Deep learning

Metric (unit)

Metric space

Mathematics

Evolutionary biology

Biology

Operating system

Image (mathematics)

Mathematical analysis

Function (biology)

Artificial intelligence

Economics

Set (abstract data type)

Programming language

Class (philosophy)

Operations management

Information retrieval

Space (punctuation)

Code (set theory)

Visualization

Computer science

Theoretical computer science

Embedding

Deep metric learning seeks to define an embedding where semantically similar images are embedded to nearby locations, and semantically dissimilar images are embedded to distant locations. Substantial work has focused on loss functions and strategies to learn these embeddings by pushing images from the same class as close together in the embedding space as possible. In this paper, we propose an alternative, loosened embedding strategy that requires the embedding function only map each training image to the most similar examples from the same class, an approach we call "Easy Positive" mining. We provide a collection of experiments and visualizations that highlight that this Easy Positive mining leads to embed-dings that are more flexible and generalize better to new unseen data. This simple mining strategy yields recall performance that exceeds state of the art approaches (including those with complicated loss functions and ensemble methods) on image retrieval datasets including CUB, Stanford Online Products, In-Shop Clothes and Hotels-50K. Code is available at: https://github.com/littleredxh/EasyPositiveHardNegative.

Improved Embeddings with Easy Positive Triplet Mining