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

• URL: http://arxiv.org/abs/2405.14467v1
• Date: Thu, 23 May 2024 11:54:27 GMT
• Title: Segformer++: Efficient Token-Merging Strategies for High-Resolution Semantic Segmentation
• Authors: Daniel Kienzle, Marco Kantonis, Robin Schön, Rainer Lienhart,
• Abstract summary: token merging has exhibited remarkable enhancements in inference speed, training efficiency, and memory utilization for image classification tasks. This paper facilitates the deployment of transformer-based architectures on resource-constrained devices and in real-time applications.
• Score: 12.249546377051438
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• AsCAN: Asymmetric Convolution-Attention Networks for Efficient Recognition and Generation [48.82264764771652]
  We introduce AsCAN -- a hybrid architecture, combining both convolutional and transformer blocks. AsCAN supports a variety of tasks: recognition, segmentation, class-conditional image generation. We then scale the same architecture to solve a large-scale text-to-image task and show state-of-the-art performance.
  arXiv  Detail & Related papers  (2024-11-07T18:43:17Z)
• MacFormer: Semantic Segmentation with Fine Object Boundaries [38.430631361558426]
  We introduce a new semantic segmentation architecture, MacFormer'', which features two key components. Firstly, using learnable agent tokens, a Mutual Agent Cross-Attention (MACA) mechanism effectively facilitates the bidirectional integration of features across encoder and decoder layers. Secondly, a Frequency Enhancement Module (FEM) in the decoder leverages high-frequency and low-frequency components to boost features in the frequency domain. MacFormer is demonstrated to be compatible with various network architectures and outperforms existing methods in both accuracy and efficiency on datasets benchmark ADE20K and Cityscapes.
  arXiv  Detail & Related papers  (2024-08-11T05:36:10Z)
• Semantic Equitable Clustering: A Simple and Effective Strategy for Clustering Vision Tokens [57.37893387775829]
  We introduce a fast and balanced clustering method, named textbfSemantic textbfEquitable textbfClustering (SEC) SEC clusters tokens based on their global semantic relevance in an efficient, straightforward manner. We propose a versatile vision backbone, SECViT, to serve as a vision language connector.
  arXiv  Detail & Related papers  (2024-05-22T04:49:00Z)
• PEM: Prototype-based Efficient MaskFormer for Image Segmentation [10.795762739721294]
  Recent transformer-based architectures have shown impressive results in the field of image segmentation. We propose Prototype-based Efficient MaskFormer (PEM), an efficient transformer-based architecture that can operate in multiple segmentation tasks.
  arXiv  Detail & Related papers  (2024-02-29T18:21:54Z)
• A Decoding Scheme with Successive Aggregation of Multi-Level Features for Light-Weight Semantic Segmentation [4.454210876879237]
  We propose a novel decoding scheme for semantic segmentation. It takes multi-level features from the encoder with multi-scale architecture. It aims to achieve not only reduced computational expense but also higher segmentation accuracy.
  arXiv  Detail & Related papers  (2024-02-17T05:31:10Z)
• MST: Adaptive Multi-Scale Tokens Guided Interactive Segmentation [8.46894039954642]
  We propose a novel multi-scale token adaptation algorithm for interactive segmentation. By performing top-k operations across multi-scale tokens, the computational complexity is greatly simplified. We also propose a token learning algorithm based on contrastive loss.
  arXiv  Detail & Related papers  (2024-01-09T07:59:42Z)
• Low-Resolution Self-Attention for Semantic Segmentation [96.81482872022237]
  We introduce the Low-Resolution Self-Attention (LRSA) mechanism to capture global context at a significantly reduced computational cost. Our approach involves computing self-attention in a fixed low-resolution space regardless of the input image's resolution. We demonstrate the effectiveness of our LRSA approach by building the LRFormer, a vision transformer with an encoder-decoder structure.
  arXiv  Detail & Related papers  (2023-10-08T06:10:09Z)
• Semantics-Aware Dynamic Localization and Refinement for Referring Image Segmentation [102.25240608024063]
  Referring image segments an image from a language expression. We develop an algorithm that shifts from being localization-centric to segmentation-language. Compared to its counterparts, our method is more versatile yet effective.
  arXiv  Detail & Related papers  (2023-03-11T08:42:40Z)
• Transforming the Interactive Segmentation for Medical Imaging [34.57242805353604]
  The goal of this paper is to interactively refine the automatic segmentation on challenging structures that fall behind human performance. We propose a novel Transformer-based architecture for Interactive (TIS) Our proposed architecture is composed of Transformer Decoder variants, which naturally fulfills feature comparison with the attention mechanisms.
  arXiv  Detail & Related papers  (2022-08-20T03:28:23Z)
• A Holistically-Guided Decoder for Deep Representation Learning with Applications to Semantic Segmentation and Object Detection [74.88284082187462]
  One common strategy is to adopt dilated convolutions in the backbone networks to extract high-resolution feature maps. We propose one novel holistically-guided decoder which is introduced to obtain the high-resolution semantic-rich feature maps.
  arXiv  Detail & Related papers  (2020-12-18T10:51:49Z)
• Synthetic Convolutional Features for Improved Semantic Segmentation [139.5772851285601]
  We suggest to generate intermediate convolutional features and propose the first synthesis approach that is catered to such intermediate convolutional features. This allows us to generate new features from label masks and include them successfully into the training procedure. Experimental results and analysis on two challenging datasets Cityscapes and ADE20K show that our generated feature improves performance on segmentation tasks.
  arXiv  Detail & Related papers  (2020-09-18T14:12:50Z)

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.