DA-CIL: Towards Domain Adaptive Class-Incremental 3D Object Detection
- URL: http://arxiv.org/abs/2212.02057v1
- Date: Mon, 5 Dec 2022 06:45:27 GMT
- Title: DA-CIL: Towards Domain Adaptive Class-Incremental 3D Object Detection
- Authors: Ziyuan Zhao, Mingxi Xu, Peisheng Qian, Ramanpreet Singh Pahwa, Richard
Chang
- Abstract summary: We propose a novel 3D domain adaptive class-incremental object detection framework, DA-CIL.
We design a novel dual-domain copy-paste augmentation method to construct multiple augmented domains for diversifying training distributions.
Experiments on various datasets demonstrate the effectiveness of the proposed method over baselines.
- Score: 2.207918236777924
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Deep learning has achieved notable success in 3D object detection with the
advent of large-scale point cloud datasets. However, severe performance
degradation in the past trained classes, i.e., catastrophic forgetting, still
remains a critical issue for real-world deployment when the number of classes
is unknown or may vary. Moreover, existing 3D class-incremental detection
methods are developed for the single-domain scenario, which fail when
encountering domain shift caused by different datasets, varying environments,
etc. In this paper, we identify the unexplored yet valuable scenario, i.e.,
class-incremental learning under domain shift, and propose a novel 3D domain
adaptive class-incremental object detection framework, DA-CIL, in which we
design a novel dual-domain copy-paste augmentation method to construct multiple
augmented domains for diversifying training distributions, thereby facilitating
gradual domain adaptation. Then, multi-level consistency is explored to
facilitate dual-teacher knowledge distillation from different domains for
domain adaptive class-incremental learning. Extensive experiments on various
datasets demonstrate the effectiveness of the proposed method over baselines in
the domain adaptive class-incremental learning scenario.
Related papers
- Domain Generalization of 3D Object Detection by Density-Resampling [14.510085711178217]
Point-cloud-based 3D object detection suffers from performance degradation when encountering data with novel domain gaps.
We propose an SDG method to improve the generalizability of 3D object detection to unseen target domains.
Our work introduces a novel data augmentation method and contributes a new multi-task learning strategy in the methodology.
arXiv Detail & Related papers (2023-11-17T20:01:29Z) - Revisiting Domain-Adaptive 3D Object Detection by Reliable, Diverse and
Class-balanced Pseudo-Labeling [38.07637524378327]
Unsupervised domain adaptation (DA) with the aid of pseudo labeling techniques has emerged as a crucial approach for domain-adaptive 3D object detection.
Existing DA methods suffer from a substantial drop in performance when applied to a multi-class training setting.
We propose a novel ReDB framework tailored for learning to detect all classes at once.
arXiv Detail & Related papers (2023-07-16T04:34:11Z) - Unsupervised Domain Adaptation for Monocular 3D Object Detection via
Self-Training [57.25828870799331]
We propose STMono3D, a new self-teaching framework for unsupervised domain adaptation on Mono3D.
We develop a teacher-student paradigm to generate adaptive pseudo labels on the target domain.
STMono3D achieves remarkable performance on all evaluated datasets and even surpasses fully supervised results on the KITTI 3D object detection dataset.
arXiv Detail & Related papers (2022-04-25T12:23:07Z) - Improving Transferability of Domain Adaptation Networks Through Domain
Alignment Layers [1.3766148734487902]
Multi-source unsupervised domain adaptation (MSDA) aims at learning a predictor for an unlabeled domain by assigning weak knowledge from a bag of source models.
We propose to embed Multi-Source version of DomaIn Alignment Layers (MS-DIAL) at different levels of the predictor.
Our approach can improve state-of-the-art MSDA methods, yielding relative gains of up to +30.64% on their classification accuracies.
arXiv Detail & Related papers (2021-09-06T18:41:19Z) - Unsupervised Domain Adaptive 3D Detection with Multi-Level Consistency [90.71745178767203]
Deep learning-based 3D object detection has achieved unprecedented success with the advent of large-scale autonomous driving datasets.
Existing 3D domain adaptive detection methods often assume prior access to the target domain annotations, which is rarely feasible in the real world.
We study a more realistic setting, unsupervised 3D domain adaptive detection, which only utilizes source domain annotations.
arXiv Detail & Related papers (2021-07-23T17:19:23Z) - AFAN: Augmented Feature Alignment Network for Cross-Domain Object
Detection [90.18752912204778]
Unsupervised domain adaptation for object detection is a challenging problem with many real-world applications.
We propose a novel augmented feature alignment network (AFAN) which integrates intermediate domain image generation and domain-adversarial training.
Our approach significantly outperforms the state-of-the-art methods on standard benchmarks for both similar and dissimilar domain adaptations.
arXiv Detail & Related papers (2021-06-10T05:01:20Z) - Adaptively-Accumulated Knowledge Transfer for Partial Domain Adaptation [66.74638960925854]
Partial domain adaptation (PDA) deals with a realistic and challenging problem when the source domain label space substitutes the target domain.
We propose an Adaptively-Accumulated Knowledge Transfer framework (A$2$KT) to align the relevant categories across two domains.
arXiv Detail & Related papers (2020-08-27T00:53:43Z) - Domain Conditioned Adaptation Network [90.63261870610211]
We propose a Domain Conditioned Adaptation Network (DCAN) to excite distinct convolutional channels with a domain conditioned channel attention mechanism.
This is the first work to explore the domain-wise convolutional channel activation for deep DA networks.
arXiv Detail & Related papers (2020-05-14T04:23:24Z) - Multi-Task Incremental Learning for Object Detection [71.57155077119839]
Multi-task learns multiple tasks, while sharing knowledge and computation among them.
It suffers from catastrophic forgetting of previous knowledge when learned incrementally without access to the old data.
arXiv Detail & Related papers (2020-02-13T04:58:37Z)
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.