Sampling Matters in Deep Embedding Learning

Chao-Yuan Wu, R. Manmatha, Alexander J. Smola, Philipp Krahenbuhl; Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2017, pp. 2840-2848

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 CUB200-2011, CAR196, and the Stanford Online Products 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.