计算机科学
人工智能
弹丸
一次性
图像(数学)
计算机视觉
发电机(电路理论)
强化学习
模式识别(心理学)
上下文图像分类
机器学习
机械工程
物理
工程类
功率(物理)
有机化学
化学
量子力学
作者
Satoshi Tsutsui,Yanwei Fu,David Crandall
标识
DOI:10.1109/tpami.2022.3167112
摘要
One-shot fine-grained visual recognition often suffers from the problem of having few training examples for new fine-grained classes. To alleviate this problem, off-the-shelf image generation techniques based on Generative Adversarial Networks (GANs) can potentially create additional training images. However, these GAN-generated images are often not helpful for actually improving the accuracy of one-shot fine-grained recognition. In this paper, we propose a meta-learning framework to combine generated images with original images, so that the resulting "hybrid" training images 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. Our experiments demonstrate consistent improvement over baselines on one-shot fine-grained image classification benchmarks. Furthermore, our analysis shows that the reinforced images have more diversity compared to the original and GAN-generated images.
科研通智能强力驱动
Strongly Powered by AbleSci AI