Tal Hassner, Kevin Liang, Vladan Petrovic, Samrudhdhi Rangrej
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.
Few-shot learning (FSL) methods typically assume clean support sets with accurately labeled samples when training on novel classes. This assumption can often be unrealistic: support sets, no matter how small, can still include mislabeled samples. Robustness to label noise is therefore essential for FSL methods to be practical, but this problem surprisingly remains largely unexplored. To address mislabeled samples in FSL settings, we make several technical contributions. (1) We offer simple, yet effective, feature aggregation methods, improving the prototypes used by Pro-toNet, a popular FSL technique. (2) We describe a novel Transformer model for Noisy Few-Shot Learning (TraNFS). TraNFS leverages a transformer's attention mechanism to weigh mislabeled versus correct samples. (3) Finally, we extensively test these methods on noisy versions of MiniIm-ageNet and TieredImageNet. Our results show that TraNFS is on-par with leading FSL methods on clean support sets, yet outperforms them, by far, in the presence of label noise.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2204.05494")
get_code_for_paper("2204.05494")
have("2204.05494")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2204.05494.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2204.05494)
Connect an agent — have() is free.