中文
相关论文

相关论文: Addressing Exacerbated Attention Sink for Source-F…

200 篇论文

Source-Free Cross-Domain Few-Shot Learning (SF-CDFSL) focuses on fine-tuning with limited training data from target domains (e.g., medical or satellite images), where Vision-Language Models (VLMs) such as CLIP and SigLIP have shown…

计算机视觉与模式识别 · 计算机科学 2026-03-17 Zhenyu Zhang , Yixiong Zou , Yuhua Li , Ruixuan Li , Guangyao Chen

Cross-Domain Few-Shot Learning (CDFSL) aims to adapt large-scale pretrained models to specialized target domains with limited samples, yet the few-shot fine-tuning of vision-language models like CLIP remains underexplored. By establishing…

计算机视觉与模式识别 · 计算机科学 2026-05-13 Yaze Zhao , Yicong Liu , Yixiong Zou , Yuhua Li , Ruixuan Li

Cross-Domain Few-Shot Learning (CDFSL) adapts models trained with large-scale general data (source domain) to downstream target domains with only scarce training data, where the research on vision-language models (e.g., CLIP) is still in…

计算机视觉与模式识别 · 计算机科学 2026-03-24 Yaze Zhao , Yixiong Zou , Yuhua Li , Ruixuan Li

Vision-Language Models (VLMs) such as CLIP demonstrate strong zero-shot generalization, but their performance significantly degrades in cross-domain scenarios with scarce target-domain training data (Cross-Domain Few-Shot Learning, CDFSL).…

计算机视觉与模式识别 · 计算机科学 2026-05-29 Shuai Yi , Yixiong Zou , Yuhua Li , Ruixuan Li

While deep learning excels in computer vision tasks with abundant labeled data, its performance diminishes significantly in scenarios with limited labeled samples. To address this, Few-shot learning (FSL) enables models to perform the…

计算机视觉与模式识别 · 计算机科学 2025-02-19 Huali Xu , Shuaifeng Zhi , Shuzhou Sun , Vishal M. Patel , Li Liu

Cross-domain few-shot learning (CD-FSL), where there are few target samples under extreme differences between source and target domains, has recently attracted huge attention. Recent studies on CD-FSL generally focus on transfer learning…

计算机视觉与模式识别 · 计算机科学 2022-09-20 Jaehoon Oh , Sungnyun Kim , Namgyu Ho , Jin-Hwa Kim , Hwanjun Song , Se-Young Yun

Cross-domain few-shot learning (CDFSL) aims to transfer knowledge from a data-sufficient source domain to data-scarce target domains. Although Vision Transformer (ViT) has shown superior capability in many vision tasks, its transferability…

计算机视觉与模式识别 · 计算机科学 2025-06-04 Shuai Yi , Yixiong Zou , Yuhua Li , Ruixuan Li

Few-shot video action recognition is an effective approach to recognizing new categories with only a few labeled examples, thereby reducing the challenges associated with collecting and annotating large-scale video datasets. Existing…

计算机视觉与模式识别 · 计算机科学 2023-09-18 Sarinda Samarasinghe , Mamshad Nayeem Rizve , Navid Kardan , Mubarak Shah

Cross-domain few-shot learning (CDFSL) aims to acquire knowledge from limited training data in the target domain by leveraging prior knowledge transferred from source domains with abundant training samples. CDFSL faces challenges in…

计算机视觉与模式识别 · 计算机科学 2024-04-22 Yixiong Zou , Yicong Liu , Yiman Hu , Yuhua Li , Ruixuan Li

Prompt tuning, which involves training a small set of parameters, effectively enhances the pre-trained Vision-Language Models (VLMs) to downstream tasks. However, they often come at the cost of flexibility and adaptability when the tuned…

计算机视觉与模式识别 · 计算机科学 2024-07-08 Mushui Liu , Bozheng Li , Yunlong Yu

A recent study finds that existing few-shot learning methods, trained on the source domain, fail to generalize to the novel target domain when a domain gap is observed. This motivates the task of Cross-Domain Few-Shot Learning (CD-FSL). In…

计算机视觉与模式识别 · 计算机科学 2022-11-30 Yuqian Fu , Yanwei Fu , Yu-Gang Jiang

Few-Shot Learning (FSL) has attracted growing attention in computer vision due to its capability in model training without the need for excessive data. FSL is challenging because the training and testing categories (the base vs. novel sets)…

计算机视觉与模式识别 · 计算机科学 2022-12-14 Ying-Yu Chen , Jun-Wei Hsieh , Ming-Ching Chang

Cross-domain few-shot object detection (CD-FSOD) aims to adapt pretrained detectors from a source domain to target domains with limited annotations, suffering from severe domain shifts and data scarcity problems. In this work, we find a…

计算机视觉与模式识别 · 计算机科学 2026-03-20 Yongwei Jiang , Yixiong Zou , Yuhua Li , Ruixuan Li

Few-shot class-incremental learning (FSCIL) presents a core challenge in continual learning, requiring models to rapidly adapt to new classes with very limited samples while mitigating catastrophic forgetting. Recent prompt-based methods,…

计算机视觉与模式识别 · 计算机科学 2026-01-26 Shuai Huang , Xuhan Lin , Yuwu Lu

Existing few-shot learning (FSL) methods usually assume base classes and novel classes are from the same domain (in-domain setting). However, in practice, it may be infeasible to collect sufficient training samples for some special domains…

计算机视觉与模式识别 · 计算机科学 2021-11-02 Yixiong Zou , Shanghang Zhang , JianPeng Yu , Yonghong Tian , José M. F. Moura

Source-Free Cross-Domain Few-Shot Learning (SF-CDFSL) focuses on fine-tuning with limited training data from target domains (e.g., medical or satellite images), where CLIP has recently shown promising results due to its generalizability to…

人工智能 · 计算机科学 2026-03-06 Zhenyu Zhang , Guangyao Chen , Yixiong Zou , Yuhua Li , Ruixuan Li

Vision Transformer (ViT) has achieved remarkable success due to its large-scale pretraining on general domains, but it still faces challenges when applying it to downstream distant domains that have only scarce training data, which gives…

计算机视觉与模式识别 · 计算机科学 2025-06-04 Shuai Yi , Yixiong Zou , Yuhua Li , Ruixuan Li

Cross-domain few-shot learning (CD-FSL) has drawn increasing attention for handling large differences between the source and target domains--an important concern in real-world scenarios. To overcome these large differences, recent works…

机器学习 · 计算机科学 2022-10-13 Jaehoon Oh , Sungnyun Kim , Namgyu Ho , Jin-Hwa Kim , Hwanjun Song , Se-Young Yun

The domain shift between the source and target domain is the main challenge in Cross-Domain Few-Shot Learning (CD-FSL). However, the target domain is absolutely unknown during the training on the source domain, which results in lacking…

计算机视觉与模式识别 · 计算机科学 2021-09-06 Xiyao Liu , Zhong Ji , Yanwei Pang , Zhongfei Zhang

Cross-Domain Few-Shot Learning (CDFSL) endeavors to transfer generalized knowledge from the source domain to target domains using only a minimal amount of training data, which faces a triplet of learning challenges in the meantime, i.e.,…

计算机视觉与模式识别 · 计算机科学 2025-11-19 Tong Zhang , Yifan Zhao , Liangyu Wang , Jia Li
‹ 上一页 1 2 3 10 下一页 ›