CFPFormer: Feature-pyramid like Transformer Decoder for Segmentation and Detection

arXiv:2404.15451v1 Announce Type: new
Abstract: Feature pyramids have been widely adopted in convolutional neural networks (CNNs) and transformers for tasks like medical image segmentation and object detection. However, the currently existing models generally focus on the Encoder-side Transformer to extract features, from which decoder improvement can bring further potential with well-designed architecture. We propose CFPFormer, a novel decoder block that integrates feature pyramids and transformers. Specifically, by leveraging patch embedding, cross-layer feature concatenation, and Gaussian attention mechanisms, CFPFormer enhances feature …

abstract arxiv cnns convolutional neural networks cs.cv decoder detection encoder extract feature features focus however image improvement medical networks neural networks object pyramid segmentation tasks transformer transformer decoder transformers type