English
Related papers

Related papers: Unsupervised Domain Adaptation within Deep Foundat…

200 papers

Vision transformers (ViTs) - especially feature foundation models like DINOv2 - learn rich representations useful for many downstream tasks. However, architectural choices (such as positional encoding) can lead to these models displaying…

Computer Vision and Pattern Recognition · Computer Science 2026-03-18 Moritz Pawlowsky , Antonis Vamvakeros , Alexander Weiss , Anja Bielefeld , Samuel J. Cooper , Ronan Docherty

Conventional unsupervised domain adaptation (UDA) studies the knowledge transfer between a limited number of domains. This neglects the more practical scenario where data are distributed in numerous different domains in the real world. The…

Computer Vision and Pattern Recognition · Computer Science 2020-07-21 Xingchao Peng , Yichen Li , Kate Saenko

Face Anti-Spoofing (FAS) remains challenging due to the requirement for robust domain generalization across unseen environments. While recent trends leverage Vision-Language Models (VLMs) for semantic supervision, these multimodal…

Computer Vision and Pattern Recognition · Computer Science 2026-04-22 Mika Feng , Pierre Gallin-Martel , Koichi Ito , Takafumi Aoki

Unsupervised domain adaptation (UDA) aims to transfer knowledge from a labeled source domain to an unlabeled target domain. The most recent UDA methods always resort to adversarial training to yield state-of-the-art results and a dominant…

Computer Vision and Pattern Recognition · Computer Science 2024-04-25 Yahan Li , Yuan Wu

The recent breakthroughs in natural language processing for model pretraining on large quantities of data have opened the way for similar foundation models in computer vision. These models could greatly simplify the use of images in any…

A commercial robot, trained by its manufacturer to recognize a predefined number and type of objects, might be used in many settings, that will in general differ in their illumination conditions, background, type and degree of clutter, and…

Computer Vision and Pattern Recognition · Computer Science 2018-02-27 Gabriele Angeletti , Barbara Caputo , Tatiana Tommasi

Face recognition systems are increasingly used in biometric security for convenience and effectiveness. However, they remain vulnerable to spoofing attacks, where attackers use photos, videos, or masks to impersonate legitimate users. This…

Computer Vision and Pattern Recognition · Computer Science 2024-10-23 Arman Keresh , Pakizar Shamoi

Due to the existence of dataset shifts, the distributions of data acquired from different working conditions show significant differences in real-world industrial applications, which leads to performance degradation of traditional machine…

Signal Processing · Electrical Eng. & Systems 2021-01-28 Huanjie Wang , Jie Tan , Xiwei Bai , Jiechao Yang

Unsupervised domain adaptation is one of the challenging problems in computer vision. This paper presents a novel approach to unsupervised domain adaptations based on the optimal transport-based distance. Our approach allows aligning target…

Computer Vision and Pattern Recognition · Computer Science 2022-05-24 Thanh-Dat Truong , Naga Venkata Sai Raviteja Chappa , Xuan Bac Nguyen , Ngan Le , Ashley Dowling , Khoa Luu

This paper investigates the problem of domain adaptation for diabetic retinopathy (DR) grading. We learn invariant target-domain features by defining a novel self-supervised task based on retinal vessel image reconstructions, inspired by…

Computer Vision and Pattern Recognition · Computer Science 2021-07-21 Duy M. H. Nguyen , Truong T. N. Mai , Ngoc T. T. Than , Alexander Prange , Daniel Sonntag

Selecting or designing an appropriate domain adaptation algorithm for a given problem remains challenging. This paper presents a Transformer model that can provably approximate and opt for domain adaptation methods for a given dataset in…

Machine Learning · Computer Science 2024-05-28 Ryuichiro Hataya , Kota Matsui , Masaaki Imaizumi

We propose a method to infer domain-specific models such as classifiers for unseen domains, from which no data are given in the training phase, without domain semantic descriptors. When training and test distributions are different,…

Machine Learning · Statistics 2018-07-10 Atsutoshi Kumagai , Tomoharu Iwata

Foundation models have advanced computer vision by enabling strong performance across diverse tasks through large-scale pretraining and supervised fine-tuning. However, they may underperform in domains with distribution shifts and scarce…

Computer Vision and Pattern Recognition · Computer Science 2025-10-27 Jesimon Barreto , Carlos Caetano , André Araujo , William Robson Schwartz

Recently, cross domain transfer has been applied for unsupervised image restoration tasks. However, directly applying existing frameworks would lead to domain-shift problems in translated images due to lack of effective supervision.…

Computer Vision and Pattern Recognition · Computer Science 2020-03-31 Wenchao Du , Hu Chen , Hongyu Yang

In this paper, we address the problem of unsupervised Domain Adaptation. The need for such an adaptation arises when the distribution of the target data differs from that which is used to develop the model and the ground truth information…

Machine Learning · Computer Science 2022-10-04 Siddharth Roheda , Ashkan Panahi , Hamid Krim

We study the use of deep features extracted from a pretrained Vision Transformer (ViT) as dense visual descriptors. We observe and empirically demonstrate that such features, when extractedfrom a self-supervised ViT model (DINO-ViT),…

Computer Vision and Pattern Recognition · Computer Science 2022-10-18 Shir Amir , Yossi Gandelsman , Shai Bagon , Tali Dekel

Deep learning-based object reconstruction algorithms have shown remarkable improvements over classical methods. However, supervised learning based methods perform poorly when the training data and the test data have different distributions.…

Computer Vision and Pattern Recognition · Computer Science 2021-08-26 Brandon Leung , Siddharth Singh , Arik Horodniceanu

General-purpose pre-trained models ("foundation models") have enabled practitioners to produce generalizable solutions for individual machine learning problems with datasets that are significantly smaller than those required for learning…

Robotics · Computer Science 2023-10-25 Dhruv Shah , Ajay Sridhar , Nitish Dashora , Kyle Stachowicz , Kevin Black , Noriaki Hirose , Sergey Levine

End-to-end learning methods have achieved impressive results in many areas of computer vision. At the same time, these methods still suffer from a degradation in performance when testing on new datasets that stem from a different…

Computer Vision and Pattern Recognition · Computer Science 2016-03-24 Rahaf Aljundi , Tinne Tuytelaars

Unsupervised domain adaptation (UDA) aims to transfer and adapt knowledge from a labeled source domain to an unlabeled target domain. Traditionally, subspace-based methods form an important class of solutions to this problem. Despite their…

Machine Learning · Computer Science 2022-01-07 Kowshik Thopalli , Jayaraman J Thiagarajan , Rushil Anirudh , Pavan K Turaga