SPFormer: Enhancing Vision Transformer with Superpixel Representation

5 Jan 2024  ·  Jieru Mei, Liang-Chieh Chen, Alan Yuille, Cihang Xie ·

In this work, we introduce SPFormer, a novel Vision Transformer enhanced by superpixel representation. Addressing the limitations of traditional Vision Transformers' fixed-size, non-adaptive patch partitioning, SPFormer employs superpixels that adapt to the image's content. This approach divides the image into irregular, semantically coherent regions, effectively capturing intricate details and applicable at both initial and intermediate feature levels. SPFormer, trainable end-to-end, exhibits superior performance across various benchmarks. Notably, it exhibits significant improvements on the challenging ImageNet benchmark, achieving a 1.4% increase over DeiT-T and 1.1% over DeiT-S respectively. A standout feature of SPFormer is its inherent explainability. The superpixel structure offers a window into the model's internal processes, providing valuable insights that enhance the model's interpretability. This level of clarity significantly improves SPFormer's robustness, particularly in challenging scenarios such as image rotations and occlusions, demonstrating its adaptability and resilience.

PDF Abstract
No code implementations yet. Submit your code now

Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods