| Abstract | This dataset comprises combined gradient maps from sixteen pretrained residual-based networks for use with Multi-Targeted Gradient Training (MTGT). The combined gradients were optimized for a cyan (488 nm) Wavelength-Specific Map Attack. Each example corresponds to an original ImageNet-1K training or validation image, and the resulting combined gradient is stored as a single-channel (1 X 224 X 224) map. The combined gradient was computed by averaging the cross-entropy gradient of each network with respect to the true class, multiplying channel-wise by the RGB translation of a 488 nm cyan laser, and summing across channels. The ensemble includes RegNetX-400MF, RegNetX-800MF, RegNetX-1.6GF, RegNetY-400MF, RegNetY-800MF, RegNetY-1.6GF, RegNetY-3.2GF, ResNet-18, ResNet-34, ResNet-50, ResNet-101, ResNet-152, ResNeXt-50 (32 X 4d), ResNeXt-101 (32 X 8d), Wide ResNet-50-2, and Wide ResNet-101-2, all sourced from the PyTorch Model Library and trained using a common preprocessing scheme in which the shortest side of the input was resized to 256 pixels while preserving aspect ratio, followed by a 224 X 224 center crop. The networks were chosen to better approximate the gradient behavior of residual architectures during MTGT. |
