Hard Negative Examples Are Hard, But Useful
2020 · Hong Xuan, Abby Stylianou, Xiaotong Liu, et al.
Abstract
Triplet loss is an extremely common approach to distance metric learning. Representations of images from the same class are optimized to be mapped closer together in an embedding space than representations of images from different classes. Much work on triplet losses focuses on selecting the most useful triplets of images to consider, with strategies that select dissimilar examples from the same class or similar examples from different classes. The consensus of previous research is that optimizing with the \textit\{hardest\} negative examples leads to bad training behavior. That's a problem -- these hardest negatives are literally the cases where the distance metric fails to capture semantic similarity. In this paper, we characterize the space of triplets and derive why hard negatives make triplet loss training fail. We offer a simple fix to the loss function and show that, with this fix, optimizing with hard negative examples becomes feasible. This leads to more generalizable features
Authors
(none)
Tags
Stats
Related papers
- Loop: Looking For Optimal Hard Negative Embeddings For Deep Metric Learning (2021)8.82
- Your Negative May Not Be True Negative: Boosting Image-text Matching With False Negative Elimination (2023)14.32
- Do Lessons From Metric Learning Generalize To Image-caption Retrieval? (2022)5.24
- Comparing Contrastive And Triplet Loss: Variance Analysis And Optimization Behavior (2025)0.00
- Improved Embeddings With Easy Positive Triplet Mining (2019)15.06
- Improving Collaborative Metric Learning With Efficient Negative Sampling (2019)10.07
- Constellation Loss: Improving The Efficiency Of Deep Metric Learning Loss Functions For Optimal Embedding (2019)0.00
- A Quadruplet Loss For Enforcing Semantically Coherent Embeddings In Multi-output Classification Problems (2020)6.77