Search papers, labs, and topics across Lattice.
This paper introduces BADGE-Greedy-DPP, a novel deterministic batch selection method for active learning in bioacoustic call-type classification that addresses the challenges of sparse target calls and long-tailed distributions. By maximizing the volume of gradient embeddings, the method guarantees a batch value that is at least a (1-1/e) fraction of the optimal, outperforming existing strategies like k-means++ and MCMC DPP sampling. Experimental results on a hyena call-type dataset demonstrate that BADGE-Greedy-DPP significantly enhances performance for both overall and rare call types compared to other query strategies.
Greedy selection of segments based on gradient embeddings can dramatically improve rare call-type classification in bioacoustics, achieving superior performance over traditional methods.
Bioacoustic call-type classification relies on costly expert annotation. Active learning can reduce this burden by selecting a small batch of segments for expert annotation and using the labeled segments for training the classifier. The setting is hard: the target calls are extremely sparse and the call-type distribution is long-tailed, so a tight budget must be spent on the few rare, informative segments. We propose BADGE-Greedy-DPP, a deterministic batch selector that greedily adds the segment whose BADGE gradient embedding most enlarges the volume spanned by the batch; because this log-volume objective is submodular, the greedy rule guarantees a batch value at least a (1-1/e) fraction of the optimum of this objective, a guarantee not provided by BADGE's existing k-means++ and MCMC DPP sampling heuristics. There is also a temporal granularity mismatch in the task. The acquisition function scores whole segments, yet the informative frames inside them are few. Uniform averaging therefore washes them out. We show that the BADGE construction naturally addresses this mismatch when applied frame-wise, as prediction residuals weight the aggregated pseudo-gradient, so confidently predicted no-call frames contribute little while a single uncertain rare-call frame can still set the segment's direction. Across 10 runs on a sparse, imbalanced hyena call-type dataset, BADGE-Greedy-DPP achieves the best overall and rare-call-type performance among all compared query strategies, including MFFT, the strongest non-BADGE baseline, and the two vanilla BADGE traversals.
