More Like this

1. Neural Neural Textures Make Sim2Real Consistent

   Burgert, Ryan; Shang, Jinghuan; Li, Xiang; Ryoo, Michael S. (December 2022, Conference on Robot Learning (CoRL))
2. Neural Spike Sorting Using Binarized Neural Networks

   https://doi.org/10.1109/TNSRE.2020.3043403  

   Valencia, Daniel; Alimohammad, Amir (January 2021, IEEE Transactions on Neural Systems and Rehabilitation Engineering)
3. NeuTex: Neural Texture Mapping for Volumetric Neural Rendering

   Xiang, Fanbo; Xu, Zexiang; Hasan, Milos; Hold-Geoffroy, Yannick; Sunkavalli, Kalyan; Su, Hao (January 2021, IEEE Conference on Computer Vision and Pattern Recognition)

   null (Ed.)
4. Neural radiosity

   https://doi.org/10.1145/3478513.3480569  

   Hadadan, Saeed; Chen, Shuhong; Zwicker, Matthias (December 2021, ACM Transactions on Graphics)

   We introduce Neural Radiosity, an algorithm to solve the rendering equation by minimizing the norm of its residual, similar as in classical radiosity techniques. Traditional basis functions used in radiosity, such as piecewise polynomials or meshless basis functions are typically limited to representing isotropic scattering from diffuse surfaces. Instead, we propose to leverage neural networks to represent the full four-dimensional radiance distribution, directly optimizing network parameters to minimize the norm of the residual. Our approach decouples solving the rendering equation from rendering (perspective) images similar as in traditional radiosity techniques, and allows us to efficiently synthesize arbitrary views of a scene. In addition, we propose a network architecture using geometric learnable features that improves convergence of our solver compared to previous techniques. Our approach leads to an algorithm that is simple to implement, and we demonstrate its effectiveness on a variety of scenes with diffuse and non-diffuse surfaces. 

   more » « less
5. Neural Bootstrapper

   Shin, M.; Cho, H.; Min, H-S.; Lim, S. (January 2021, Advances in neural information processing systems)

   Ranzato, M.; Beygelzimer, A.; Dauphin, Y.; Liang, P. S.; Wortman Vaughan, J. (Ed.)

   Bootstrapping has been a primary tool for ensemble and uncertainty quantification in machine learning and statistics. However, due to its nature of multiple training and resampling, bootstrapping deep neural networks is computationally burdensome; hence it has difficulties in practical application to the uncertainty estimation and related tasks. To overcome this computational bottleneck, we propose a novel approach called Neural Bootstrapper (NeuBoots), which learns to generate bootstrapped neural networks through single model training. NeuBoots injects the bootstrap weights into the high-level feature layers of the backbone network and outputs the bootstrapped predictions of the target, without additional parameters and the repetitive computations from scratch. We apply NeuBoots to various machine learning tasks related to uncertainty quantification, including prediction calibrations in image classification and semantic segmentation, active learning, and detection of out-of-distribution samples. Our empirical results show that NeuBoots outperforms other bagging based methods under a much lower computational cost without losing the validity of bootstrapping. 

   more » « less