arXiv · 2025 · Preprint

Beyond Synthetic Replays: Turning Diffusion Features into Few-Shot Class-Incremental Learning Knowledge

Junsu Kim, Yunhoe Ku, Dongyoon Han, Seungryul Baek

Rendered by arXiv from the LaTeX source. If anything looks wrong, switch to the PDF.HTML · PDF · Open in a new tab ↗ · Close
Date
2025-03-30
Citations
2
arXiv
2503.23402
Cite
@misc{kim2025beyond,
  title = {Beyond Synthetic Replays: Turning Diffusion Features into Few-Shot Class-Incremental Learning Knowledge},
  author = {Junsu Kim and Yunhoe Ku and Dongyoon Han and Seungryul Baek},
  year = {2025},
  eprint = {2503.23402},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2503.23402},
}