Bharath Hariharan, Utkarsh Mall, Kavita Bala
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.
Modern recognition systems require large amounts of supervision to achieve accuracy. Adapting to new domains requires significant data from experts, which is onerous and can become too expensive. Zero-shot learning requires an annotated set of attributes for a novel category. Annotating the full set of attributes for a novel category proves to be a tedious and expensive task in deployment. This is especially the case when the recognition domain is an expert domain. We introduce a new field-guide-inspired approach to zeroshot annotation where the learner model interactively asks for the most useful attributes that define a class. We evaluate our method on classification benchmarks with attribute annotations like CUB, SUN, and AWA2 and show that our model achieves the performance of a model with full annotations at the cost of significantly fewer number of annotations. Since the time of experts is precious, decreasing annotation cost can be very valuable for real-world deployment.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2108.10967")
get_code_for_paper("2108.10967")
have("2108.10967")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2108.10967.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2108.10967)
Connect an agent — have() is free.