Adrian Weller, Nikola Simidjievski, Andrei Margeloiu, Mateja Jamnik
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
We investigate the influence of adversarial training on the interpretability of convolutional neural networks (CNNs), specifically applied to diagnosing skin cancer. We show that gradient-based saliency maps of adversarially trained CNNs are significantly sharper and more visually coherent than those of standardly trained CNNs. Furthermore, we show that adversarially trained networks highlight regions with significant color variation within the lesion, a common characteristic of melanoma. We find that fine-tuning a robust network with a small learning rate further improves saliency maps' sharpness. Lastly, we provide preliminary work suggesting that robustifying the first layers to extract robust low-level features leads to visually coherent explanations.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2012.01166")
get_code_for_paper("2012.01166")
have("2012.01166")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2012.01166.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2012.01166)
Connect an agent — have() is free.