L3DOC: Lifelong 3D Object Classification

By Yuyang Liu, Yang Cong, Gan Sun. 2021

48 citations recorded by the source corpus.

3D object classification has been widely applied in both academic and industrial scenarios. However, most state-of-the-art algorithms rely on a fixed object classification task set, which cannot tackle the scenario when a new 3D object classification task is coming. Meanwhile, the existing lifelong learning models can easily destroy the learned tasks performance, due to the unordered, large-scale, and irregular 3D geometry data. To address these challenges, we propose a <underline>L</underline>ifelong <underline>3D</underline> <underline>O</underline>bject <underline>C</underline>lassification (<italic>i.e.,</italic> L3DOC) model, which can consecutively learn new 3D object classification tasks via imitating “human learning”. More specifically, the core idea of our model is to capture and store the cross-task common knowledge of 3D geometry data in a 3D neural network, named as <italic>point-knowledge</italic>, through employing layer-wise <italic>point-knowledge</italic> factorization architecture. Afterwards, a task-relevant knowledge distillation mechanism is employed to connect the current task to previous relevant tasks and effectively prevent <italic>catastrophic forgetting</italic>. It consists of a <italic>point-knowledge</italic> distillation module and a transforming-space distillation module, which transfers the accumulated <italic>point-knowledge</italic> from previous tasks and soft-transfers the compact factorized representations of the transforming-space, respectively. To our best knowledge, the proposed L3DOC algorithm is the first attempt to perform deep learning on 3D object classification tasks in a lifelong learning way. Extensive experiments on several point cloud benchmarks illustrate the superiority of our L3DOC model over the state-of-the-art lifelong learning methods.

Subfields: Aerospace Engineering, Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

Gunhee Kim

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Imbalanced Continual Learning with Partitioning Reservoir Sampling (2020, background): “Specifically, there have been many ventures into but not limited to single-label text classification [19], question answering [19], language instruction and translation [50], object detection [77,53], captioning [64] and even video representation learning [67,68].”
Augmented Box Replay: Overcoming Foreground Shift for Incremental Object Detection (2023, unknown): “Parameter-isolation methods [41, 44, 45, 61] modify the initial network to accommodate new classes.”