Image segmentation, which has become a research hotspot in the field of image processing
and computer vision, refers to the process of dividing an image into meaningful and non …

Humans can naturally and effectively find salient regions in complex scenes. Motivated by
this observation, attention mechanisms were introduced into computer vision with the aim of …

Although perception systems have made remarkable advancements in recent years they still
rely on explicit human instruction or pre-defined categories to identify the target objects …

Using light-weight architectures or reasoning on low-resolution images, recent methods
realize very fast scene parsing, even running at more than 100 FPS on a single GPU …

Large, pretrained models are commonly finetuned with imagery that is heavily augmented to
mimic different conditions and scales, with the resulting models used for various tasks with …

Unsupervised pre-training methods for large vision models have shown to enhance
performance on downstream supervised tasks. Develo** similar techniques for satellite …

Visual segmentation seeks to partition images, video frames, or point clouds into multiple
segments or groups. This technique has numerous real-world applications, such as …

Prevalent semantic segmentation solutions, despite their different network designs (FCN
based or attention based) and mask decoding strategies (parametric softmax based or pixel …

Unsupervised domain adaptation (UDA) aims to adapt a model trained on the source
domain (eg synthetic data) to the target domain (eg real-world data) without requiring further …

We present SegFormer, a simple, efficient yet powerful semantic segmentation framework
which unifies Transformers with lightweight multilayer perceptron (MLP) decoders …