Name
Abstract | ||
|---|---|---|
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 zero-shot 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 a significantly fewer number of annotations. Since the time of experts is precious, decreasing annotation cost can be very valuable for real-world deployment. |
Year | DOI | Venue |
|---|---|---|
2021 | 10.1109/ICCV48922.2021.00941 | ICCV |
DocType | Citations | PageRank |
Conference | 0 | 0.34 |
References | Authors | |
0 | 3 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Utkarsh Mall | 1 | 8 | 1.90 |
| Bharath Hariharan | 2 | 0 | 1.01 |
| Kavita Bala | 3 | 2046 | 138.75 |