Search Results for author:
Found 12 papers, 7 papers with code
Accelerating Inference of Networks in the Frequency Domain
In particular, we propose a frequency inference chain that is dual to the network inference in the spatial domain.
Deep Clustering via Distribution Learning
Thus, in this work, we provide a theoretical analysis to guide the optimization of clustering via distribution learning.
RAST: Restorable Arbitrary Style Transfer
Embedding an artistic style can result in unintended changes to the image content.
RAST: Restorable arbitrary style transfer via multi-restoration
We control the content-style balance in stylized images by the accuracy of image restoration.
Frequency Regularization: Reducing Information Redundancy in Convolutional Neural Networks
Since high-frequency components of images are known to be less critical, a large proportion of these parameters can be set to zero when networks are trained with the proposed frequency regularization.
Affine-Transformation-Invariant Image Classification by Differentiable Arithmetic Distribution Module
On this foundation, we present a novel Differentiable Arithmetic Distribution Module (DADM), which is designed to extract the intrinsic probability distributions from images.
Bridging Distribution Learning and Image Clustering in High-dimensional Space
Based on the experimental results, we believe distribution learning can exploit the potential of GMM in image clustering within high-dimensional space.
Is Deep Learning Network Necessary for Image Generation?
In this paper, we investigate the possibility of image generation without using a deep learning network, motivated by validating the assumption that images follow a high-dimensional distribution.
Learning Distributions via Monte-Carlo Marginalization
One strong evidence of the benefit of our method is that the distributions learned by the proposed approach can generate better images even based on a pre-trained VAE's decoder.
Learning Temporal Distribution and Spatial Correlation Towards Universal Moving Object Segmentation
In this paper, we propose a method called Learning Temporal Distribution and Spatial Correlation (LTS) that has the potential to be a general solution for universal moving object segmentation.
Frequency Regularization: Restricting Information Redundancy of Convolutional Neural Networks
Since high frequency components of images are known to be less critical, a large proportion of these parameters can be set to zero when networks are trained with the proposed frequency regularization.
Universal Background Subtraction based on Arithmetic Distribution Neural Network
Thus, the proposed approach is able to utilize the probability information of the histogram and achieve promising results with a very simple architecture compared to traditional convolutional neural networks.
