SDDGR: Stable Diffusion-Based Deep Generative Replay for Class Incremental Object Detection

In the field of class incremental leaming (CIL), generative replay has become increasingly prominent as a method to mitigate the catastrophic forgetting, alongside the continuous improvements in generative models. However, its application in class incremental object detection (CIOD) has been signifi...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) pp. 28772 - 28781
Main Authors: Kim, Junsu, Cho, Hoseong, Kim, Jihyeon, Tiruneh, Yihalem Yimolal, Baek, Seungryul
Format: Conference Proceeding
Language:English
Published: IEEE 16.06.2024
Subjects:
Class Incremental Object detection
Complexity theory
Computational efficiency
Computer vision
Continual learning
deep generative
Incremental learning
Object detection
Pattern recognition
Regulation
replay
Stable diffusion
Text to image
ISSN:1063-6919
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In the field of class incremental leaming (CIL), generative replay has become increasingly prominent as a method to mitigate the catastrophic forgetting, alongside the continuous improvements in generative models. However, its application in class incremental object detection (CIOD) has been significantly limited, primarily due to the complexities of scenes involving multiple labels. In this paper, we propose a novel approach called stable diffusion deep generative replay (SDDGR) for CIOD. Our method utilizes a diffusion-based generative model with pre-trained text-to-image diffusion networks to generate realistic and diverse synthetic images. SDDGR incorporates an iterative refinement strategy to produce high-quality images encompassing old classes. Additionally, we adopt an L2 knowledge distillation technique to improve the retention of prior knowledge in synthetic images. Furthermore, our approach includes pseudo-labeling for old objects within new task images, preventing misclassification as background elements. Extensive experiments on the COCO 2017 dataset demonstrate that SD-DGR significantly outperforms existing algorithms, achieving a new state-of-the-art in various CIOD scenarios.
ISSN:1063-6919
DOI:10.1109/CVPR52733.2024.02718