DeepAI AI Chat
Log In Sign Up

Few-Shot Learning with Localization in Realistic Settings

by   Davis Wertheimer, et al.
cornell university

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.


page 1

page 6

page 7


One-Class Meta-Learning: Towards Generalizable Few-Shot Open-Set Classification

Real-world classification tasks are frequently required to work in an op...

Domain Agnostic Few-Shot Learning For Document Intelligence

Few-shot learning aims to generalize to novel classes with only a few sa...

Many-Class Few-Shot Learning on Multi-Granularity Class Hierarchy

We study many-class few-shot (MCFS) problem in both supervised learning ...

A Unified Framework with Meta-dropout for Few-shot Learning

Conventional training of deep neural networks usually requires a substan...

Interpretable Concept-based Prototypical Networks for Few-Shot Learning

Few-shot learning aims at recognizing new instances from classes with li...

FHIST: A Benchmark for Few-shot Classification of Histological Images

Few-shot learning has recently attracted wide interest in image classifi...

Few-shot Image Recognition with Manifolds

In this paper, we extend the traditional few-shot learning (FSL) problem...