Criteria for Selecting Embeddings to Drive Active Learning
Establish principled criteria for selecting an embedding representation to drive active learning in biodiversity monitoring, given that downstream performance is sensitive to the choice of embedding.
References
Downstream performance is sensitive to the choice of embedding \citep{dumoulin2025search}, yet principled criteria for selecting an embedding to drive AL remain to be established; we identify this as an open question.
— Active Learning for Biodiversity Monitoring: From Label Efficiency to Reliable Ecological Inference
(2609.27409 - McEwen et al., 23 Sep 2026) in Section 3.2, subsection “Models”
When FINE is applied to this setting, the choice of representation remains an open question.
— Learning What to Trust in Multimodal Learning under Noisy Supervision
(2610.11057 - Zou et al., 8 Oct 2026) in Section 3.1, subsection “FINE for Learning with Noisy Labels: A Recap”