Your ViT is Secretly an Image Segmentation Model

• URL: http://arxiv.org/abs/2503.19108v1
• Date: Mon, 24 Mar 2025 19:56:02 GMT
• Title: Your ViT is Secretly an Image Segmentation Model
• Authors: Tommie Kerssies, Niccolò Cavagnero, Alexander Hermans, Narges Norouzi, Giuseppe Averta, Bastian Leibe, Gijs Dubbelman, Daan de Geus,
• Abstract summary: Vision Transformers (ViTs) have shown remarkable performance and scalability across various computer vision tasks.<n>We show that inductive biases introduced by task-specific components can instead be learned by the ViT itself.<n>We introduce the Mask Transformer (EoMT), which repurposes the plain ViT architecture to conduct image segmentation.
• Score: 50.71238842539735
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Vision Transformers (ViTs) have shown remarkable performance and scalability across various computer vision tasks. To apply single-scale ViTs to image segmentation, existing methods adopt a convolutional adapter to generate multi-scale features, a pixel decoder to fuse these features, and a Transformer decoder that uses the fused features to make predictions. In this paper, we show that the inductive biases introduced by these task-specific components can instead be learned by the ViT itself, given sufficiently large models and extensive pre-training. Based on these findings, we introduce the Encoder-only Mask Transformer (EoMT), which repurposes the plain ViT architecture to conduct image segmentation. With large-scale models and pre-training, EoMT obtains a segmentation accuracy similar to state-of-the-art models that use task-specific components. At the same time, EoMT is significantly faster than these methods due to its architectural simplicity, e.g., up to 4x faster with ViT-L. Across a range of model sizes, EoMT demonstrates an optimal balance between segmentation accuracy and prediction speed, suggesting that compute resources are better spent on scaling the ViT itself rather than adding architectural complexity. Code: https://www.tue-mps.org/eomt/.

Related papers

• Depth-Wise Convolutions in Vision Transformers for Efficient Training on Small Datasets [11.95214938154427]
  Vision Transformer (ViT) captures global information by dividing images into patches. ViT lacks inductive bias during image or video dataset training. We present a lightweight Depth-Wise Convolution module as a shortcut in ViT models.
  arXiv  Detail & Related papers  (2024-07-28T04:23:40Z)
• Minimalist and High-Performance Semantic Segmentation with Plain Vision Transformers [10.72362704573323]
  We introduce the PlainSeg, a model comprising only three 3$times$3 convolutions in addition to the transformer layers. We also present the PlainSeg-Hier, which allows for the utilization of hierarchical features.
  arXiv  Detail & Related papers  (2023-10-19T14:01:40Z)
• PriViT: Vision Transformers for Fast Private Inference [55.36478271911595]
  Vision Transformer (ViT) architecture has emerged as the backbone of choice for state-of-the-art deep models for computer vision applications. ViTs are ill-suited for private inference using secure multi-party protocols, due to the large number of non-polynomial operations. We propose PriViT, an algorithm to selectively " Taylorize" nonlinearities in ViTs while maintaining their prediction accuracy.
  arXiv  Detail & Related papers  (2023-10-06T21:45:05Z)
• RangeViT: Towards Vision Transformers for 3D Semantic Segmentation in Autonomous Driving [80.14669385741202]
  Vision transformers (ViTs) have achieved state-of-the-art results in many image-based benchmarks. ViTs are notoriously hard to train and require a lot of training data to learn powerful representations. We show that our method, called RangeViT, outperforms existing projection-based methods on nuScenes and Semantic KITTI.
  arXiv  Detail & Related papers  (2023-01-24T18:50:48Z)
• Where are my Neighbors? Exploiting Patches Relations in Self-Supervised Vision Transformer [3.158346511479111]
  We propose a simple but still effective self-supervised learning (SSL) strategy to train Vision Transformers (ViTs) We define a set of SSL tasks based on relations of image patches that the model has to solve before or jointly during the downstream training. Our RelViT model optimize all the output tokens of the transformer encoder that are related to the image patches, thus exploiting more training signal at each training step.
  arXiv  Detail & Related papers  (2022-06-01T13:25:32Z)
• HiViT: Hierarchical Vision Transformer Meets Masked Image Modeling [126.89573619301953]
  We propose a new design of hierarchical vision transformers named HiViT (short for Hierarchical ViT) HiViT enjoys both high efficiency and good performance in MIM. In running MAE on ImageNet-1K, HiViT-B reports a +0.6% accuracy gain over ViT-B and a 1.9$times$ speed-up over Swin-B.
  arXiv  Detail & Related papers  (2022-05-30T09:34:44Z)
• A Simple Single-Scale Vision Transformer for Object Localization and Instance Segmentation [79.265315267391]
  We propose a simple and compact ViT architecture called Universal Vision Transformer (UViT) UViT achieves strong performance on object detection and instance segmentation tasks.
  arXiv  Detail & Related papers  (2021-12-17T20:11:56Z)
• Vision Transformers are Robust Learners [65.91359312429147]
  We study the robustness of the Vision Transformer (ViT) against common corruptions and perturbations, distribution shifts, and natural adversarial examples. We present analyses that provide both quantitative and qualitative indications to explain why ViTs are indeed more robust learners.
  arXiv  Detail & Related papers  (2021-05-17T02:39:22Z)

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.