# Segformer++: Efficient Token-Merging Strategies for High-Resolution Semantic Segmentation

arXiv: https://arxiv.org/abs/2405.14467 · HTML: https://mlsanity.com/paper/2405.14467/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Placed in Token pruning and merging for ViTs, one of 12 directions in Efficient LLM inference and serving.
- Builds on 25 of its 28 references that are in the map.
- First posted on arXiv 23 May 2024.

## Placed in

- Efficient LLM inference and serving / [Token pruning and merging for ViTs](https://mlsanity.com/inference/token-pruning-and-merging-for-vits/)

## Builds on (most cited first, 25 of 25)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Pyramid Scene Parsing Network](https://mlsanity.com/paper/1612.01105/) (2016)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [Deep High-Resolution Representation Learning for Visual Recognition](https://mlsanity.com/paper/1908.07919/) (2019)
- [Deep High-Resolution Representation Learning for Human Pose Estimation](https://mlsanity.com/paper/1902.09212/) (2019)
- [Unified Perceptual Parsing for Scene Understanding](https://mlsanity.com/paper/1807.10221/) (2018)
- [Token Merging: Your ViT But Faster](https://mlsanity.com/paper/2210.09461/) (2022)
- [Multiscale Vision Transformers](https://mlsanity.com/paper/2104.11227/) (2021)
- [DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification](https://mlsanity.com/paper/2106.02034/) (2021)
- [Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation](https://mlsanity.com/paper/1909.11065/) (2019)
- [Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations](https://mlsanity.com/paper/2202.07800/) (2022)
- [AdaViT: Adaptive Tokens for Efficient Vision Transformer](https://mlsanity.com/paper/2112.07658/) (2021)
- [AdaViT: Adaptive Vision Transformers for Efficient Image Recognition](https://mlsanity.com/paper/2111.15668/) (2021)
- [Token Merging for Fast Stable Diffusion](https://mlsanity.com/paper/2303.17604/) (2023)
- [SPViT: Enabling Faster Vision Transformers via Soft Token Pruning](https://mlsanity.com/paper/2112.13890/) (2021)
- [HRFormer: High-Resolution Transformer for Dense Prediction](https://mlsanity.com/paper/2110.09408/) (2021)
- [Dynamically pruning segformer for efficient semantic segmentation](https://mlsanity.com/paper/2111.09499/) (2021)
- [All Keypoints You Need: Detecting Arbitrary Keypoints on the Body of Triple, High, and Long Jump Athletes](https://mlsanity.com/paper/2304.02939/) (2023)

## Built on by (most cited first, 9 of 9)

- [Importance-Based Token Merging for Efficient Image and Video Generation](https://mlsanity.com/paper/2411.16720/) (2024)
- [Towards Ball Spin and Trajectory Analysis in Table Tennis Broadcast Videos via Physically Grounded Synthetic-to-Real Transfer](https://mlsanity.com/paper/2504.19863/) (2025)
- [Uplifting Table Tennis: A Robust, Real-World Application for 3D Trajectory and Spin Estimation](https://mlsanity.com/paper/2511.20250/) (2025)
- [Video, How Do Your Tokens Merge?](https://mlsanity.com/paper/2506.03885/) (2025)
- [Efficient-SAM2: Accelerating SAM2 with Object-Aware Visual Encoding and Memory Retrieval](https://mlsanity.com/paper/2602.08224/) (2026)
- [TT4D: A Pipeline and Dataset for Table Tennis 4D Reconstruction From Monocular Videos](https://mlsanity.com/paper/2605.01234/) (2026)
- [MMMS: Multi-Modal Multi-Surface Interactive Segmentation](https://mlsanity.com/paper/2509.12963/) (2025)
- [DSFlash: Comprehensive Panoptic Scene Graph Generation in Realtime](https://mlsanity.com/paper/2603.10538/) (2026)
- [Lean-SAM2: Target-Anchored Memory and Encoder Acceleration for SAM2](https://mlsanity.com/paper/2607.19811/) (2026)

## Abstract (arXiv)

Utilizing transformer architectures for semantic segmentation of high-resolution images is hindered by the attention's quadratic computational complexity in the number of tokens. A solution to this challenge involves decreasing the number of tokens through token merging, which has exhibited remarkable enhancements in inference speed, training efficiency, and memory utilization for image classification tasks. In this paper, we explore various token merging strategies within the framework of the Segformer architecture and perform experiments on multiple semantic segmentation and human pose estimation datasets. Notably, without model re-training, we, for example, achieve an inference acceleration of 61% on the Cityscapes dataset while maintaining the mIoU performance. Consequently, this paper facilitates the deployment of transformer-based architectures on resource-constrained devices and in real-time applications.