DeepAI AI Chat
Log In Sign Up

Learning without Forgetting for 3D Point Cloud Objects

by   Townim Chowdhury, et al.
North South University
Australian National University

When we fine-tune a well-trained deep learning model for a new set of classes, the network learns new concepts but gradually forgets the knowledge of old training. In some real-life applications, we may be interested in learning new classes without forgetting the capability of previous experience. Such learning without forgetting problem is often investigated using 2D image recognition tasks. In this paper, considering the growth of depth camera technology, we address the same problem for the 3D point cloud object data. This problem becomes more challenging in the 3D domain than 2D because of the unavailability of large datasets and powerful pretrained backbone models. We investigate knowledge distillation techniques on 3D data to reduce catastrophic forgetting of the previous training. Moreover, we improve the distillation process by using semantic word vectors of object classes. We observe that exploring the interrelation of old and new knowledge during training helps to learn new concepts without forgetting old ones. Experimenting on three 3D point cloud recognition backbones (PointNet, DGCNN, and PointConv) and synthetic (ModelNet40, ModelNet10) and real scanned (ScanObjectNN) datasets, we establish new baseline results on learning without forgetting for 3D data. This research will instigate many future works in this area.


page 1

page 2

page 3

page 4


Few-shot Class-incremental Learning for 3D Point Cloud Objects

Few-shot class-incremental learning (FSCIL) aims to incrementally fine-t...

Empowering Knowledge Distillation via Open Set Recognition for Robust 3D Point Cloud Classification

Real-world scenarios pose several challenges to deep learning based comp...

InCloud: Incremental Learning for Point Cloud Place Recognition

Place recognition is a fundamental component of robotics, and has seen t...

L3DOR: Lifelong 3D Object Recognition

3D object recognition has been widely-applied. However, most state-of-th...

I3DOL: Incremental 3D Object Learning without Catastrophic Forgetting

3D object classification has attracted appealing attentions in academic ...

InOR-Net: Incremental 3D Object Recognition Network for Point Cloud Representation

3D object recognition has successfully become an appealing research topi...

Semantic-aware Knowledge Distillation for Few-Shot Class-Incremental Learning

Few-shot class incremental learning (FSCIL) portrays the problem of lear...