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

02/20/2023
by   Jiahua Dong, et al.
0

3D object recognition has successfully become an appealing research topic in the real-world. However, most existing recognition models unreasonably assume that the categories of 3D objects cannot change over time in the real-world. This unrealistic assumption may result in significant performance degradation for them to learn new classes of 3D objects consecutively, due to the catastrophic forgetting on old learned classes. Moreover, they cannot explore which 3D geometric characteristics are essential to alleviate the catastrophic forgetting on old classes of 3D objects. To tackle the above challenges, we develop a novel Incremental 3D Object Recognition Network (i.e., InOR-Net), which could recognize new classes of 3D objects continuously via overcoming the catastrophic forgetting on old classes. Specifically, a category-guided geometric reasoning is proposed to reason local geometric structures with distinctive 3D characteristics of each class by leveraging intrinsic category information. We then propose a novel critic-induced geometric attention mechanism to distinguish which 3D geometric characteristics within each class are beneficial to overcome the catastrophic forgetting on old classes of 3D objects, while preventing the negative influence of useless 3D characteristics. In addition, a dual adaptive fairness compensations strategy is designed to overcome the forgetting brought by class imbalance, by compensating biased weights and predictions of the classifier. Comparison experiments verify the state-of-the-art performance of the proposed InOR-Net model on several public point cloud datasets.

READ FULL TEXT

page 1

page 4

page 9

page 10

page 13

research
12/16/2020

I3DOL: Incremental 3D Object Learning without Catastrophic Forgetting

3D object classification has attracted appealing attentions in academic ...
research
08/07/2023

Heterogeneous Forgetting Compensation for Class-Incremental Learning

Class-incremental learning (CIL) has achieved remarkable successes in le...
research
02/02/2023

No One Left Behind: Real-World Federated Class-Incremental Learning

Federated learning (FL) is a hot collaborative training framework via ag...
research
06/27/2021

Learning without Forgetting for 3D Point Cloud Objects

When we fine-tune a well-trained deep learning model for a new set of cl...
research
04/06/2021

Learnable Expansion-and-Compression Network for Few-shot Class-Incremental Learning

Few-shot class-incremental learning (FSCIL), which targets at continuous...
research
09/23/2021

Lifelong 3D Object Recognition and Grasp Synthesis Using Dual Memory Recurrent Self-Organization Networks

Humans learn to recognize and manipulate new objects in lifelong setting...
research
11/27/2017

Memory Aware Synapses: Learning what (not) to forget

Humans can learn in a continuous manner. Old rarely utilized knowledge c...

Please sign up or login with your details

Forgot password? Click here to reset