TensorX
返回文献探索

Paper · arXiv 2503.19108

Your ViT is Secretly an Image Segmentation Model

Tommie Kerssies, Niccolò Cavagnero, Alexander Hermans, Narges Norouzi, Giuseppe Averta, Bastian Leibe, Gijs Dubbelman, Daan de Geus

25 upvotesMarch 24, 2025arXiv 预印本
AI 摘要

The Encoder-only Mask Transformer (EoMT) achieves state-of-the-art image segmentation accuracy by learning task-specific components through large-scale pre-training, while maintaining superior prediction speed compared to models with additional architectural complexity.

Vision TransformersViTsimage segmentationmulti-scale featurespixel decoderTransformer decoderinductive biasesEncoder-only Mask TransformerEoMTlarge-scale pre-trainingprediction speed

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/.

北京市昌平区探索星信息技术及软件开发工作室

京ICP备2026059466号