Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

SPFormer: Enhancing Vision Transformer with Superpixel Representation

About

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.

Jieru Mei, Liang-Chieh Chen, Alan Yuille, Cihang Xie• 2024

Related benchmarks

TaskDatasetResultRank
Part SegmentationImageNet (IN)
mIoU (M2O)12.1
13
Part SegmentationIN-S919
M2O mIoU51.92
13
Part SegmentationADE20K
M2O mIoU14.65
13
Part SegmentationPartImageNet (PartIN)
M2O mIoU27.21
13
Part SegmentationCOCO
M2O mIoU8.37
13
Showing 5 of 5 rows

Other info

Follow for update