The exceptionally rapid development of highly flexible, reusable artificial intelligence (AI)
models is likely to usher in newfound capabilities in medicine. We propose a new paradigm …

Recently, the proposed deep multilayer perceptron (MLP) models have stirred up a lot of
interest in the vision community. Historically, the availability of larger datasets combined with …

Designing computationally efficient network architectures remains an ongoing necessity in
computer vision. In this paper, we adapt Mamba, a state-space language model, into …

Abstract This work presents Depth Anything a highly practical solution for robust monocular
depth estimation. Without pursuing novel technical modules we aim to build a simple yet …

We present SegNeXt, a simple convolutional network architecture for semantic
segmentation. Recent transformer-based models have dominated the field of se-mantic …

In unsupervised domain adaptation (UDA), a model trained on source data (eg synthetic) is
adapted to target data (eg real-world) without access to target annotation. Most previous …

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

The current modus operandi in adapting pre-trained models involves updating all the
backbone parameters, ie., full fine-tuning. This paper introduces Visual Prompt Tuning (VPT) …

We revisit large kernel design in modern convolutional neural networks (CNNs). Inspired by
recent advances in vision transformers (ViTs), in this paper, we demonstrate that using a few …

Test-time domain adaptation aims to adapt a source pre-trained model to a target domain
without using any source data. Existing works mainly consider the case where the target …