pith. sign in

arxiv: 1904.08502 · v2 · pith:VW7RI5QEnew · submitted 2019-04-09 · 💻 cs.CV · cs.AI· cs.LG· stat.ML

Few-Shot Learning with Localization in Realistic Settings

classification 💻 cs.CV cs.AIcs.LGstat.ML
keywords few-shotlearningmethodsarchitecturesclassimprovementsmeta-inatparameter-free
0
0 comments X
read the original abstract

Traditional recognition methods typically require large, artificially-balanced training classes, while few-shot learning methods are tested on artificially small ones. In contrast to both extremes, real world recognition problems exhibit heavy-tailed class distributions, with cluttered scenes and a mix of coarse and fine-grained class distinctions. We show that prior methods designed for few-shot learning do not work out of the box in these challenging conditions, based on a new "meta-iNat" benchmark. We introduce three parameter-free improvements: (a) better training procedures based on adapting cross-validation to meta-learning, (b) novel architectures that localize objects using limited bounding box annotations before classification, and (c) simple parameter-free expansions of the feature space based on bilinear pooling. Together, these improvements double the accuracy of state-of-the-art models on meta-iNat while generalizing to prior benchmarks, complex neural architectures, and settings with substantial domain shift.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.