Distance Metric Learning for Large Margin Nearest Neighbor Classification

Citations in the corpus

Prototypical Networks for Few-shot Learning (2017, neutral): “Large margin nearest neighbor (LMNN) classiﬁcation [30] also attempts to optimize KNN accuracy but does so using a hinge loss that encourages the local neighborhood of a point to contain other points with the same label.”
This looks like that: deep learning for interpretable image recognition (2018, neutral): “Our work relates closely to other case-based classiﬁcation techniques using k-nearest neighbors [47, 35, 32] or prototypes [33, 2, 48], and very closely, to the Bayesian Case Model [18].”
Supervised Contrastive Learning (2020, neutral): “We also show that triplet loss [48] is a special case of our loss when only a single positive and negative are used.”
Recurrent Pixel Embedding for Instance Grouping (2017, neutral): “This problem is broadly re-lated to supervised distance metric learning [86, 48, 50] and clustering [49] but adapted to the speciﬁcs of instance labeling where the embedding vectors are treated as labels for a variable number of objects in each image.”
Metric Learning with Adaptive Density Discrimination (2015, neutral): “This issue is well-known, and has motivated the notion of local similarity: each example is designated only a small number of target neighbours of the same class (Weinberger & Saul, 2009; Qian et al., 2015; Hadsell et al., 2006).”