Related papers: TVT: Transferable Vision Transformer for Unsupervi…

Vision Transformer (ViT) extends the application range of transformers from language processing to computer vision tasks as being an alternative architecture against the existing convolutional neural networks (CNN). Since the…

Unsupervised domain adaptation (UDA) aims to learn transferable representation across domains. Recently a few UDA works have successfully applied Transformer-based methods and achieved state-of-the-art (SOTA) results. However, it remains…

This paper presents an unsupervised domain adaptation (UDA) method for predicting unlabeled target domain data, specific to complex UDA tasks where the domain gap is significant. Mainstream UDA models aim to learn from both domains and…

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…

Transformer, an attention-based encoder-decoder architecture, has not only revolutionized the field of natural language processing (NLP), but has also done some pioneering work in the field of computer vision (CV). Compared to convolutional…

Multi-target unsupervised domain adaptation (UDA) aims to learn a unified model to address the domain shift between multiple target domains. Due to the difficulty of obtaining annotations for dense predictions, it has recently been…

Beyond the complexity of CNNs that require training on large annotated datasets, the domain shift between design and operational data has limited the adoption of CNNs in many real-world applications. For instance, in person…

Expanding visual categorization into a novel domain without the need of extra annotation has been a long-term interest for multimedia intelligence. Previously, this challenge has been approached by unsupervised domain adaptation (UDA).…

Deep perception models have to reliably cope with an open-world setting of domain shifts induced by different geographic regions, sensor properties, mounting positions, and several other reasons. Since covering all domains with annotated…

Vision transformers (ViT) have demonstrated impressive performance across various machine vision problems. These models are based on multi-head self-attention mechanisms that can flexibly attend to a sequence of image patches to encode…

In this paper, we tackle a new problem: how to transfer knowledge from the pre-trained cumbersome yet well-performed CNN-based model to learn a compact Vision Transformer (ViT)-based model while maintaining its learning capacity? Due to the…

Unsupervised Domain Adaptation (UDA) essentially trades a model's performance on a source domain for improving its performance on a target domain. To overcome this, Unsupervised Domain Expansion (UDE) has been introduced, which adapts the…

Prior Unsupervised Domain Adaptation (UDA) methods often aim to train a domain-invariant feature extractor, which may hinder the model from learning sufficiently discriminative features. To tackle this, a line of works based on prompt…

Semantic segmentation is essential for analysing anatomical features in biomedical research, yet a performance gap remains for Vision Transformers (ViTs) in the field, particularly for sparse, fine-structured, and low signal-to-noise…

Video analysis tasks such as action recognition have received increasing research interest with growing applications in fields such as smart healthcare, thanks to the introduction of large-scale datasets and deep learning-based…

Vision Transformers (ViTs) have achieved impressive performance on various vision tasks, yet their generalization under distribution shifts (DS) is rarely understood. In this work, we comprehensively study the out-of-distribution (OOD)…

Unsupervised Domain Adaptation for semantic segmentation has gained immense popularity since it can transfer knowledge from simulation to real (Sim2Real) by largely cutting out the laborious per pixel labeling efforts at real. In this work,…

Continuous Video Domain Adaptation (CVDA) is a scenario where a source model is required to adapt to a series of individually available changing target domains continuously without source data or target supervision. It has wide…

Vision Transformers (ViTs) have demonstrated remarkable capabilities in learning representations, but their performance is compromised when applied to unseen domains. Previous methods either engage in prompt learning during the training…

Transformers have shown superior performance on various vision tasks. Their large receptive field endows Transformer models with higher representation power than their CNN counterparts. Nevertheless, simply enlarging the receptive field…