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

TL;DR

CFPFormer introduces a novel transformer-based decoder with feature pyramids and Gaussian Attention, improving medical image segmentation by capturing long-range dependencies efficiently.

Contribution

The paper proposes CFPFormer, a new decoder architecture that enhances feature extraction in segmentation models while reducing complexity through Gaussian Attention.

Findings

Achieved 92.02% Dice Score on medical datasets.

Outperformed more complex ViT and Swin Transformer baselines.

Demonstrated effectiveness of the proposed decoder architecture.

Abstract

Feature pyramids have been widely adopted in convolutional neural networks and transformers for tasks in medical image segmentation. However, existing models generally focus on the Encoder-side Transformer for feature extraction. We further explore the potential in improving the feature decoder with a well-designed architecture. We propose Cross Feature Pyramid Transformer decoder (CFPFormer), a novel decoder block that integrates feature pyramids and transformers. Even though transformer-like architecture impress with outstanding performance in segmentation, the concerns to reduce the redundancy and training costs still exist. Specifically, by leveraging patch embedding, cross-layer feature concatenation mechanisms, CFPFormer enhances feature extraction capabilities while complexity issue is mitigated by our Gaussian Attention. Benefiting from Transformer structure and U-shaped connections, our work is capable of capturing long-range dependencies and effectively up-sample feature maps. Experimental results are provided to evaluate CFPFormer on medical image segmentation datasets, demonstrating the efficacy and effectiveness. With a ResNet50 backbone, our method achieves 92.02\% Dice Score, highlighting the efficacy of our methods. Notably, our VGG-based model outperformed baselines with more complex ViT and Swin Transformer backbone.