Segmenter: Transformer for Semantic Segmentation - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2021

Segmenter: Transformer for Semantic Segmentation


Image segmentation is often ambiguous at the level of individual image patches and requires contextual information to reach label consensus. In this paper we introduce Segmenter, a transformer model for semantic segmentation. In contrast to convolution-based methods, our approach allows to model global context already at the first layer and throughout the network. We build on the recent Vision Transformer (ViT) and extend it to semantic segmentation. To do so, we rely on the output embeddings corresponding to image patches and obtain class labels from these embeddings with a point-wise linear decoder or a mask transformer decoder. We leverage models pre-trained for image classification and show that we can fine-tune them on moderate sized datasets available for semantic segmentation. The linear decoder allows to obtain excellent results already, but the performance can be further improved by a mask transformer generating class masks. We conduct an extensive ablation study to show the impact of the different parameters, in particular the performance is better for large models and small patch sizes. Segmenter attains excellent results for semantic segmentation. It outperforms the state of the art on both ADE20K and Pascal Context datasets and is competitive on Cityscapes.
Fichier principal
Vignette du fichier
2105.05633.pdf (6.18 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03481207 , version 1 (15-12-2021)


  • HAL Id : hal-03481207 , version 1


Robin Strudel, Ricardo Garcia, Ivan Laptev, Cordelia Schmid. Segmenter: Transformer for Semantic Segmentation. ICCV 2021 - International Conference on Computer Vision, Oct 2021, Virtual, France. ⟨hal-03481207⟩
130 View
252 Download


Gmail Facebook X LinkedIn More