Dimensionality Reduction by Learning an Invariant Mapping
Citations
14,635 citations
7,951 citations
Cites background from "Dimensionality Reduction by Learnin..."
...Discriminative approaches based on contrastive learning in the latent space have recently shown great promise, achieving state-of-theart results (Hadsell et al., 2006; Dosovitskiy et al., 2014; Oord et al., 2018; Bachman et al., 2019)....
[...]
...Dating back to Hadsell et al. (2006), these approaches learn representations by contrasting positive pairs against negative pairs....
[...]
7,767 citations
Cites methods from "Dimensionality Reduction by Learnin..."
...The same criterion had already been used successfully to learn a low-dimensional embedding with an unsupervised manifold learning algorithm [59] but is here [202] applied at one or more intermediate layer of the neural network....
[...]
6,273 citations
Cites methods from "Dimensionality Reduction by Learnin..."
...To improve intra-class invariance, we employ the similarity loss similar to [26, 10]....
[...]
4,272 citations
Cites background from "Dimensionality Reduction by Learnin..."
...Learning is formulated as minimizing a contrastive loss [29]....
[...]
...Contrastive losses [29] measure the similarities of sample pairs in a representation space....
[...]
...The contrastive loss serves as an unsupervised objective function for training the encoder networks that represent the queries and keys [29]....
[...]
...A contrastive loss [29] is a function whose value is low when q is similar to its positive key k+ and dissimilar to all other keys (considered negative keys for q)....
[...]
...Contrastive loss functions can also be based on other forms [29, 59, 61, 36], such as margin-based losses and variants of NCE losses....
[...]
References
42,067 citations
17,446 citations
15,106 citations
"Dimensionality Reduction by Learnin..." refers background or methods in this paper
...Recently proposed algorithms include ISOMAP (2000) by Tenenbaumet al. [1], Local Linear Embedding - LLE (2000) by Roweis and Saul [ 15 ], Laplacian Eigenmaps (2003) due to Belkin and Niyogi [2] and Hessian LLE (2003) by Donoho and Grimes [8]....
[...]
...For example, Locally Linear Embedding (LLE) [ 15 ] linearly combines input vectors that are identified as neighbors....
[...]
13,789 citations
13,652 citations