ResNet-18
An 18-layer-deep residual neural network proposed by Microsoft Research. Residual connections alleviate the degradation problem of deep networks, and it is widely used as a benchmark model for image classification.
Timeline (last 90 days)
The study used ResNet-18 as the baseline model for diatom classification.
Users can test the preset MobileNetV3-Small, ResNet-18 and ViT-Tiny configurations directly in the browser Studio without installation; they can also use the local Python CLI to process their own .pt or .onnx checkpoints and then drag the generated .bitlens.json back into the Studio for visualization.
The paper tested GCD on CIFAR-10 and ImageNet, covering three architectures, ResNet-18, ResNet-50, and ViT-B/16, and evaluated four mainstream attack methods.
ResNet-18 has more than 11 million parameters, nearly 20 times the 595,000 parameters of this project.
All Facts (4)
The study used ResNet-18 as the baseline model for diatom classification.
50%UnverifiedUsers can test the preset MobileNetV3-Small, ResNet-18 and ViT-Tiny configurations directly in the browser Studio without installation; they can also use the local Python CLI to process their own .pt or .onnx checkpoints and then drag the generated .bitlens.json back into the Studio for visualization.
50%UnverifiedThe paper tested GCD on CIFAR-10 and ImageNet, covering three architectures, ResNet-18, ResNet-50, and ViT-B/16, and evaluated four mainstream attack methods.
50%UnverifiedResNet-18 has more than 11 million parameters, nearly 20 times the 595,000 parameters of this project.
50%