dai, S **ng, Q Xu, P Li, J Pan… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Feature learning of airborne laser scanning (ALS) point clouds is challenged by both the
limited annotated samples and imbalanced class distribution. An intuitive way involves …
limited annotated samples and imbalanced class distribution. An intuitive way involves …
Rethinking task-incremental learning baselines
It is common to have continuous streams of new data that need to be introduced in the
system in real-world applications. The model needs to learn newly added capabilities (future …
system in real-world applications. The model needs to learn newly added capabilities (future …
A Benchmark Grocery Dataset of Realworld Point Clouds From Single View
Fine-grained grocery object recognition is an important computer vision problem with broad
applications in automatic checkout, in-store robotic navigation, and assistive technologies …
applications in automatic checkout, in-store robotic navigation, and assistive technologies …
ReFu: Recursive Fusion for Exemplar-Free 3D Class-Incremental Learning
We introduce a novel Recursive Fusion model, dubbed ReFu, designed to integrate point
clouds and meshes for exemplar-free 3D Class-Incremental Learning, where the model …
clouds and meshes for exemplar-free 3D Class-Incremental Learning, where the model …
Continual Learning in 3D Point Clouds: Employing Spectral Techniques for Exemplar Selection
We introduce a novel framework for Continual Learning in 3D object classification (CL3D).
Our approach is based on the selection of prototypes from each class using spectral …
Our approach is based on the selection of prototypes from each class using spectral …