SparseSwin: Swin Transformer with Sparse Transformer Block

TL;DR

SparseSwin introduces a sparse transformer block within the Swin Transformer architecture, significantly reducing parameters and computational complexity while maintaining high accuracy in image classification tasks.

Contribution

The paper proposes the Sparse Transformer (SparTa) Block with a sparse token converter and integrates it into Swin Transformer, enhancing efficiency and performance.

Findings

Achieves 86.96% accuracy on ImageNet100

Outperforms state-of-the-art models on CIFAR10 and CIFAR100

Uses fewer parameters while maintaining high accuracy

Abstract

Advancements in computer vision research have put transformer architecture as the state of the art in computer vision tasks. One of the known drawbacks of the transformer architecture is the high number of parameters, this can lead to a more complex and inefficient algorithm. This paper aims to reduce the number of parameters and in turn, made the transformer more efficient. We present Sparse Transformer (SparTa) Block, a modified transformer block with an addition of a sparse token converter that reduces the number of tokens used. We use the SparTa Block inside the Swin T architecture (SparseSwin) to leverage Swin capability to downsample its input and reduce the number of initial tokens to be calculated. The proposed SparseSwin model outperforms other state of the art models in image classification with an accuracy of 86.96%, 97.43%, and 85.35% on the ImageNet100, CIFAR10, and CIFAR100 datasets respectively. Despite its fewer parameters, the result highlights the potential of a transformer architecture using a sparse token converter with a limited number of tokens to optimize the use of the transformer and improve its performance.