论文标题
贝叶斯三胞胎损失：图像检索中的不确定性量化
Bayesian Triplet Loss: Uncertainty Quantification in Image Retrieval
论文作者
论文摘要
图像检索中的不确定性量化对于下游决策至关重要，但它仍然是一个具有挑战性且在很大程度上没有探索的问题。当前估计不确定性的方法的校准较差，计算昂贵或基于启发式方法。我们提出了一种新方法，将图像嵌入为随机特征而不是确定性特征。我们的两个主要贡献是（1）与三胞胎约束相匹配的可能性，并评估锚定接近阳性的概率而不是负面； （2）在特征空间上的先前，可以证明常规L2归一化的合理性。为了确保计算效率，我们得出了后部的变异近似，称为贝叶斯三重态损失，该损失会产生最新的不确定性估计，并匹配当前最新方法的预测性能。
Uncertainty quantification in image retrieval is crucial for downstream decisions, yet it remains a challenging and largely unexplored problem. Current methods for estimating uncertainties are poorly calibrated, computationally expensive, or based on heuristics. We present a new method that views image embeddings as stochastic features rather than deterministic features. Our two main contributions are (1) a likelihood that matches the triplet constraint and that evaluates the probability of an anchor being closer to a positive than a negative; and (2) a prior over the feature space that justifies the conventional l2 normalization. To ensure computational efficiency, we derive a variational approximation of the posterior, called the Bayesian triplet loss, that produces state-of-the-art uncertainty estimates and matches the predictive performance of current state-of-the-art methods.
