# Meta-Reinforced Synthetic Data for One-Shot Fine-Grained Visual Recognition

Source: [Meta-Reinforced Synthetic Data for One-Shot Fine-Grained Visual Recognition](<https://www.sota2.com/research/paper/68fa66aa1e209131cea117c6>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T21:55:21.281Z

Authors: Satoshi Tsutsui, Yanwei Fu, David Crandall

Published: 2019-11-17T06:37:58.000Z

## Abstract

One-shot fine-grained visual recognition often suffers from the problem of training data scarcity for new fine-grained classes. To alleviate this problem, an off-the-shelf image generator can be applied to synthesize additional training images, but these synthesized images are often not helpful for actually improving the accuracy of one-shot fine-grained recognition. This paper proposes a meta-learning framework to combine generated images with original images, so that the resulting \`\`hybrid'' training images can improve one-shot learning. Specifically, the generic image generator is updated by a few training instances of novel classes, and a Meta Image Reinforcing Network (MetaIRNet) is proposed to conduct one-shot fine-grained recognition as well as image reinforcement. The model is trained in an end-to-end manner, and our experiments demonstrate consistent improvement over baselines on one-shot fine-grained image classification benchmarks.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1911.07164>)

[PDF](<https://arxiv.org/pdf/1911.07164.pdf>)