English
Related papers

Related papers: Domain-invariant Prototypes for Semantic Segmentat…

200 papers

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…

Computer Vision and Pattern Recognition · Computer Science 2020-03-03 Umberto Michieli , Matteo Biasetton , Gianluca Agresti , Pietro Zanuttigh

The cost of large scale data collection and annotation often makes the application of machine learning algorithms to new tasks or datasets prohibitively expensive. One approach circumventing this cost is training models on synthetic data…

Computer Vision and Pattern Recognition · Computer Science 2016-08-23 Konstantinos Bousmalis , George Trigeorgis , Nathan Silberman , Dilip Krishnan , Dumitru Erhan

Unsupervised domain adaptation (UDA) and domain generalization (DG) enable machine learning models trained on a source domain to perform well on unlabeled or even unseen target domains. As previous UDA&DG semantic segmentation methods are…

Computer Vision and Pattern Recognition · Computer Science 2023-09-28 Lukas Hoyer , Dengxin Dai , Luc Van Gool

Convolutional neural network-based approaches have achieved remarkable progress in semantic segmentation. However, these approaches heavily rely on annotated data which are labor intensive. To cope with this limitation, automatically…

Computer Vision and Pattern Recognition · Computer Science 2020-07-16 Fei Pan , Inkyu Shin , Francois Rameau , Seokju Lee , In So Kweon

Semantic segmentation has achieved significant advances in recent years. While deep neural networks perform semantic segmentation well, their success rely on pixel level supervision which is expensive and time-consuming. Further, training…

Computer Vision and Pattern Recognition · Computer Science 2020-12-14 Ying Chen , Xu Ouyang , Kaiyue Zhu , Gady Agam

Unsupervised domain adaption (UDA) aims to adapt models learned from a well-annotated source domain to a target domain, where only unlabeled samples are given. Current UDA approaches learn domain-invariant features by aligning source and…

Computer Vision and Pattern Recognition · Computer Science 2022-02-15 Chunjiang Ge , Rui Huang , Mixue Xie , Zihang Lai , Shiji Song , Shuang Li , Gao Huang

Large-scale labeled training datasets have enabled deep neural networks to excel on a wide range of benchmark vision tasks. However, in many applications it is prohibitively expensive or time-consuming to obtain large quantities of labeled…

Computer Vision and Pattern Recognition · Computer Science 2018-03-28 Sicheng Zhao , Bichen Wu , Joseph Gonzalez , Sanjit A. Seshia , Kurt Keutzer

Self-training is a competitive approach in domain adaptive segmentation, which trains the network with the pseudo labels on the target domain. However inevitably, the pseudo labels are noisy and the target features are dispersed due to the…

Computer Vision and Pattern Recognition · Computer Science 2021-01-29 Pan Zhang , Bo Zhang , Ting Zhang , Dong Chen , Yong Wang , Fang Wen

Significant advances have been made towards building accurate automatic segmentation systems for a variety of biomedical applications using machine learning. However, the performance of these systems often degrades when they are applied on…

Generalisation of deep neural networks becomes vulnerable when distribution shifts are encountered between train (source) and test (target) domain data. Few-shot domain adaptation mitigates this issue by adapting deep neural networks…

Computer Vision and Pattern Recognition · Computer Science 2023-08-10 Youssef Dawoud , Gustavo Carneiro , Vasileios Belagiannis

We propose a general framework for unsupervised domain adaptation, which allows deep neural networks trained on a source domain to be tested on a different target domain without requiring any training annotations in the target domain. This…

Computer Vision and Pattern Recognition · Computer Science 2017-12-05 Zak Murez , Soheil Kolouri , David Kriegman , Ravi Ramamoorthi , Kyungnam Kim

Training deep networks for semantic segmentation requires large amounts of labeled training data, which presents a major challenge in practice, as labeling segmentation masks is a highly labor-intensive process. To address this issue, we…

Computer Vision and Pattern Recognition · Computer Science 2021-08-31 Lukas Hoyer , Dengxin Dai , Qin Wang , Yuhua Chen , Luc Van Gool

Domain adaptive semantic segmentation enables robust pixel-wise understanding in real-world driving scenes. Source-free domain adaptation, as a more practical technique, addresses the concerns of data privacy and storage limitations in…

Computer Vision and Pattern Recognition · Computer Science 2024-03-27 Yihong Cao , Hui Zhang , Xiao Lu , Zheng Xiao , Kailun Yang , Yaonan Wang

Unsupervised domain adaption aims to learn a powerful classifier for the target domain given a labeled source data set and an unlabeled target data set. To alleviate the effect of `domain shift', the major challenge in domain adaptation,…

Computer Vision and Pattern Recognition · Computer Science 2018-12-03 Yexun Zhang , Ya Zhang , Yanfeng Wang , Qi Tian

Large-scale labeled training datasets have enabled deep neural networks to excel across a wide range of benchmark vision tasks. However, in many applications, it is prohibitively expensive and time-consuming to obtain large quantities of…

Computer Vision and Pattern Recognition · Computer Science 2020-09-22 Sicheng Zhao , Xiangyu Yue , Shanghang Zhang , Bo Li , Han Zhao , Bichen Wu , Ravi Krishna , Joseph E. Gonzalez , Alberto L. Sangiovanni-Vincentelli , Sanjit A. Seshia , Kurt Keutzer

Learning semantic segmentation models requires a huge amount of pixel-wise labeling. However, labeled data may only be available abundantly in a domain different from the desired target domain, which only has minimal or no annotations. In…

Computer Vision and Pattern Recognition · Computer Science 2020-08-13 Sujoy Paul , Yi-Hsuan Tsai , Samuel Schulter , Amit K. Roy-Chowdhury , Manmohan Chandraker

Performance achievable by modern deep learning approaches are directly related to the amount of data used at training time. Unfortunately, the annotation process is notoriously tedious and expensive, especially for pixel-wise tasks like…

Computer Vision and Pattern Recognition · Computer Science 2018-10-16 Pierluigi Zama Ramirez , Alessio Tonioni , Luigi Di Stefano

Few-shot slot tagging is an emerging research topic in the field of Natural Language Understanding (NLU). With sufficient annotated data from source domains, the key challenge is how to train and adapt the model to another target domain…

Computation and Language · Computer Science 2021-09-14 Zezhong Wang , Hongru Wang , Kwan Wai Chung , Jia Zhu , Gabriel Pui Cheong Fung , Kam-Fai Wong

Unsupervised domain adaptation (DA) has gained substantial interest in semantic segmentation. However, almost all prior arts assume concurrent access to both labeled source and unlabeled target, making them unsuitable for scenarios…

Computer Vision and Pattern Recognition · Computer Science 2022-05-13 Jogendra Nath Kundu , Akshay Kulkarni , Amit Singh , Varun Jampani , R. Venkatesh Babu

Domain adaptive semantic segmentation aims to train a model performing satisfactory pixel-level predictions on the target with only out-of-domain (source) annotations. The conventional solution to this task is to minimize the discrepancy…

Computer Vision and Pattern Recognition · Computer Science 2020-11-03 Guoliang Kang , Yunchao Wei , Yi Yang , Yueting Zhuang , Alexander G. Hauptmann