Resnet Based Feature Extraction For Textline Images

via “resnet-50 cnn feature extraction with imagenet pretraining”

object-detection model by undefined. 2,28,520 downloads.

Unique: Uses ImageNet-1k pretrained ResNet-50 weights frozen or fine-tuned during DETR training, providing a stable feature extractor that has been validated across millions of natural images

vs others: More computationally efficient than Vision Transformer backbones while maintaining competitive accuracy; better established than EfficientNet for detection tasks due to widespread adoption in DETR implementations