Parametrizing filters of a CNN with a GAN
It is commonly agreed that the use of relevant invariances as a good statistical bias is important in machine-learning. However, most approaches that explicitly incorporate invariances into a model architecture only make use of very simple transformations, such as translations and rotations. Hence, there is a need for methods to model and extract richer transformations that capture much higher-level invariances. To that end, we introduce a tool allowing to parametrize the set of filters of a trained convolutional neural network with the latent space of a generative adversarial network. We then show that the method can capture highly non-linear invariances of the data by visualizing their effect in the data space.
Code (0)
등록된 구현이 없습니다.
Tasks
Generative Adversarial NetworkSimilar Papers 제목 키워드 기반
SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filters
Deep neural networks have enjoyed remarkable success for various vision tasks, however it remains challenging to apply CNNs to domains lacking a regular underlying structures such as 3D point clouds. Towards this we prop…
3D Part Segmentation3D Point Cloud ClassificationDeep LearningT-Net: Parametrizing Fully Convolutional Nets with a Single High-Order Tensor
Recent findings indicate that over-parametrization, while crucial for successfully training deep neural networks, also introduces large amounts of redundancy. Tensor methods have the potential to efficiently parametrize …
Pose EstimationGenerative Conditional Distributions by Neural (Entropic) Optimal Transport
Learning conditional distributions is challenging because the desired outcome is not a single distribution but multiple distributions that correspond to multiple instances of the covariates. We introduce a novel neural e…
Least Squares Auto-Tuning
Least squares is by far the simplest and most commonly applied computational method in many fields. In almost all applications, the least squares objective is rarely the true objective. We account for this discrepancy by…
Learning about passivity from data
This paper presents a data-driven methodology to estimate the storage function of a passive system. The methodology consists in parametrizing the storage function with a dictionary then running a linear program. Results …