paper-with-me

Papers

Universum Prescription: Regularization using Unlabeled Data

2015-11-11 · Xiang Zhang, Yann Lecun

This paper shows that simply prescribing "none of the above" labels to unlabeled data has a beneficial regularization effect to supervised learning. We call it universum prescription by the fact that the prescribed labels cannot be one of the supervised labels. In spite of its simplicity, universum prescription obtained competitive results in training deep convolutional networks for CIFAR-10, CIFAR-100, STL-10 and ImageNet datasets. A qualitative justification of these approaches using Rademacher complexity is presented. The effect of a regularization parameter -- probability of sampling from unlabeled data -- is also studied empirically.

📄 PDF Abstract BibTeX arXiv:1511.03719

Code (0)

등록된 구현이 없습니다.

Tasks

Image Classification

Similar Papers 제목 키워드 기반

Graph-Guided Universum Learning in Generalized Eigenvalue Proximal SVMs for Alzheimer's Disease Classification

2026-06-03 · Yogesh Kumar, Vrushank Ahire, Mudasir Ganaie arxiv

Early and accurate detection of Alzheimer's disease (AD) is important for timely intervention and disease management. Generalized Eigenvalue Proximal Support Vector Machine (GEPSVM) and its Universum-based variants have …

Universum GANs: Improving GANs through contradictions

2021-06-18 · Sauptik Dhar, Javad Heydari, Samarth Tripathi, Unmesh Kurup 외

Limited availability of labeled-data makes any supervised learning problem challenging. Alternative learning settings like semi-supervised and universum learning alleviate the dependency on labeled data, but still requir…

Synthetic Data Generation

Universum Learning for SVM Regression

2016-05-27 · Sauptik Dhar, Vladimir Cherkassky

This paper extends the idea of Universum learning [18, 19] to regression problems. We propose new Universum-SVM formulation for regression problems that incorporates a priori knowledge in the form of additional data samp…

regression

Universum-inspired Supervised Contrastive Learning

2022-04-22 · Aiyang Han, Chuanxing Geng, Songcan Chen

As an effective data augmentation method, Mixup synthesizes an extra amount of samples through linear interpolations. Despite its theoretical dependency on data properties, Mixup reportedly performs well as a regularizer…

Contrastive LearningData Augmentation

Universum Learning for Multiclass SVM

2016-09-29 · Sauptik Dhar, Naveen Ramakrishnan, Vladimir Cherkassky, Mohak Shah

We introduce Universum learning for multiclass problems and propose a novel formulation for multiclass universum SVM (MU-SVM). We also propose a span bound for MU-SVM that can be used for model selection thereby avoiding…

Model Selection