mlsanityData to 14 Oct 2026

Catching Image Retrieval Generalization

arXiv 2306.13357 ↗First posted 23 Jun 2023cs.LG cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

The concepts of overfitting and generalization are vital for evaluating machine learning models. In this work, we show that the popular Recall@K metric depends on the number of classes in the dataset, which limits its ability to estimate generalization. To fix this issue, we propose a new metric, which measures retrieval performance, and, unlike Recall@K, estimates generalization. We apply the proposed metric to popular image retrieval methods and provide new insights about deep metric learning generalization.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 14 of its 24 references that are in the map. First posted on arXiv 23 Jun 2023.

Builds on

14 of 24 references.

References · 14

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  3. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,884
  4. 2017SphereFace: Deep Hypersphere Embedding for Face Recognitioncited by 737
  5. 2017Spectrally-normalized margin bounds for neural networkscited by 686
  6. 2020A Metric Learning Reality Checkcited by 321
  7. 2017Generalization in Deep Learningcited by 146
  8. 2020Revisiting Training Strategies and Generalization Performance in Deep Metric Learningcited by 100
  9. 2018The Singular Values of Convolutional Layerscited by 95
  10. 2017Implicit Regularization in Deep Learningcited by 90
  11. 2018Generalization Error in Deep Learningcited by 47
  12. 2022On the Generalization Mystery in Deep Learningcited by 25
2 more
  1. 2020Sharing Matters for Generalization in Deep Metric Learningcited by 15
  2. 2022Generalizing in the Real World with Representation Learningcited by 1

Built on by

Not cited yet.