cifar-100
A Experimental setup
In this section, we detail the model architectures examined in the experiments and list all hyperpa-rameters used in the experiments. Both architectures consist of five stages, each consisting of a combination of convolutional layers with ReLU activation and max pooling layers. The base number of channels in consecutive stages for VGG architectures equals 64, 128, 256, 512, and 512. The subsequent stages are composed of residual blocks. In the case of ResNets, we report the results for the'conv2' layers.
Country:
- North America > Canada > Alberta (0.14)
- Europe > Poland > Masovia Province > Warsaw (0.04)
- North America > United States > Maryland > Baltimore (0.04)
- (2 more...)
Technology:
Efficient Adversarial Contrastive Learning via Robustness-Aware Coreset Selection
To speed up ACL, this paper proposes a robustness-aware coreset selection (RCS) method.
Country:
- Asia > Singapore (0.04)
- Oceania > New Zealand > North Island > Auckland Region > Auckland (0.04)
- Asia > Japan > Honshū > Kantō > Tokyo Metropolis Prefecture > Tokyo (0.04)
- (4 more...)
Technology:
Technology: Information Technology > Artificial Intelligence > Machine Learning > Statistical Learning > Regression (0.50)
Country:
- North America > United States (0.04)
- Asia > China > Jiangsu Province > Nanjing (0.04)
Technology:
Technology: Information Technology > Artificial Intelligence > Machine Learning > Neural Networks (0.48)
