Sampling Matters in Deep Embedding Learning

Citations Over TimeTop 1% of 2017 papers

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.

Related Papers

• → Embedding as a modeling problem(1998)167 cited
• → Implementing convolutional neural network model for prediction in medical imaging(2022)6 cited
• Intensive Margin and Extensive Margin Adjustments of Labor Market : Turkey versus United States(2013)
• On the Necessity and Feasibility of Constructing Big Water Margin Cultural System——Taking Big Folk Water Margin by Fan Chaoyang and Zhang Qingjian as an Example(2009)