Related papers: Vision Transformer-based Adversarial Domain Adapta…

Deep learning techniques have been widely used in autonomous driving systems for the semantic understanding of urban scenes. However, they need a huge amount of labeled data for training, which is difficult and expensive to acquire. A…

Recent advancements in keypoint detection and descriptor extraction have shown impressive performance in local feature learning tasks. However, existing methods generally exhibit suboptimal performance under extreme conditions such as…

Pretraining Vision Transformers (ViTs) has achieved great success in visual recognition. A following scenario is to adapt a ViT to various image and video recognition tasks. The adaptation is challenging because of heavy computation and…

Unsupervised Domain Adaptation (UDA) refers to the method that utilizes annotated source domain data and unlabeled target domain data to train a model capable of generalizing to the target domain data. Domain discrepancy leads to a…

Vision Transformers (ViTs) have become prominent models for solving various vision tasks. However, the interpretability of ViTs has not kept pace with their promising performance. While there has been a surge of interest in developing {\it…

Unsupervised domain adaptation (UDA) plays a crucial role in object detection when adapting a source-trained detector to a target domain without annotated data. In this paper, we propose a novel and effective four-step UDA approach that…

Unsupervised Domain Adaptation (UDA) aims to adapt the model trained on the labeled source domain to an unlabeled target domain. In this paper, we present Prototypical Contrast Adaptation (ProCA), a simple and efficient contrastive learning…

Visual recognition models are not invariant to viewpoint changes in the 3D world, as different viewing directions can dramatically affect the predictions given the same object. Although many efforts have been devoted to making neural…

In this work, we address the task of unsupervised domain adaptation (UDA) for semantic segmentation in presence of multiple target domains: The objective is to train a single model that can handle all these domains at test time. Such a…

As a special type of transformer, Vision Transformers (ViTs) are used to various computer vision applications (CV), such as image recognition. There are several potential problems with convolutional neural networks (CNNs) that can be solved…

Unsupervised domain adaptation (UDA) aims to transfer knowledge learned from a labeled source domain to a different unlabeled target domain. Most existing UDA methods focus on learning domain-invariant feature representation, either from…

In this paper, we ask whether Vision Transformers (ViTs) can serve as an underlying architecture for improving the adversarial robustness of machine learning models against evasion attacks. While earlier works have focused on improving…

Vision Transformer (ViT) is becoming more popular in image processing. Specifically, we investigate the effectiveness of test-time adaptation (TTA) on ViT, a technique that has emerged to correct its prediction during test-time by itself.…

Unsupervised domain adaptation (UDA) aims to transfer knowledge learned from a fully-labeled source domain to a different unlabeled target domain. Most existing UDA methods learn domain-invariant feature representations by minimizing…

Deep learning frameworks allowed for a remarkable advancement in semantic segmentation, but the data hungry nature of convolutional networks has rapidly raised the demand for adaptation techniques able to transfer learned knowledge from…

The quality of patient care associated with diagnostic radiology is proportionate to a physician workload. Segmentation is a fundamental limiting precursor to both diagnostic and therapeutic procedures. Advances in machine learning (ML) aim…

Vision Transformers (ViT) have recently emerged as a powerful alternative to convolutional networks (CNNs). Although hybrid models attempt to bridge the gap between these two architectures, the self-attention layers they rely on induce a…

The diversity of retinal imaging devices poses a significant challenge: domain shift, which leads to performance degradation when applying the deep learning models trained on one domain to new testing domains. In this paper, we propose a…

A source model trained on source data and a target model learned through unsupervised domain adaptation (UDA) usually encode different knowledge. To understand the adaptation process, we portray their knowledge difference with image…

Domain adaption (DA) allows machine learning methods trained on data sampled from one distribution to be applied to data sampled from another. It is thus of great practical importance to the application of such methods. Despite the fact…