中文
相关论文

相关论文: SWAT: Sliding Window Adversarial Training for Grad…

200 篇论文

In classification tasks, the classification accuracy diminishes when the data is gathered in different domains. To address this problem, in this paper, we investigate several adversarial models for domain adaptation (DA) and their effect on…

声音 · 计算机科学 2023-09-08 Stanisław Kacprzak , Konrad Kowalczyk

In many practical applications, it is often difficult and expensive to obtain enough large-scale labeled data to train deep neural networks to their full capability. Therefore, transferring the learned knowledge from a separate, labeled…

机器学习 · 计算机科学 2020-02-28 Sicheng Zhao , Bo Li , Colorado Reed , Pengfei Xu , Kurt Keutzer

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…

计算机视觉与模式识别 · 计算机科学 2023-05-09 Jun Kataoka , Hyunsoo Yoon

Visual domain adaptation aims to learn discriminative and domain-invariant representation for an unlabeled target domain by leveraging knowledge from a labeled source domain. Partial domain adaptation (PDA) is a general and practical…

计算机视觉与模式识别 · 计算机科学 2025-05-06 Yi-Ming Zhai , Chuan-Xian Ren , Hong Yan

Visual Domain Adaptation is a problem of immense importance in computer vision. Previous approaches showcase the inability of even deep neural networks to learn informative representations across domain shift. This problem is more severe…

计算机视觉与模式识别 · 计算机科学 2018-04-03 Swami Sankaranarayanan , Yogesh Balaji , Arpit Jain , Ser Nam Lim , Rama Chellappa

Extensive Unsupervised Domain Adaptation (UDA) studies have shown great success in practice by learning transferable representations across a labeled source domain and an unlabeled target domain with deep models. However, previous works…

机器学习 · 计算机科学 2021-09-03 Muhammad Awais , Fengwei Zhou , Hang Xu , Lanqing Hong , Ping Luo , Sung-Ho Bae , Zhenguo Li

Unsupervised domain adaptation (UDA) enables knowledge transfer from the labelled source domain to the unlabeled target domain by reducing the cross-domain discrepancy. However, most of the studies were based on direct adaptation from the…

计算机视觉与模式识别 · 计算机科学 2022-02-22 Qiuhao Zeng , Tianze Luo , Boyu Wang

End-to-end automatic speech recognition (ASR) usually suffers from performance degradation when applied to a new domain due to domain shift. Unsupervised domain adaptation (UDA) aims to improve the performance on the unlabeled target domain…

计算与语言 · 计算机科学 2023-02-23 Jiaming Zhou , Shiwan Zhao , Ning Jiang , Guoqing Zhao , Yong Qin

Unsupervised Domain Adaptation (UDA) makes predictions for the target domain data while manual annotations are only available in the source domain. Previous methods minimize the domain discrepancy neglecting the class information, which may…

计算机视觉与模式识别 · 计算机科学 2019-04-12 Guoliang Kang , Lu Jiang , Yi Yang , Alexander G Hauptmann

Due to the numerous potential applications in visual surveillance and nighttime driving, recognizing human action in low-light conditions remains a difficult problem in computer vision. Existing methods separate action recognition and dark…

计算机视觉与模式识别 · 计算机科学 2022-11-01 Anwaar Ulhaq

Unsupervised Domain Adaptation (UDA) is essential for enabling semantic segmentation in new domains without requiring costly pixel-wise annotations. State-of-the-art (SOTA) UDA methods primarily use self-training with architecturally…

计算机视觉与模式识别 · 计算机科学 2025-04-15 Beomseok Kang , Niluthpol Chowdhury Mithun , Abhinav Rajvanshi , Han-Pang Chiu , Supun Samarasekera

Existing 3D object detection suffers from expensive annotation costs and poor transferability to unknown data due to the domain gap, Unsupervised Domain Adaptation (UDA) aims to generalize detection models trained in labeled source domains…

计算机视觉与模式识别 · 计算机科学 2024-06-28 Yanan Zhang , Chao Zhou , Di Huang

Domain Adaptation (DA) has recently received significant attention due to its potential to adapt a learning model across source and target domains with mismatched distributions. Since DA methods rely exclusively on the given source and…

机器学习 · 统计学 2022-11-01 Akram S. Awad , George K. Atia

Unsupervised domain adaptation (UDA) transfers knowledge from a label-rich source domain to a fully-unlabeled target domain. To tackle this task, recent approaches resort to discriminative domain transfer in virtue of pseudo-labels to…

计算机视觉与模式识别 · 计算机科学 2019-05-21 Chaoqi Chen , Weiping Xie , Wenbing Huang , Yu Rong , Xinghao Ding , Yue Huang , Tingyang Xu , Junzhou Huang

Robust Unsupervised Domain Adaptation (RoUDA) aims to achieve not only clean but also robust cross-domain knowledge transfer from a labeled source domain to an unlabeled target domain. A number of works have been conducted by directly…

计算机视觉与模式识别 · 计算机科学 2024-06-21 Jia-Li Yin , Haoyuan Zheng , Ximeng Liu

In this work, we explore the usage of the Frequency Transformation for reducing the domain shift between the source and target domain (e.g., synthetic image and real image respectively) towards solving the Domain Adaptation task. Most of…

计算机视觉与模式识别 · 计算机科学 2024-07-30 Vikash Kumar , Himanshu Patil , Rohit Lal , Anirban Chakraborty

The main progress for action segmentation comes from densely-annotated data for fully-supervised learning. Since manual annotation for frame-level actions is time-consuming and challenging, we propose to exploit auxiliary unlabeled videos,…

计算机视觉与模式识别 · 计算机科学 2021-04-19 Min-Hung Chen , Baopu Li , Yingze Bao , Ghassan AlRegib

Fine-grained action recognition datasets exhibit environmental bias, where multiple video sequences are captured from a limited number of environments. Training a model in one environment and deploying in another results in a drop in…

计算机视觉与模式识别 · 计算机科学 2020-03-20 Jonathan Munro , Dima Damen

In this technical report, we present our submission to the VisDA Challenge in ECCV 2020 and we achieved one of the top-performing results on the leaderboard. Our solution is based on Structured Domain Adaptation (SDA) and Mutual…

计算机视觉与模式识别 · 计算机科学 2020-08-25 Yixiao Ge , Shijie Yu , Dapeng Chen

Unsupervised sim-to-real domain adaptation (UDA) for semantic segmentation aims to improve the real-world test performance of a model trained on simulated data. It can save the cost of manually labeling data in real-world applications such…

计算机视觉与模式识别 · 计算机科学 2022-12-15 Rui Gong , Qin Wang , Dengxin Dai , Luc Van Gool