README.md

Deep Data Augmentation for Weed Recognition Enhancement: A Diffusion Models and Transfer Learning Based Approach

Generated Samples

Performance comparison between diffusion models and GANs.

Fig.1 Performance comparison between diffusion models and state-of-the-art GANs. Best values are in bold.

Diffusion Models

Fig.2 Real (upper) and generated (lower) weed samples for CottonWeedID15 dataset. Each column represents one weed class.

Fig.3 Real (upper) and generated (lower) weed samples for DeepWeeds dataset. Each column represents one weed class.

GANs

BigGAN

Fig.4 Generated weed samples for CottonWeedID15 dataset by BigGAN. Each column represents one weed class.

Fig.5 Generated weed samples for DeepWeeds dataset by BigGAN. Each column represents one weed class.

StyleGAN2

Fig.6 Generated weed samples for CottonWeedID15 dataset by StyleGAN2. Each column represents one weed class.

Fig.7 Generated weed samples for DeepWeeds dataset by StyleGAN2. Each column represents one weed class.

StyleGAN3

Fig.8 Generated weed samples for CottonWeedID15 dataset by StyleGAN3. Each column represents one weed class.