Meta-Reinforced Synthetic Data for One-Shot Fine-Grained Visual Recognition
This work addresses data scarcity for researchers and practitioners in fine-grained visual recognition, but it is incremental as it builds on existing meta-learning and image generation methods.
The paper tackles the problem of training data scarcity in one-shot fine-grained visual recognition by proposing a meta-learning framework that combines generated images with original images to improve accuracy, demonstrating consistent improvement over baselines on benchmarks.
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.