# Learned Thresholds Token Merging and Pruning for Vision Transformers

Source: [Learned Thresholds Token Merging and Pruning for Vision Transformers](<https://www.sota2.com/research/paper/68fa70551e209131cea4a4ce>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-04T03:52:39.285Z

Authors: Maxim Bonnaerens, Joni Dambre

Published: 2023-07-20T11:30:12.000Z

## Abstract

Vision transformers have demonstrated remarkable success in a wide range of computer vision tasks over the last years. However, their high computational costs remain a significant barrier to their practical deployment. In particular, the complexity of transformer models is quadratic with respect to the number of input tokens. Therefore techniques that reduce the number of input tokens that need to be processed have been proposed. This paper introduces Learned Thresholds token Merging and Pruning (LTMP), a novel approach that leverages the strengths of both token merging and token pruning. LTMP uses learned threshold masking modules that dynamically determine which tokens to merge and which to prune. We demonstrate our approach with extensive experiments on vision transformers on the ImageNet classification task. Our results demonstrate that LTMP achieves state-of-the-art accuracy across reduction rates while requiring only a single fine-tuning epoch, which is an order of magnitude faster than previous methods. Code is available at https://github.com/Mxbonn/ltmp .

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Image Classification on ImageNet-1K (val) (Accuracy, Latency, and FLOPs)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-1k-val-accuracy-latency-and-flops.md>): Image Classification; ImageNet-1k (val); Latency (ms): 107.

- [Image Classification on ImageNet-1K (val) (Accuracy)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-1k-val-accuracy.md>): Image Classification; ImageNet-1k (val); Top-1 Accuracy: not recorded.

- [Image Classification on ImageNet-1k](<https://www.sota2.com/research/sota/image-classification-on-imagenet-1k.md>): Image Classification; ImageNet-1K; Top-1 Acc: not recorded.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2307.10780>)

[PDF](<https://arxiv.org/pdf/2307.10780.pdf>)

[Implementation](<https://github.com/Mxbonn/ltmp>)