Exploring the Integration of Key-Value Attention Into Pure and Hybrid Transformers for Semantic Segmentation

• URL: http://arxiv.org/abs/2503.18862v1
• Date: Mon, 24 Mar 2025 16:38:31 GMT
• Title: Exploring the Integration of Key-Value Attention Into Pure and Hybrid Transformers for Semantic Segmentation
• Authors: DeShin Hwa, Tobias Holmes, Klaus Drechsler,
• Abstract summary: KV Transformer shows promising results in synthetic, NLP, and image classification tasks.<n>This is especially conducive to use cases where local inference is required, such as medical screening applications.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: While CNNs were long considered state of the art for image processing, the introduction of Transformer architectures has challenged this position. While achieving excellent results in image classification and segmentation, Transformers remain inherently reliant on large training datasets and remain computationally expensive. A newly introduced Transformer derivative named KV Transformer shows promising results in synthetic, NLP, and image classification tasks, while reducing complexity and memory usage. This is especially conducive to use cases where local inference is required, such as medical screening applications. We endeavoured to further evaluate the merit of KV Transformers on semantic segmentation tasks, specifically in the domain of medical imaging. By directly comparing traditional and KV variants of the same base architectures, we provide further insight into the practical tradeoffs of reduced model complexity. We observe a notable reduction in parameter count and multiply accumulate operations, while achieving similar performance from most of the KV variant models when directly compared to their QKV implementation.

Related papers

• Key-Value Transformer [47.64219291655723]
  Key-value formulation (KV) generates symmetric attention maps, along with an asymmetric version that incorporates a 2D positional encoding into the attention matrix. Experiments encompass three task types -- synthetics (such as reversing or sorting a list), vision (mnist or cifar classification), and NLP.
  arXiv  Detail & Related papers  (2023-05-28T20:26:06Z)
• SSformer: A Lightweight Transformer for Semantic Segmentation [7.787950060560868]
  Swin Transformer set a new record in various vision tasks by using hierarchical architecture and shifted windows. We design a lightweight yet effective transformer model, called SSformer. Experimental results show the proposed SSformer yields comparable mIoU performance with state-of-the-art models.
  arXiv  Detail & Related papers  (2022-08-03T12:57:00Z)
• TransNorm: Transformer Provides a Strong Spatial Normalization Mechanism for a Deep Segmentation Model [4.320393382724066]
  convolutional neural networks (CNNs) have been the prevailing technique in the medical image processing era. We propose Trans-Norm, a novel deep segmentation framework which consolidates a Transformer module into both encoder and skip-connections of the standard U-Net.
  arXiv  Detail & Related papers  (2022-07-27T09:54:10Z)
• Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentation [58.4650849317274]
  Volumetric Aggregation with Transformers (VAT) is a cost aggregation network for few-shot segmentation. VAT attains state-of-the-art performance for semantic correspondence as well, where cost aggregation also plays a central role.
  arXiv  Detail & Related papers  (2022-07-22T04:10:30Z)
• Efficient Vision Transformers via Fine-Grained Manifold Distillation [96.50513363752836]
  Vision transformer architectures have shown extraordinary performance on many computer vision tasks. Although the network performance is boosted, transformers are often required more computational resources. We propose to excavate useful information from the teacher transformer through the relationship between images and the divided patches.
  arXiv  Detail & Related papers  (2021-07-03T08:28:34Z)
• XCiT: Cross-Covariance Image Transformers [73.33400159139708]
  We propose a "transposed" version of self-attention that operates across feature channels rather than tokens. The resulting cross-covariance attention (XCA) has linear complexity in the number of tokens, and allows efficient processing of high-resolution images.
  arXiv  Detail & Related papers  (2021-06-17T17:33:35Z)
• Visformer: The Vision-friendly Transformer [105.52122194322592]
  We propose a new architecture named Visformer, which is abbreviated from the Vision-friendly Transformer' With the same computational complexity, Visformer outperforms both the Transformer-based and convolution-based models in terms of ImageNet classification accuracy.
  arXiv  Detail & Related papers  (2021-04-26T13:13:03Z)
• Medical Transformer: Gated Axial-Attention for Medical Image Segmentation [73.98974074534497]
  We study the feasibility of using Transformer-based network architectures for medical image segmentation tasks. We propose a Gated Axial-Attention model which extends the existing architectures by introducing an additional control mechanism in the self-attention module. To train the model effectively on medical images, we propose a Local-Global training strategy (LoGo) which further improves the performance.
  arXiv  Detail & Related papers  (2021-02-21T18:35:14Z)
• Training Vision Transformers for Image Retrieval [32.09708181236154]
  We adopt vision transformers for generating image descriptors and train the resulting model with a metric learning objective. Our results show consistent and significant improvements of transformers over convolution-based approaches.
  arXiv  Detail & Related papers  (2021-02-10T18:56:41Z)
• Toward Transformer-Based Object Detection [12.704056181392415]
  Vision Transformers can be used as a backbone by a common detection task head to produce competitive COCO results. ViT-FRCNN demonstrates several known properties associated with transformers, including large pretraining capacity and fast fine-tuning performance. We view ViT-FRCNN as an important stepping stone toward a pure-transformer solution of complex vision tasks such as object detection.
  arXiv  Detail & Related papers  (2020-12-17T22:33:14Z)

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.