Multiple instance learning with generalized support vector machines

By Stuart Andrews, Thomas Hofmann, Ioannis Tsochantaridis. 2002

117 citations recorded by the source corpus.

Subfields: Representation & Self-Supervised Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Representation & Self-Supervised Learning

1. Li Fei-Fei
2. Serge J. Belongie
3. Iasonas Kokkinos
4. Xiaohui S. Xie
5. Piotr Doll'ar
6. Armand Joulin
7. Wentao Zhu
8. Andrej Karpathy

Citations in the corpus

• Deep Fragment Embeddings for Bidirectional Image Sentence Mapping (2014, methodology): “This objective cannot be solved efficiently [40] but a commonly used heuristic is to set yij = sign(v T i sj).”
• Modeling local and global deformations in Deep Learning: Epitomic convolution, Multiple Instance Learning, and sliding window detection (2015, background): “For the particular case of the hinge loss function, this would lead us to latent-SVM training [2, 10].”
• Multiple Instance Learning: Algorithms and Applications (2008, methodology): “Finally, document/text classification has been investigated within a MIL framework [27].”
• Multiple Instance Learning with Manifold Bags (2011, methodology): “This situation arises in many other MIL applications where some type of sliding window is used to break up an object into many overlapping pieces: images (Andrews et al., 2002; Viola et al., 2005), video (Ali & Shah, 2008; Buehler et al.”
• Deep Multi-instance Networks with Sparse Label Assignment for Whole Mammogram Classification (2016, background): “generalized support vector machine for the multi-instance problem [1].”