Search Results for author:
Found 3 papers, 2 papers with code
Learning from Emergence: A Study on Proactively Inhibiting the Monosemantic Neurons of Artificial Neural Networks
We validate our conjecture that monosemanticity brings about performance change at different model scales on a variety of neural networks and benchmark datasets in different areas, including language, image, and physics simulation tasks.
SSIN: Self-Supervised Learning for Rainfall Spatial Interpolation
Inspired by the Cloze task and BERT, we fully consider the characteristics of spatial interpolation and design the SpaFormer model based on the Transformer architecture as the core of SSIN.
Noise2Info: Noisy Image to Information of Noise for Self-Supervised Image Denoising
However, such a method is highly sensitive to the standard deviation \sigma_n of noises injected to clean images, where \sigma_n is inaccessible without knowing clean images.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
