Search Results for author:
Found 5 papers, 3 papers with code
Knowledge Distillation Layer that Lets the Student Decide
Albeit useful especially in the penultimate layer and beyond, its action on student's feature transform is rather implicit, limiting its practice in the intermediate layers.
Generalized Sum Pooling for Metric Learning
GSP improves GAP with two distinct abilities: i) the ability to choose a subset of semantic entities, effectively learning to ignore nuisance information, and ii) learning the weights corresponding to the importance of each entity.
Generalizable Embeddings with Cross-batch Metric Learning
Global average pooling (GAP) is a popular component in deep metric learning (DML) for aggregating features.
Feature Embedding by Template Matching as a ResNet Block
Convolution blocks serve as local feature extractors and are the key to success of the neural networks.
Deep Metric Learning with Chance Constraints
Deep metric learning (DML) aims to minimize empirical expected loss of the pairwise intra-/inter- class proximity violations in the embedding space.
