Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Few-Shot Learning with Localization in Realistic Settings

About

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.

Davis Wertheimer, Bharath Hariharan• 2019

Related benchmarks

TaskDatasetResultRank
Few-shot classificationtieredImageNet (test)--
282
Few-shot classificationCUB (test)--
145
Few-shot Image ClassificationminiImageNet (test)--
111
Few-shot Image Classificationmini-Cars (test)
Accuracy52.9
28
Few-shot classificationi-Nat (test)
Accuracy51.25
26
Image ClassificationminiImageNet -> FGVC-Aircraft (test)
Accuracy63.56
8
Showing 6 of 6 rows

Other info

Follow for update