Generalized sum pooling for metric learning
A common architectural choice for deep metric learning is a convolutional neural network
followed by global average pooling (GAP). Albeit simple, GAP is a highly effective way to …
followed by global average pooling (GAP). Albeit simple, GAP is a highly effective way to …
Generalizable embeddings with cross-batch metric learning
Global average pooling (GAP) is a popular component in deep metric learning (DML) for
aggregating features. Its effectiveness is often attributed to treating each feature vector as a …
aggregating features. Its effectiveness is often attributed to treating each feature vector as a …