Pith. sign in

REVIEW 3 cited by

SPFormer: Enhancing Vision Transformer with Superpixel Representation

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2401.02931 v1 pith:SRJ2GI6E submitted 2024-01-05 cs.CV

classification cs.CV
keywords spformerimagesuperpixelvisionchallengingexhibitsfeaturemodel
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

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.

Discussion (0). Sign in to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. TrajTok: Learning Trajectory Tokens enables better Video Understanding

    cs.CV 2026-02 unverdicted novelty 7.0 of 10

    TrajTok learns adaptive trajectory tokens for videos through a unified end-to-end segmenter, improving understanding performance and efficiency over patch-based or external-pipeline tokenizers.

  2. Elastic Attention Cores for Scalable Vision Transformers

    cs.CV 2026-05 unverdicted novelty 6.0 of 10

    VECA learns effective visual representations using core-periphery attention where patches interact exclusively via a resolution-invariant set of learned core embeddings, achieving linear O(N) complexity while maintain...

  3. TrajTok: Learning Trajectory Tokens enables better Video Understanding

    cs.CV 2026-02 conditional novelty 6.0 of 10

    TrajTok learns to tokenize video into object-trajectory tokens end-to-end, improving video CLIP, probing, and VLM performance over patch and token-merging baselines.

Pith tools