Daniele De Martini, Benjamin Ramtoula, Paul Newman, Layer, Matthew Gadd, Neuron, Neuron Layer, L Neuron, Neuron !#, Dataset Neuron
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. We have no repository linked to it either. That is a statement about our graph, not about the paper.
Selecting appropriate datasets is critical in modern computer vision. However, no general-purpose tools exist to evaluate the extent to which two datasets differ. For this, we propose representing images -and by extension datasetsusing Distributions of Neuron Activations (DNAs). DNAs fit distributions, such as histograms or Gaussians, to activations of neurons in a pre-trained feature extractor through which we pass the image(s) to represent. This extractor is frozen for all datasets, and we rely on its generally expressive power in feature space. By comparing two DNAs, we can evaluate the extent to which two datasets differ with granular control over the comparison attributes of interest, providing the ability to customise the way distances are measured to suit the requirements of the task at hand. Furthermore, DNAs are compact, representing datasets of any size with less than 15 megabytes. We demonstrate the value of DNAs by evaluating their applicability on several tasks, including conditional dataset comparison, synthetic image evaluation, and transfer learning, and across diverse datasets, ranging from synthetic cat images to celebrity faces and urban driving scenes.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2304.10036")
get_code_for_paper("2304.10036")
have("2304.10036")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2304.10036.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2304.10036)
Connect an agent — have() is free.