Pith. sign in

REVIEW 1 cited by

Superpixel Tokenization for Vision Transformers: Preserving Semantic Integrity in Visual Tokens

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 2412.04680 v3 pith:YNASVBLS submitted 2024-12-06 cs.CV

classification cs.CV
keywords tokenizationsuperpixelsuperpixelstokentokensvisionvisualsuccess
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Transformers, a groundbreaking architecture proposed for Natural Language Processing (NLP), have also achieved remarkable success in Computer Vision. A cornerstone of their success lies in the attention mechanism, which models relationships among tokens. While the tokenization process in NLP inherently ensures that a single token does not contain multiple semantics, the tokenization of Vision Transformer (ViT) utilizes tokens from uniformly partitioned square image patches, which may result in an arbitrary mixing of visual concepts in a token. In this work, we propose to substitute the grid-based tokenization in ViT with superpixel tokenization, which employs superpixels to generate a token that encapsulates a sole visual concept. Unfortunately, the diverse shapes, sizes, and locations of superpixels make integrating superpixels into ViT tokenization rather challenging. Our tokenization pipeline, comprised of pre-aggregate extraction and superpixel-aware aggregation, overcomes the challenges that arise in superpixel tokenization. Extensive experiments demonstrate that our approach, which exhibits strong compatibility with existing frameworks, enhances the accuracy and robustness of ViT on various downstream tasks.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

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

  1. Position: Foundation Models Need Digital Twin Representations

    cs.LG 2025-05 conditional novelty 4.0 of 10

    A position paper proposes replacing token-based representations in foundation models with outcome-driven digital twin representations that explicitly encode physical and semantic structure.

Pith tools