Pith. sign in

REVIEW 4 cited by

SaiT: Sparse Vision Transformers through Adaptive Token Pruning

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 2210.05832 v1 pith:5WCMFXHM submitted 2022-10-11 cs.CV

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

Signed reviews

No signed human review yet.

0 comments
read the original abstract

While vision transformers have achieved impressive results, effectively and efficiently accelerating these models can further boost performances. In this work, we propose a dense/sparse training framework to obtain a unified model, enabling weight sharing across various token densities. Thus one model offers a range of accuracy and throughput tradeoffs for different applications. Besides, we introduce adaptive token pruning to optimize the patch token sparsity based on the input image. In addition, we investigate knowledge distillation to enhance token selection capability in early transformer modules. Sparse adaptive image Transformer (SaiT) offers varying levels of model acceleration by merely changing the token sparsity on the fly. Specifically, SaiT reduces the computation complexity (FLOPs) by 39% - 43% and increases the throughput by 67% - 91% with less than 0.5% accuracy loss for various vision transformer models. Meanwhile, the same model also provides the zero accuracy drop option by skipping the sparsification step. SaiT achieves better accuracy and computation tradeoffs than state-of-the-art transformer and convolutional models.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

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

  1. Token Cropr: Faster ViTs for Quite a Few Tasks

    cs.CV 2024-12 conditional novelty 6.0 of 10

    Cropr uses removable auxiliary heads to learn task-relevant token pruning in ViTs, achieving 1.5-4x speedups with small accuracy drops across image classification, semantic segmentation, and object detection.

  2. Importance-Based Token Merging for Efficient Image and Video Generation

    cs.CV 2024-11 conditional novelty 6.0 of 10

    A token-merging method that anchors computation on high-CFG-importance tokens improves generation quality at fixed inference speedups.

  3. Fusion: A Framework for Unified Sequential Token AdaptatIon in VisiOn TraNsformers

    cs.CV 2026-07 conditional novelty 5.0 of 10

    Staged merge o exit o prune ordering plus lightweight routers lets adaptive ViTs combine three efficiency axes without the accuracy collapse of parallel composition.

  4. Back to Fundamentals: Low-Level Visual Features Guided Progressive Token Pruning

    cs.CV 2025-04 reject novelty 4.0 of 10

    LVTP prunes transformer tokens during semantic segmentation using multi-scale Tsallis entropy with Sobel edge guidance, reporting 20-46% FLOP reduction with a few mIoU points lost and no retraining.

Pith tools