classification accuracy
Model and Feature Diversity for Bayesian Neural Networks in Mutual Learning
Utilizing mutual learning can effectively enhance the performance of peer BNNs.
- North America > Canada > Ontario > Toronto (0.14)
- Oceania > Australia > South Australia > Adelaide (0.04)
- Europe > United Kingdom > England > Surrey (0.04)
- Asia > Vietnam (0.04)
- Information Technology > Artificial Intelligence > Machine Learning > Neural Networks (1.00)
- Information Technology > Artificial Intelligence > Representation & Reasoning > Uncertainty > Bayesian Inference (0.46)
- Information Technology > Artificial Intelligence > Machine Learning > Learning Graphical Models > Directed Networks > Bayesian Learning (0.46)
Supplementary Material: Scale-teaching: Robust Multi-scale Training for Time Series Classification with Noisy Labels
The statistical information of the four individual time series datasets is shown in Table 1.
- Asia > China > Guangdong Province > Guangzhou (0.04)
- Asia > China > Liaoning Province > Dalian (0.04)
- Asia > China > Guangdong Province > Guangzhou (0.04)
- Asia > China > Liaoning Province > Dalian (0.04)
Practical and Asymptotically Exact Conditional Sampling in Diffusion Models
Conditional sampling is an essential primitive in the machine learning toolkit.
Practical and Asymptotically Exact Conditional Sampling in Diffusion Models
Conditional sampling is an essential primitive in the machine learning toolkit.
Learnable Polyphase Sampling for Shift Invariant and Equivariant Convolutional Networks Renan A. Rojas-Gomez T eck-Yian Lim Alexander G. Schwing Minh N. Do Raymond A. Y eh
LPS can be trained end-to-end from data and generalizes existing handcrafted downsampling layers. It is widely applicable as it can be integrated into any convolutional network by replacing down/upsampling layers. We evaluate LPS on image classification and semantic segmentation. Experiments show that LPS is on-par with or outperforms existing methods in both performance and shift consistency. For the first time, we achieve true shift-equivariance on semantic segmentation (P ASCAL VOC), i.e., 100% shift consistency, outperforming baselines by an absolute 3.3%.
- Asia > Japan > Honshū > Tōhoku > Fukushima Prefecture > Fukushima (0.04)
- North America > United States > Illinois > Cook County > Chicago (0.04)
- Europe > United Kingdom > England > Cambridgeshire > Cambridge (0.04)