ClustViT: Clustering-based Token Merging for Semantic Segmentation

• URL: http://arxiv.org/abs/2510.01948v1
• Date: Thu, 02 Oct 2025 12:15:40 GMT
• Title: ClustViT: Clustering-based Token Merging for Semantic Segmentation
• Authors: Fabio Montello, Ronja Güldenring, Lazaros Nalpantidis,
• Abstract summary: Recent works have focused on dynamically merging tokens according to the image complexity.<n>We propose ClustViT, where we expand upon the Vision Transformer (ViT) backbone and address semantic segmentation.<n>Our approach achieves up to 2.18x fewer GFLOPs and 1.64x faster inference on three different datasets, with comparable segmentation accuracy.
• Score: 2.661056455199956
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Vision Transformers can achieve high accuracy and strong generalization across various contexts, but their practical applicability on real-world robotic systems is limited due to their quadratic attention complexity. Recent works have focused on dynamically merging tokens according to the image complexity. Token merging works well for classification but is less suited to dense prediction. We propose ClustViT, where we expand upon the Vision Transformer (ViT) backbone and address semantic segmentation. Within our architecture, a trainable Cluster module merges similar tokens along the network guided by pseudo-clusters from segmentation masks. Subsequently, a Regenerator module restores fine details for downstream heads. Our approach achieves up to 2.18x fewer GFLOPs and 1.64x faster inference on three different datasets, with comparable segmentation accuracy. Our code and models will be made publicly available.

Related papers

• Revisiting the Integration of Convolution and Attention for Vision Backbone [59.50256661158862]
  Convolutions and multi-head self-attentions (MHSAs) are typically considered alternatives to each other for building vision backbones. We propose in this work to use MSHAs and Convs in parallel textbfat different granularity levels instead. We empirically verify the potential of the proposed integration scheme, named textitGLMix: by offloading the burden of fine-grained features to light-weight Convs, it is sufficient to use MHSAs in a few semantic slots.
  arXiv  Detail & Related papers  (2024-11-21T18:59:08Z)
• Semantic Equitable Clustering: A Simple and Effective Strategy for Clustering Vision Tokens [57.37893387775829]
  We introduce a fast and balanced clustering method, named Semantic Equitable Clustering (SEC)<n>SEC clusters tokens based on their global semantic relevance in an efficient, straightforward manner.<n>We propose a versatile vision backbone, SECViT, to serve as a vision language connector.
  arXiv  Detail & Related papers  (2024-05-22T04:49:00Z)
• A Lightweight Clustering Framework for Unsupervised Semantic Segmentation [28.907274978550493]
  Unsupervised semantic segmentation aims to categorize each pixel in an image into a corresponding class without the use of annotated data. We propose a lightweight clustering framework for unsupervised semantic segmentation. Our framework achieves state-of-the-art results on PASCAL VOC and MS COCO datasets.
  arXiv  Detail & Related papers  (2023-11-30T15:33:42Z)
• HGFormer: Hierarchical Grouping Transformer for Domain Generalized Semantic Segmentation [113.6560373226501]
  This work studies semantic segmentation under the domain generalization setting. We propose a novel hierarchical grouping transformer (HGFormer) to explicitly group pixels to form part-level masks and then whole-level masks. Experiments show that HGFormer yields more robust semantic segmentation results than per-pixel classification methods and flat grouping transformers.
  arXiv  Detail & Related papers  (2023-05-22T13:33:41Z)
• Making Vision Transformers Efficient from A Token Sparsification View [26.42498120556985]
  We propose a novel Semantic Token ViT (STViT) for efficient global and local vision transformers. Our method can achieve competitive results compared to the original networks in object detection and instance segmentation, with over 30% FLOPs reduction for backbone. In addition, we design a STViT-R(ecover) network to restore the detailed spatial information based on the STViT, making it work for downstream tasks.
  arXiv  Detail & Related papers  (2023-03-15T15:12:36Z)
• ClusTR: Exploring Efficient Self-attention via Clustering for Vision Transformers [70.76313507550684]
  We propose a content-based sparse attention method, as an alternative to dense self-attention. Specifically, we cluster and then aggregate key and value tokens, as a content-based method of reducing the total token count. The resulting clustered-token sequence retains the semantic diversity of the original signal, but can be processed at a lower computational cost.
  arXiv  Detail & Related papers  (2022-08-28T04:18:27Z)
• CloudAttention: Efficient Multi-Scale Attention Scheme For 3D Point Cloud Learning [81.85951026033787]
  We set transformers in this work and incorporate them into a hierarchical framework for shape classification and part and scene segmentation. We also compute efficient and dynamic global cross attentions by leveraging sampling and grouping at each iteration. The proposed hierarchical model achieves state-of-the-art shape classification in mean accuracy and yields results on par with the previous segmentation methods.
  arXiv  Detail & Related papers  (2022-07-31T21:39:15Z)
• CenterCLIP: Token Clustering for Efficient Text-Video Retrieval [67.21528544724546]
  In CLIP, the essential visual tokenization process, which produces discrete visual token sequences, generates many homogeneous tokens due to the redundancy nature of consecutive frames in videos. This significantly increases computation costs and hinders the deployment of video retrieval models in web applications. In this paper, we design a multi-segment token clustering algorithm to find the most representative tokens and drop the non-essential ones.
  arXiv  Detail & Related papers  (2022-05-02T12:02:09Z)
• SOTR: Segmenting Objects with Transformers [0.0]
  We present a novel, flexible, and effective transformer-based model for high-quality instance segmentation. The proposed method, Segmenting Objects with TRansformers (SOTR), simplifies the segmentation pipeline. Our SOTR performs well on the MS COCO dataset and surpasses state-of-the-art instance segmentation approaches.
  arXiv  Detail & Related papers  (2021-08-15T14:10:11Z)
• Segmenter: Transformer for Semantic Segmentation [79.9887988699159]
  We introduce Segmenter, a transformer model for semantic segmentation. We build on the recent Vision Transformer (ViT) and extend it to semantic segmentation. It outperforms the state of the art on the challenging ADE20K dataset and performs on-par on Pascal Context and Cityscapes.
  arXiv  Detail & Related papers  (2021-05-12T13:01:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.