Hard negative mining
Hard negative mining, also referred to as hard negative sampling, is a family of techniques in machine learning for selecting or constructing negative samples more difficult to distinguish from a corresponding positive example with respect to uniformly-sampled negatives, leading to a more informative training signal for discriminative classifiers and similarity models.
Overview schema of hard negative mining from data. In the example above, the model is trained to classify gray cats from anything else. The "Hard Negative Selector" prioritizes other images of cats with a different fur color, since they are the most difficult negatives to distinguish from the positive samples. Hard negative mining, also referred to as hard negative sampling, is a family of techniques in machine learning for selecting or constructing negative samples more difficult to distinguish from a corresponding positive example with respect to uniformly-sampled negatives, leading to a…
saved by
related reading
- Learning with not Enough Data Part 1: Semi-Supervised Learning | Lil'Loglilianweng.github.io
- CS231n Deep Learning for Computer Visioncs231n.github.io
- Support vector machine - Wikipediaen.wikipedia.org
- Contrastive Representation Learning | Lil'Loglilianweng.github.io
- ImageNet Classification with Deep Convolutional Neural Networksproceedings.neurips.cc
- What is Contrastive Learning? (Contrastive Learning/Self-supervised Learning Explained)youtube.com
- d89a66c7c80a29b1bdbab0f2a1a94af8-Paper.pdfproceedings.neurips.cc
- Self-supervised learning: The dark matter of intelligenceai.facebook.com
- [2205.13147] Matryoshka Representation Learningarxiv.org
- Meta-Learning: Learning to Learn Fastlilianweng.github.io
- Neighbor2Neighborarxiv.org
- An Overview of Deep Semi-Supervised Learningarxiv.org