Sampling Matters in Deep Embedding Learning
Chao-Yuan Wu, Raghaven Manmatha, Alexander Johannes Smola et al. · IEEE International Conference on Computer Vision (ICCV) · 2017
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.
Cited by 836 works. doi:10.1109/iccv.2017.309
Authors
References
- Deep Residual Learning for Image Recognition
- ImageNet: A large-scale hierarchical image database
- Support-Vector Networks
- Adam: A Method for Stochastic Optimization
- AutoResearch Lite: a reproducible paper-inspired experiment runner (Adam mechanism reproduction and convergence-speed comparison)
- Independent component analysis, A new concept?
- Labeled Faces in the Wild: A Database forStudying Face Recognition in Unconstrained Environments
- DeepFace: Closing the Gap to Human-Level Performance in Face Verification
- ImageNet: A large-scale hierarchical image database
- FaceNet: A unified embedding for face recognition and clustering