Sampling Matters In Deep Embedding Learning

Abstract

Deep embeddings answer one simple question: How similar are two images? Learning these embeddings is the bedrock of verification, zero-shot learning, and visual search. The most prominent approaches optimize a deep convolutional network with a suitable loss function, such as contrastive loss or triplet loss. While a rich line of work focuses solely on the loss functions, we show in this paper that selecting training examples plays an equally important role. We propose distance weighted sampling, which selects more informative and stable examples than traditional approaches. In addition, we show that a simple margin based loss is sufficient to outperform all other loss functions. We evaluate our approach on the Stanford Online Products, CAR196, and the CUB200-2011 datasets for image retrieval and clustering, and on the LFW dataset for face verification. Our method achieves state-of-the-art performance on all of them.

Stats

• citations528
• S2 citations—
• github stars0
• HF likes0
• heat score20.43
• arxiv keywu2017sampling

Related papers

• Dynamic Sampling For Deep Metric Learning (2020)5.84
• DAS: Densely-anchored Sampling For Deep Metric Learning (2022)9.76
• Local Similarity-aware Deep Feature Embedding (2016)0.00
• Learning Deep Optimal Embeddings With Sinkhorn Divergences (2022)0.00
• Learning Embeddings For Product Visual Search With Triplet Loss And Online Sampling (2018)0.00
• Sharing Matters For Generalization In Deep Metric Learning (2020)8.35
• Visualizing How Embeddings Generalize (2019)0.00
• Deep Metric Learning For Computer Vision: A Brief Overview (2023)6.77