SSformer: A Lightweight Transformer for Semantic Segmentation

TL;DR

SSformer is a lightweight transformer model tailored for semantic segmentation, combining hierarchical design and a novel decoder to achieve competitive accuracy with reduced model size and computational cost.

Contribution

The paper introduces SSformer, a new lightweight transformer architecture that effectively integrates local and global attention for semantic segmentation.

Findings

Achieves comparable mIoU to state-of-the-art models.

Maintains smaller model size and lower computational complexity.

Demonstrates effectiveness of hierarchical design with a specialized decoder.

Abstract

It is well believed that Transformer performs better in semantic segmentation compared to convolutional neural networks. Nevertheless, the original Vision Transformer may lack of inductive biases of local neighborhoods and possess a high time complexity. Recently, Swin Transformer sets a new record in various vision tasks by using hierarchical architecture and shifted windows while being more efficient. However, as Swin Transformer is specifically designed for image classification, it may achieve suboptimal performance on dense prediction-based segmentation task. Further, simply combing Swin Transformer with existing methods would lead to the boost of model size and parameters for the final segmentation model. In this paper, we rethink the Swin Transformer for semantic segmentation, and design a lightweight yet effective transformer model, called SSformer. In this model, considering the inherent hierarchical design of Swin Transformer, we propose a decoder to aggregate information from different layers, thus obtaining both local and global attentions. Experimental results show the proposed SSformer yields comparable mIoU performance with state-of-the-art models, while maintaining a smaller model size and lower compute.