English
Related papers

Related papers: Self-Taught Cross-Domain Few-Shot Learning with We…

200 papers

Just like other few-shot learning problems, few-shot segmentation aims to minimize the need for manual annotation, which is particularly costly in segmentation tasks. Even though the few-shot setting reduces this cost for novel test…

Computer Vision and Pattern Recognition · Computer Science 2021-11-04 Mustafa Sercan Amac , Ahmet Sencan , Orhun Bugra Baran , Nazli Ikizler-Cinbis , Ramazan Gokberk Cinbis

Vision-language foundation models have shown promising zero-shot generalization for Cross-Domain Few-Shot Object Detection (CD-FSOD). However, they face two critical challenges in fine-tuning: insufficient support set utilization due to…

Computer Vision and Pattern Recognition · Computer Science 2026-05-29 Jiacong Liu , Shu Luo , Yikai Qin , Yaze Zhao , Yongwei Jiang , Yixiong Zou

Few-shot learning (FSL) aims to learn a classifier that can be easily adapted to accommodate new tasks not seen during training, given only a few examples. To handle the limited-data problem in few-shot regimes, recent methods tend to…

Computer Vision and Pattern Recognition · Computer Science 2022-03-21 Yang Liu , Weifeng Zhang , Chao Xiang , Tu Zheng , Deng Cai , Xiaofei He

Few-shot semantic segmentation (FSS) offers immense potential in the field of medical image analysis, enabling accurate object segmentation with limited training data. However, existing FSS techniques heavily rely on annotated semantic…

Computer Vision and Pattern Recognition · Computer Science 2023-07-28 Sanaz Karimijafarbigloo , Reza Azad , Dorit Merhof

Cross-domain few-shot learning (CDFSL) addresses learning problems where knowledge needs to be transferred from one or more source domains into an instance-scarce target domain with an explicitly different distribution. Recently published…

Computer Vision and Pattern Recognition · Computer Science 2023-10-26 Hongyu Wang , Eibe Frank , Bernhard Pfahringer , Michael Mayo , Geoffrey Holmes

Few-shot learning aims to build classifiers for new classes from a small number of labeled examples and is commonly facilitated by access to examples from a distinct set of 'base classes'. The difference in data distribution between the…

Computer Vision and Pattern Recognition · Computer Science 2021-04-26 Zitian Chen , Subhransu Maji , Erik Learned-Miller

The ability to incrementally learn new classes from limited samples is crucial to the development of artificial intelligence systems for real clinical application. Although existing incremental learning techniques have attempted to address…

Computer Vision and Pattern Recognition · Computer Science 2023-04-13 Hao Yang , Weijian Huang , Jiarun Liu , Cheng Li , Shanshan Wang

Detecting novel objects from few examples has become an emerging topic in computer vision recently. However, these methods need fully annotated training images to learn new object categories which limits their applicability in real world…

Computer Vision and Pattern Recognition · Computer Science 2021-03-29 Amirreza Shaban , Amir Rahimi , Thalaiyasingam Ajanthan , Byron Boots , Richard Hartley

To mitigate the detection performance drop caused by domain shift, we aim to develop a novel few-shot adaptation approach that requires only a few target domain images with limited bounding box annotations. To this end, we first observe…

Computer Vision and Pattern Recognition · Computer Science 2019-03-25 Tao Wang , Xiaopeng Zhang , Li Yuan , Jiashi Feng

Cross-domain few-shot segmentation (CD-FSS) aims to achieve semantic segmentation in previously unseen domains with a limited number of annotated samples. Although existing CD-FSS models focus on cross-domain feature transformation, relying…

Computer Vision and Pattern Recognition · Computer Science 2023-09-15 Xinyang Huang , Chuang Zhu , Wenkai Chen

Automatic cell segmentation in microscopy images works well with the support of deep neural networks trained with full supervision. Collecting and annotating images, though, is not a sustainable solution for every new microscopy database…

Computer Vision and Pattern Recognition · Computer Science 2020-07-06 Youssef Dawoud , Julia Hornauer , Gustavo Carneiro , Vasileios Belagiannis

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…

Computer Vision and Pattern Recognition · Computer Science 2024-06-28 Yanan Zhang , Chao Zhou , Di Huang

Unsupervised Domain Adaptation (UDA) transfers predictive models from a fully-labeled source domain to an unlabeled target domain. In some applications, however, it is expensive even to collect labels in the source domain, making most…

Computer Vision and Pattern Recognition · Computer Science 2021-04-01 Xiangyu Yue , Zangwei Zheng , Shanghang Zhang , Yang Gao , Trevor Darrell , Kurt Keutzer , Alberto Sangiovanni Vincentelli

Unsupervised domain adaptation aims to train a classification model from the labeled source domain for the unlabeled target domain. Since the data distributions of the two domains are different, the model often performs poorly on the target…

Computer Vision and Pattern Recognition · Computer Science 2022-03-10 Jieren Cheng , Le Liu , Xiangyan Tang , Wenxuan Tu , Boyi Liu , Ke Zhou , Qiaobo Da , Yue Yang

Semi-supervised domain adaptation (SSDA) aims to adapt models trained from a labeled source domain to a different but related target domain, from which unlabeled data and a small set of labeled data are provided. Current methods that treat…

Computer Vision and Pattern Recognition · Computer Science 2021-09-24 Luyu Yang , Yan Wang , Mingfei Gao , Abhinav Shrivastava , Kilian Q. Weinberger , Wei-Lun Chao , Ser-Nam Lim

Self-training is a simple yet effective method for semi-supervised learning, during which pseudo-label selection plays an important role for handling confirmation bias. Despite its popularity, applying self-training to landmark detection…

Computer Vision and Pattern Recognition · Computer Science 2024-09-17 Haibo Jin , Haoxuan Che , Hao Chen

The task of learning a sentiment classification model that adapts well to any target domain, different from the source domain, is a challenging problem. Majority of the existing approaches focus on learning a common representation by…

Machine Learning · Computer Science 2019-12-05 Pratik Kayal , Mayank Singh , Pawan Goyal

The goal of Few-Shot Continual Learning (FSCL) is to incrementally learn novel tasks with limited labeled samples and preserve previous capabilities simultaneously, while current FSCL methods are all for the class-incremental purpose.…

Computer Vision and Pattern Recognition · Computer Science 2023-02-14 Yawen Cui , Zitong Yu , Rizhao Cai , Xun Wang , Alex C. Kot , Li Liu

Domain shift is a well known problem where a model trained on a particular domain (source) does not perform well when exposed to samples from a different domain (target). Unsupervised methods that can adapt to domain shift are highly…

Computer Vision and Pattern Recognition · Computer Science 2021-08-04 Botos Csaba , Xiaojuan Qi , Arslan Chaudhry , Puneet Dokania , Philip Torr

Recent advances of deep learning have achieved remarkable performances in various challenging computer vision tasks. Especially in object localization, deep convolutional neural networks outperform traditional approaches based on extraction…

Computer Vision and Pattern Recognition · Computer Science 2016-02-05 Sangheum Hwang , Hyo-Eun Kim