This work investigates a simple yet powerful adapter for Vision Transformer (ViT). Unlike
recent visual transformers that introduce vision-specific inductive biases into their …

Abstract Universal Image Segmentation is not a new concept. Past attempts to unify image
segmentation include scene parsing, panoptic segmentation, and, more recently, new …

Recent progress in vision Transformers exhibits great success in various tasks driven by the
new spatial modeling mechanism based on dot-product self-attention. In this paper, we …

Image segmentation groups pixels with different semantics, eg, category or instance
membership. Each choice of semantics defines a task. While only the semantics of each task …

Real-world applications have high demands for semantic segmentation methods. Although
semantic segmentation has made remarkable leap-forwards with deep learning, the …

3D scene graphs have recently emerged as a powerful high-level representation of 3D
environments. A 3D scene graph describes the environment as a layered graph where …

Image segmentation is the task of associating pixels in an image with their respective object
class labels. It has a wide range of applications in many industries including healthcare …

Change detection is an important tool for long-term Earth observation missions. It takes bi-
temporal images as input and predicts “where” the change has occurred. Different from other …

Finetuning a pretrained backbone in the encoder part of an image transformer network has
been the traditional approach for the semantic segmentation task. However, such an …

Learning pyramidal feature representations is important for many dense prediction tasks (eg,
object detection, semantic segmentation) that demand multi-scale visual understanding …