Embedding Expansion: Augmentation In Embedding Space For Deep Metric Learning

Abstract

Learning the distance metric between pairs of samples has been studied for image retrieval and clustering. With the remarkable success of pair-based metric learning losses, recent works have proposed the use of generated synthetic points on metric learning losses for augmentation and generalization. However, these methods require additional generative networks along with the main network, which can lead to a larger model size, slower training speed, and harder optimization. Meanwhile, post-processing techniques, such as query expansion and database augmentation, have proposed the combination of feature points to obtain additional semantic information. In this paper, inspired by query expansion and database augmentation, we propose an augmentation method in an embedding space for pair-based metric learning losses, called embedding expansion. The proposed method generates synthetic points containing augmented information by a combination of feature points and performs hard negative pair

Stats

• citations39
• S2 citations—
• github stars0
• HF likes0
• heat score12.02
• arxiv keyko2020embedding

Related papers

• Symmetrical Synthesis For Deep Metric Learning (2020)8.60
• Learning To Generate Novel Classes For Deep Metric Learning (2022)0.00
• Loop: Looking For Optimal Hard Negative Embeddings For Deep Metric Learning (2021)8.82
• The General Pair-based Weighting Loss For Deep Metric Learning (2019)0.00
• ALMN: Deep Embedding Learning With Geometrical Virtual Point Generating (2018)0.00
• Divide And Conquer The Embedding Space For Metric Learning (2019)14.39
• Visualizing How Embeddings Generalize (2019)0.00
• Generalization In Metric Learning: Should The Embedding Layer Be The Embedding Layer? (2018)8.60