Figure 2 - available via license: Creative Commons Attribution 4.0 International
Content may be subject to copyright.
Few-shot classification accuracy of FuMI on iNat-Anim compared to MAML. Error bars show the uncertainty across 5 random seeds.
Source publication
When experience is scarce, models may have insufficient information to adapt to a new task. In this case, auxiliary information - such as a textual description of the task - can enable improved task inference and adaptation. In this work, we propose an extension to the Model-Agnostic Meta-Learning algorithm (MAML), which allows the model to adapt u...
Context in source publication
Context 1
... fusion improves performance in the very-few-shot regime. Figure 2 shows the relative performance gain of FuMI compared to MAML. We find that using the task-specific initialization provides significant improvements given very limited task data, whilst performance is similar with additional examples. ...
Similar publications
We present a novel framework, i.e., Segment Any Anomaly + (SAA+), for zero-shot anomaly segmentation with hybrid prompt regularization to improve the adaptability of modern foundation models. Existing anomaly segmentation models typically rely on domain-specific fine-tuning, limiting their generalization across countless anomaly patterns. In this w...
