Training an autoencoder with a triplet-style loss that uses a fixed pretrained latent space to define neighbors improves downstream task accuracy, though gains are small and inconsistent.
Ucsd pedestrian dataset
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Self-Supervised Representation Learning via Neighborhood-Relational Encoding
Training an autoencoder with a triplet-style loss that uses a fixed pretrained latent space to define neighbors improves downstream task accuracy, though gains are small and inconsistent.