Zeynep Akata, Sarkhan Badirli, George Mohler, Christine Picard, Murat Dundar
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.
Fine-grained zero-shot learning task requires some form of side-information to transfer discriminative information from seen to unseen classes. As manually annotated visual attributes are extremely costly and often impractical to obtain for a large number of classes, in this study we use DNA as side information for the first time for fine-grained zero-shot classification of species. Mitochondrial DNA plays an important role as a genetic marker in evolutionary biology and has been used to achieve near perfect accuracy in species classification of living organisms. We implement a simple hierarchical Bayesian model that uses DNA information to establish the hierarchy in the image space and employs local priors to define surrogate classes for unseen ones. On the benchmark CUB dataset we show that DNA can be equally promising, yet in general a more accessible alternative than word vectors as a side information. This is especially important as obtaining robust word representations for fine-grained species names is not a practicable goal when information about these species in free-form text is limited. On a newly compiled fine-grained insect dataset that uses DNA information from over a thousand species we show that the Bayesian approach outperforms state-of-the-art by a wide margin.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2109.14133")
get_code_for_paper("2109.14133")
have("2109.14133")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2109.14133.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2109.14133)
Connect an agent — have() is free.