Search Results for author: Fang Peng

Found 6 papers, 6 papers with code

OneRef: Unified One-tower Expression Grounding and Segmentation with Mask Referring Modeling

2 code implementations10 Oct 2024 Linhui Xiao, Xiaoshan Yang, Fang Peng, YaoWei Wang, Changsheng Xu

Simultaneously, the current mask visual language modeling (MVLM) fails to capture the nuanced referential relationship between image-text in referring tasks.

Language Modeling Language Modelling

SALI: Short-term Alignment and Long-term Interaction Network for Colonoscopy Video Polyp Segmentation

1 code implementation19 Jun 2024 Qiang Hu, Zhenyu Yi, Ying Zhou, Fang Peng, Mei Liu, Qiang Li, Zhiwei Wang

In this context, we focus on robust video polyp segmentation by enhancing the adjacent feature consistency and rebuilding the reliable polyp representation.

Segmentation Video Polyp Segmentation +2

HiVG: Hierarchical Multimodal Fine-grained Modulation for Visual Grounding

1 code implementation20 Apr 2024 Linhui Xiao, Xiaoshan Yang, Fang Peng, YaoWei Wang, Changsheng Xu

The cross-modal bridge can address the inconsistency between visual features and those required for grounding, and establish a connection between multi-level visual and text features.

cross-modal alignment Visual Grounding

CLIP-VG: Self-paced Curriculum Adapting of CLIP for Visual Grounding

2 code implementations15 May 2023 Linhui Xiao, Xiaoshan Yang, Fang Peng, Ming Yan, YaoWei Wang, Changsheng Xu

In order to utilize vision and language pre-trained models to address the grounding problem, and reasonably take advantage of pseudo-labels, we propose CLIP-VG, a novel method that can conduct self-paced curriculum adapting of CLIP with pseudo-language labels.

Diversity Transfer Learning +1

SgVA-CLIP: Semantic-guided Visual Adapting of Vision-Language Models for Few-shot Image Classification

1 code implementation28 Nov 2022 Fang Peng, Xiaoshan Yang, Linhui Xiao, YaoWei Wang, Changsheng Xu

Although significant progress has been made in few-shot learning, most of existing few-shot image classification methods require supervised pre-training on a large amount of samples of base classes, which limits their generalization ability in real world application.

Few-Shot Image Classification Few-Shot Learning +2

Cannot find the paper you are looking for? You can Submit a new open access paper.