May 20, 2020 · We present an active learning strategy for training parametric models of distance metrics, given triplet-based similarity assessments.

Abstract. We present an active learning strategy for train- ing parametric models of distance metrics, given triplet-based similarity assessments: object xi ...

Abstract. We present an active learning strategy for train- ing parametric models of distance metrics, given triplet-based similarity assessments: object xi ...

Sep 6, 2024 · We present an active learning strategy for training parametric models of distance metrics, given triplet-based similarity assessments: ...

In this work, we propose a novel method to decorrelate batches of triplets, that jointly balances informativeness and diversity while decoupling the choice of a ...

Jan 7, 2021 · Perceptual metric trained on relative similarity comparisons between objects - Is object “x” more similar to object “y” or object “z” ?

Feb 15, 2021 · We present a novel batch active metric learning method that leverages the Maximum Entropy Principle to learn the least biased estimate of triplet distribution.

Batch Decorrelation for Active Metric Learning ... We present an active learning strategy for training parametric models of distance metrics, given triplet-based ...

Abstract. Active metric learning is the problem of incrementally selecting high- utility batches of training data (typically, ordered triplets) to annotate, ...

Sep 13, 2021 · While a recent work [20] proposes batch-decorrelation strategies for metric learning, they rely on ad hoc heuristics to estimate the correlation ...