Ancestral Mamba: Enhancing Selective Discriminant Space Model with Online Visual Prototype Learning for Efficient and Robust Discriminant Approach
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_ | 1866915218446090240 |
|---|---|
| author | Qin, Jiahao Liu, Feng Zong, Lu |
| author_facet | Qin, Jiahao Liu, Feng Zong, Lu |
| contents | In the realm of computer graphics, the ability to learn continuously from non-stationary data streams while adapting to new visual patterns and mitigating catastrophic forgetting is of paramount importance. Existing approaches often struggle to capture and represent the essential characteristics of evolving visual concepts, hindering their applicability to dynamic graphics tasks. In this paper, we propose Ancestral Mamba, a novel approach that integrates online prototype learning into a selective discriminant space model for efficient and robust online continual learning. The key components of our approach include Ancestral Prototype Adaptation (APA), which continuously refines and builds upon learned visual prototypes, and Mamba Feedback (MF), which provides targeted feedback to adapt to challenging visual patterns. APA enables the model to continuously adapt its prototypes, building upon ancestral knowledge to tackle new challenges, while MF acts as a targeted feedback mechanism, focusing on challenging classes and refining their representations. Extensive experiments on graphics-oriented datasets, such as CIFAR-10 and CIFAR-100, demonstrate the superior performance of Ancestral Mamba compared to state-of-the-art baselines, achieving significant improvements in accuracy and forgetting mitigation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_22729 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Ancestral Mamba: Enhancing Selective Discriminant Space Model with Online Visual Prototype Learning for Efficient and Robust Discriminant Approach Qin, Jiahao Liu, Feng Zong, Lu Graphics Artificial Intelligence Computer Vision and Pattern Recognition In the realm of computer graphics, the ability to learn continuously from non-stationary data streams while adapting to new visual patterns and mitigating catastrophic forgetting is of paramount importance. Existing approaches often struggle to capture and represent the essential characteristics of evolving visual concepts, hindering their applicability to dynamic graphics tasks. In this paper, we propose Ancestral Mamba, a novel approach that integrates online prototype learning into a selective discriminant space model for efficient and robust online continual learning. The key components of our approach include Ancestral Prototype Adaptation (APA), which continuously refines and builds upon learned visual prototypes, and Mamba Feedback (MF), which provides targeted feedback to adapt to challenging visual patterns. APA enables the model to continuously adapt its prototypes, building upon ancestral knowledge to tackle new challenges, while MF acts as a targeted feedback mechanism, focusing on challenging classes and refining their representations. Extensive experiments on graphics-oriented datasets, such as CIFAR-10 and CIFAR-100, demonstrate the superior performance of Ancestral Mamba compared to state-of-the-art baselines, achieving significant improvements in accuracy and forgetting mitigation. |
| title | Ancestral Mamba: Enhancing Selective Discriminant Space Model with Online Visual Prototype Learning for Efficient and Robust Discriminant Approach |
| topic | Graphics Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.22729 |