ReFu: Recursive Fusion for Exemplar-Free 3D Class-Incremental Learning

• URL: http://arxiv.org/abs/2409.12326v1
• Date: Wed, 18 Sep 2024 21:44:33 GMT
• Title: ReFu: Recursive Fusion for Exemplar-Free 3D Class-Incremental Learning
• Authors: Yi Yang, Lei Zhong, Huiping Zhuang,
• Abstract summary: We introduce a novel Recursive Fusion model, dubbed ReFu, designed to integrate point clouds and meshes for exemplar-free 3D Class-Incremental Learning. We propose a fusion module, featuring a Pointcloud-guided Mesh Attention Layer that learns correlations between the two modalities. Experiments across various datasets demonstrate that our proposed framework outperforms existing methods in 3D class-incremental learning.
• Score: 22.918894897067574
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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 learns new 3D classes while retaining knowledge of previously learned ones. Unlike existing methods that either rely on storing historical data to mitigate forgetting or focus on single data modalities, ReFu eliminates the need for exemplar storage while utilizing the complementary strengths of both point clouds and meshes. To achieve this, we introduce a recursive method which continuously accumulates knowledge by updating the regularized auto-correlation matrix. Furthermore, we propose a fusion module, featuring a Pointcloud-guided Mesh Attention Layer that learns correlations between the two modalities. This mechanism effectively integrates point cloud and mesh features, leading to more robust and stable continual learning. Experiments across various datasets demonstrate that our proposed framework outperforms existing methods in 3D class-incremental learning. Project Page: https://arlo397.github.io/ReFu/

Related papers

• Foundation Model-Powered 3D Few-Shot Class Incremental Learning via Training-free Adaptor [9.54964908165465]
  This paper introduces a new method to tackle the Few-Shot Continual Incremental Learning problem in 3D point cloud environments. We leverage a foundational 3D model trained extensively on point cloud data. Our approach uses a dual cache system: first, it uses previous test samples based on how confident the model was in its predictions to prevent forgetting, and second, it includes a small number of new task samples to prevent overfitting.
  arXiv  Detail & Related papers  (2024-10-11T20:23:00Z)
• MIRACLE 3D: Memory-efficient Integrated Robust Approach for Continual Learning on Point Clouds via Shape Model construction [0.4604003661048266]
  We introduce a novel framework for memory-efficient and privacy-preserving continual learning in 3D object classification. Our method constructs a compact shape model for each class, retaining only the mean shape along with a few key modes of variation. We validate our approach through extensive experiments on the ModelNet40, ShapeNet, and ScanNet datasets.
  arXiv  Detail & Related papers  (2024-10-08T23:12:33Z)
• Hierarchical Temporal Context Learning for Camera-based Semantic Scene Completion [57.232688209606515]
  We present HTCL, a novel Temporal Temporal Context Learning paradigm for improving camera-based semantic scene completion. Our method ranks $1st$ on the Semantic KITTI benchmark and even surpasses LiDAR-based methods in terms of mIoU.
  arXiv  Detail & Related papers  (2024-07-02T09:11:17Z)
• StarNet: Style-Aware 3D Point Cloud Generation [82.30389817015877]
  StarNet is able to reconstruct and generate high-fidelity and even 3D point clouds using a mapping network. Our framework achieves comparable state-of-the-art performance on various metrics in the point cloud reconstruction and generation tasks.
  arXiv  Detail & Related papers  (2023-03-28T08:21:44Z)
• CLR-GAM: Contrastive Point Cloud Learning with Guided Augmentation and Feature Mapping [12.679625717350113]
  We present CLR-GAM, a contrastive learning-based framework with Guided Augmentation (GA) for efficient dynamic exploration strategy. We empirically demonstrate that the proposed approach achieves state-of-the-art performance on both simulated and real-world 3D point cloud datasets.
  arXiv  Detail & Related papers  (2023-02-28T04:38:52Z)
• CMD: Self-supervised 3D Action Representation Learning with Cross-modal Mutual Distillation [130.08432609780374]
  In 3D action recognition, there exists rich complementary information between skeleton modalities. We propose a new Cross-modal Mutual Distillation (CMD) framework with the following designs. Our approach outperforms existing self-supervised methods and sets a series of new records.
  arXiv  Detail & Related papers  (2022-08-26T06:06:09Z)
• Learning-based Point Cloud Registration for 6D Object Pose Estimation in the Real World [55.7340077183072]
  We tackle the task of estimating the 6D pose of an object from point cloud data. Recent learning-based approaches to addressing this task have shown great success on synthetic datasets. We analyze the causes of these failures, which we trace back to the difference between the feature distributions of the source and target point clouds.
  arXiv  Detail & Related papers  (2022-03-29T07:55:04Z)
• IDEA-Net: Dynamic 3D Point Cloud Interpolation via Deep Embedding Alignment [58.8330387551499]
  We formulate the problem as estimation of point-wise trajectories (i.e., smooth curves) We propose IDEA-Net, an end-to-end deep learning framework, which disentangles the problem under the assistance of the explicitly learned temporal consistency. We demonstrate the effectiveness of our method on various point cloud sequences and observe large improvement over state-of-the-art methods both quantitatively and visually.
  arXiv  Detail & Related papers  (2022-03-22T10:14:08Z)
• Static-Dynamic Co-Teaching for Class-Incremental 3D Object Detection [71.18882803642526]
  Deep learning approaches have shown remarkable performance in the 3D object detection task. They suffer from a catastrophic performance drop when incrementally learning new classes without revisiting the old data. This "catastrophic forgetting" phenomenon impedes the deployment of 3D object detection approaches in real-world scenarios. We present the first solution - SDCoT, a novel static-dynamic co-teaching method.
  arXiv  Detail & Related papers  (2021-12-14T09:03:41Z)
• Point Transformer for Shape Classification and Retrieval of 3D and ALS Roof PointClouds [3.3744638598036123]
  This paper proposes a fully attentional model - em Point Transformer, for deriving a rich point cloud representation. The model's shape classification and retrieval performance are evaluated on a large-scale urban dataset - RoofN3D and a standard benchmark dataset ModelNet40. The proposed method outperforms other state-of-the-art models in the RoofN3D dataset, gives competitive results in the ModelNet40 benchmark, and showcases high robustness to various unseen point corruptions.
  arXiv  Detail & Related papers  (2020-11-08T08:11:02Z)
• Two-Level Residual Distillation based Triple Network for Incremental Object Detection [21.725878050355824]
  We propose a novel incremental object detector based on Faster R-CNN to continuously learn from new object classes without using old data. It is a triple network where an old model and a residual model as assistants for helping the incremental model learning on new classes without forgetting the previous learned knowledge.
  arXiv  Detail & Related papers  (2020-07-27T11:04:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.