2 papers
cs.CV2025
Deep Learning for Cross-Domain Few-Shot Visual Recognition: A Survey
Huali Xu, Shuaifeng Zhi, Shuzhou Sun +2
While deep learning excels in computer vision tasks with abundant labeled data, its performance diminishes significantly in scenarios with limited labeled samples. To address this,…
cs.LG2025
Few-shot Class-incremental Learning for Classification and Object Detection: A Survey
Jinghua Zhang, Li Liu, Olli Silvén +2
Few-shot Class-Incremental Learning (FSCIL) presents a unique challenge in Machine Learning (ML), as it necessitates the Incremental Learning (IL) of new classes from sparsely labe…