Incorporating Invariances in Support Vector Learning Machines

By Bernhard Schölkopf, C. Burges, Vladimir Naumovich Vapnik. 1996

How researchers see this paper

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

Citations in the corpus

Conditional variance penalties and domain shift robustness (2017, methodology): “by rotating, translating, or flipping the images (Schölkopf et al., 1996).”
A Kernel Theory of Modern Data Augmentation (2018, methodology): “For many years it has been used, for example, in the form of jittering and virtual examples in the neural network and kernel methods literatures (Sietsma & Dow, 1991; Schölkopf et al., 1996; Decoste & Schölkopf, 2002).”
Chunking with Support Vector Machines (2001, unknown): “我々は, Virtual SVM[ 16 ]のアイデアを取りいれ,抽出される support ectorに対し変形規則を適用し,可変長の文脈を間接的に考慮するモデルを構築したいと考えている.”
Constructing support vector machine ensemble (2003, background): “There are some literatures on the handwritten digit recognition using SVM [1,20–22].”
Spatial regularization of SVM for the detection of diffusion alterations associated with stroke outcome (2011, methodology): “, 1998) to some chosen transformations, (ii) by generating artificially transformed examples from the training set to create virtual support vectors (Schölkopf et al., 1996), (iii) by using a combination of both these approaches called kernel jittering (Decoste and Schölkopf, 2002).”
Kernel Methods and Machine Learning (2014, background): “4 Shift-invariant kernel functions It is sometimes of practical use to examine the shift-invariance property of the kernel functions chosen [237].”
Maximum Margin Correlation Filter: A New Approach for Localization and Classification (2013, unknown): “It is important to note that we did not include shifted images of true-class vehicles as false-class images as done in some recognition approaches [14], [15], [32].”
Continual Adaptation of Visual Representations via Domain Randomization and Meta-learning (2020, background): “The use of data augmentation has a long history in computer vision [54, 56, 9, 8, 30, 50].”
Comparison of machine learning and traditional classifiers in glaucoma diagnosis (2002, background): “SVMs have demonstrated good generalization performance in face recognition [26], text categorization [27], and optical character recognition [28], [29].”
Improving Augmentation and Evaluation Schemes for Semantic Image Synthesis (2020, methodology): “Data augmentation is a widely used technique for generating additional data to train machine learning systems [50, 48, 27, 57, 11, 58].”