Brain Inspired Adaptive Memory Dual-Net for Few-Shot Image Classification
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917950024318976 |
|---|---|
| author | Di, Kexin Li, Xiuxing Han, Yuyang Li, Ziyu Li, Qing Wu, Xia |
| author_facet | Di, Kexin Li, Xiuxing Han, Yuyang Li, Ziyu Li, Qing Wu, Xia |
| contents | Few-shot image classification has become a popular research topic for its wide application in real-world scenarios, however the problem of supervision collapse induced by single image-level annotation remains a major challenge. Existing methods aim to tackle this problem by locating and aligning relevant local features. However, the high intra-class variability in real-world images poses significant challenges in locating semantically relevant local regions under few-shot settings. Drawing inspiration from the human's complementary learning system, which excels at rapidly capturing and integrating semantic features from limited examples, we propose the generalization-optimized Systems Consolidation Adaptive Memory Dual-Network, SCAM-Net. This approach simulates the systems consolidation of complementary learning system with an adaptive memory module, which successfully addresses the difficulty of identifying meaningful features in few-shot scenarios. Specifically, we construct a Hippocampus-Neocortex dual-network that consolidates structured representation of each category, the structured representation is then stored and adaptively regulated following the generalization optimization principle in a long-term memory inside Neocortex. Extensive experiments on benchmark datasets show that the proposed model has achieved state-of-the-art performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_07396 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Brain Inspired Adaptive Memory Dual-Net for Few-Shot Image Classification Di, Kexin Li, Xiuxing Han, Yuyang Li, Ziyu Li, Qing Wu, Xia Computer Vision and Pattern Recognition Artificial Intelligence Few-shot image classification has become a popular research topic for its wide application in real-world scenarios, however the problem of supervision collapse induced by single image-level annotation remains a major challenge. Existing methods aim to tackle this problem by locating and aligning relevant local features. However, the high intra-class variability in real-world images poses significant challenges in locating semantically relevant local regions under few-shot settings. Drawing inspiration from the human's complementary learning system, which excels at rapidly capturing and integrating semantic features from limited examples, we propose the generalization-optimized Systems Consolidation Adaptive Memory Dual-Network, SCAM-Net. This approach simulates the systems consolidation of complementary learning system with an adaptive memory module, which successfully addresses the difficulty of identifying meaningful features in few-shot scenarios. Specifically, we construct a Hippocampus-Neocortex dual-network that consolidates structured representation of each category, the structured representation is then stored and adaptively regulated following the generalization optimization principle in a long-term memory inside Neocortex. Extensive experiments on benchmark datasets show that the proposed model has achieved state-of-the-art performance. |
| title | Brain Inspired Adaptive Memory Dual-Net for Few-Shot Image Classification |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2503.07396 |