Výsledky vyhledávání

Report

Envisioning Class Entity Reasoning by Large Language Models for Few-shot Learning

Autor: Liu, Mushui, Wu, Fangtai, Li, Bozheng, Lu, Ziqian, Yu, Yunlong, Li, Xi

Few-shot learning (FSL) aims to recognize new concepts using a limited number of visual samples. Existing approaches attempt to incorporate semantic information into the limited visual data for category understanding. However, these methods often enr

Externí odkaz: http://arxiv.org/abs/2408.12469

Zobrazit plný text záznamu

Report

CM-UNet: Hybrid CNN-Mamba UNet for Remote Sensing Image Semantic Segmentation

Autor: Liu, Mushui, Dan, Jun, Lu, Ziqian, Yu, Yunlong, Li, Yingming, Li, Xi

Due to the large-scale image size and object variations, current CNN-based and Transformer-based approaches for remote sensing image semantic segmentation are suboptimal for capturing the long-range dependency or limited to the complex computational

Externí odkaz: http://arxiv.org/abs/2405.10530

Zobrazit plný text záznamu

Report

SYNC-CLIP: Synthetic Data Make CLIP Generalize Better in Data-Limited Scenarios

Autor: Liu, Mushui, He, Weijie, Lu, Ziqian, Yu, Yunlong

Prompt learning is a powerful technique for transferring Vision-Language Models (VLMs) such as CLIP to downstream tasks. However, the prompt-based methods that are fine-tuned solely with base classes may struggle to generalize to novel classes in ope

Externí odkaz: http://arxiv.org/abs/2312.03805

Zobrazit plný text záznamu

Report

Prompt-based test-time real image dehazing: a novel pipeline

Autor: Chen, Zixuan, He, Zewei, Lu, Ziqian, Sun, Xuecheng, Lu, Zhe-Ming

Existing methods attempt to improve models' generalization ability on real-world hazy images by exploring well-designed training schemes (\eg, CycleGAN, prior loss). However, most of them need very complicated training procedures to achieve satisfact

Externí odkaz: http://arxiv.org/abs/2309.17389

Zobrazit plný text záznamu

Report

Accurate and lightweight dehazing via multi-receptive-field non-local network and novel contrastive regularization

Autor: He, Zewei, Chen, Zixuan, Lu, Ziqian, Sun, Xuecheng, Lu, Zhe-Ming

Recently, deep learning-based methods have dominated image dehazing domain. Although very competitive dehazing performance has been achieved with sophisticated models, effective solutions for extracting useful features are still under-explored. In ad

Externí odkaz: http://arxiv.org/abs/2309.16494

Zobrazit plný text záznamu