Patch AutoAugment is a patch-level automatic data augmentation algorithm that automatically searches for the optimal augmentation policies for the patches of an image. Specifically, PAA allows each patch DA operation to be controlled by an agent and models it as a Multi-Agent Reinforcement Learning (MARL) problem. At each step, PAA samples the most effective operation for each patch based on its content and the semantics of the whole image. The agents cooperate as a team and share a unified team reward for achieving the joint optimal DA policy of the whole image. PAA is co-trained with a target network through adversarial training. At each step, the policy network samples the most effective operation for each patch based on its content and the semantics of the image.
Source: Local Patch AutoAugment with Multi-Agent CollaborationPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Object Detection | 3 | 23.08% |
Image Generation | 1 | 7.69% |
Super-Resolution | 1 | 7.69% |
Zero-Shot Learning | 1 | 7.69% |
Dialogue Generation | 1 | 7.69% |
Ensemble Learning | 1 | 7.69% |
Medical Object Detection | 1 | 7.69% |
2D Object Detection | 1 | 7.69% |
Fine-Grained Image Recognition | 1 | 7.69% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |