Hierarchical Neural Collapse Detection Transformer for Class Incremental Object Detection
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913887775883264 |
|---|---|
| author | Pham, Duc Thanh Nguyen, Hong Dang Quoc, Nhat Minh Nguyen Van, Linh Ngo Viet, Sang Dinh Nguyen, Duc Anh |
| author_facet | Pham, Duc Thanh Nguyen, Hong Dang Quoc, Nhat Minh Nguyen Van, Linh Ngo Viet, Sang Dinh Nguyen, Duc Anh |
| contents | Recently, object detection models have witnessed notable performance improvements, particularly with transformer-based models. However, new objects frequently appear in the real world, requiring detection models to continually learn without suffering from catastrophic forgetting. Although Incremental Object Detection (IOD) has emerged to address this challenge, these existing models are still not practical due to their limited performance and prolonged inference time. In this paper, we introduce a novel framework for IOD, called Hier-DETR: Hierarchical Neural Collapse Detection Transformer, ensuring both efficiency and competitive performance by leveraging Neural Collapse for imbalance dataset and Hierarchical relation of classes' labels. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_08562 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Hierarchical Neural Collapse Detection Transformer for Class Incremental Object Detection Pham, Duc Thanh Nguyen, Hong Dang Quoc, Nhat Minh Nguyen Van, Linh Ngo Viet, Sang Dinh Nguyen, Duc Anh Computer Vision and Pattern Recognition Recently, object detection models have witnessed notable performance improvements, particularly with transformer-based models. However, new objects frequently appear in the real world, requiring detection models to continually learn without suffering from catastrophic forgetting. Although Incremental Object Detection (IOD) has emerged to address this challenge, these existing models are still not practical due to their limited performance and prolonged inference time. In this paper, we introduce a novel framework for IOD, called Hier-DETR: Hierarchical Neural Collapse Detection Transformer, ensuring both efficiency and competitive performance by leveraging Neural Collapse for imbalance dataset and Hierarchical relation of classes' labels. |
| title | Hierarchical Neural Collapse Detection Transformer for Class Incremental Object Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2506.08562 |