paper-with-me

홈 › Papers

Unsupervised Transformation Learning via Convex Relaxations

2017-11-06 · NeurIPS 2017 12 · Tatsunori B. Hashimoto, John C. Duchi, Percy Liang

Our goal is to extract meaningful transformations from raw images, such as varying the thickness of lines in handwriting or the lighting in a portrait. We propose an unsupervised approach to learn such transformations by attempting to reconstruct an image from a linear combination of transformations of its nearest neighbors. On handwritten digits and celebrity portraits, we show that even with linear transformations, our method generates visually high-quality modified images. Moreover, since our method is semiparametric and does not model the data distribution, the learned transformations extrapolate off the training data and can be applied to new types of images.

📄 PDF Abstract BibTeX arXiv:1711.02226

Code (1)

https://worksheets.codalab.org/worksheets/0x4412d72b55df47e5b457dacdba91f105 공식 구현

Similar Papers 제목 키워드 기반

A Non-generative Framework and Convex Relaxations for Unsupervised Learning

2016-10-04 · NeurIPS 2016 12 · Elad Hazan, Tengyu Ma

We give a novel formal theoretical framework for unsupervised learning with two distinctive characteristics. First, it does not assume any generative model and based on a worst-case performance metric. Second, it is comp…

On the Expressiveness of Multi-Neuron Convex Relaxations

2024-10-09 · Yuhao Mao, Yani Zhang, Martin Vechev

To provide robustness guarantees, neural network certification methods heavily rely on convex relaxations. The imprecision of these convex relaxations, however, is a major obstacle: even the most precise single-neuron re…

Tightening convex relaxations of trained neural networks: a unified approach for convex and S-shaped activations

2024-10-30 · Pablo Carrasco, Gonzalo Muñoz

The non-convex nature of trained neural networks has created significant obstacles in their incorporation into optimization models. Considering the wide array of applications that this embedding has, the optimization and…

Efficient Certification of Spatial Robustness

2020-09-19 · Anian Ruoss, Maximilian Baader, Mislav Balunović, Martin Vechev

Recent work has exposed the vulnerability of computer vision models to vector field attacks. Due to the widespread usage of such models in safety-critical applications, it is crucial to quantify their robustness against …

Expressivity of ReLU-Networks under Convex Relaxations

2023-11-07 · Maximilian Baader, Mark Niklas Müller, Yuhao Mao, Martin Vechev

Convex relaxations are a key component of training and certifying provably safe neural networks. However, despite substantial progress, a wide and poorly understood accuracy gap to standard networks remains, raising the …