Multi-Level Foreground Prompt for Incremental Object Detection
In the study of incremental object detection, knowledge distillation and data replay are effective methods to mitigate catastrophic forgetting. However, current research on single-stage detectors is limited, single-stage detector outputs often contain excessive negative sample information, and direc...
Saved in:
Main Authors: | Jianwen Mo, Ronghua Zou, Hua Yuan |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2025-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/10819438/ |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
Studying Forgetting in Faster R-CNN for Online Object Detection: Analysis Scenarios, Localization in the Architecture, and Mitigation
by: Baptiste Wagner, et al.
Published: (2025-01-01) -
Knowledge Distillation in Object Detection for Resource-Constrained Edge Computing
by: Arief Setyanto, et al.
Published: (2025-01-01) -
A novel knowledge distillation framework for enhancing small object detection in blurry environments with unmanned aerial vehicle-assisted images
by: Sayed Jobaer, et al.
Published: (2024-12-01) -
Cross Teaching-Enhanced Multispectral Remote Sensing Object Detection With Transformer
by: Jiahe Zhu, et al.
Published: (2025-01-01) -
Object Re-Identification Based on Federated Incremental Subgradient Proximal Optimization
by: Li Kang, et al.
Published: (2025-01-01)