paper-with-me

Papers

CLIP-based Synergistic Knowledge Transfer for Text-based Person Retrieval

2023-09-18 · Yating Liu, Yaowei Li, Zimo Liu, Wenming Yang, YaoWei Wang, Qingmin Liao

Text-based Person Retrieval (TPR) aims to retrieve the target person images given a textual query. The primary challenge lies in bridging the substantial gap between vision and language modalities, especially when dealing with limited large-scale datasets. In this paper, we introduce a CLIP-based Synergistic Knowledge Transfer (CSKT) approach for TPR. Specifically, to explore the CLIP's knowledge on input side, we first propose a Bidirectional Prompts Transferring (BPT) module constructed by text-to-image and image-to-text bidirectional prompts and coupling projections. Secondly, Dual Adapters Transferring (DAT) is designed to transfer knowledge on output side of Multi-Head Attention (MHA) in vision and language. This synergistic two-way collaborative mechanism promotes the early-stage feature fusion and efficiently exploits the existing knowledge of CLIP. CSKT outperforms the state-of-the-art approaches across three benchmark datasets when the training parameters merely account for 7.4% of the entire model, demonstrating its remarkable efficiency, effectiveness and generalization.

📄 PDF Abstract BibTeX arXiv:2309.09496

Code (1)

Liu-Yating/CSKT 공식 구현 pytorch

Tasks

Image to textPerson RetrievalRetrievalText based Person RetrievalText-based Person RetrievalTransfer Learning

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
CLIP Contrastive Language-Image Pre-training (CLIP), consisting of a simplified version of ConVIRT trained from scratch, is an efficient method of image representation learning…

Similar Papers 제목 키워드 기반

Connecting Giants: Synergistic Knowledge Transfer of Large Multimodal Models for Few-Shot Learning

2025-10-13 · Hao Tang, Shengfeng He, Jing Qin arxiv

Few-shot learning (FSL) addresses the challenge of classifying novel classes with limited training samples. While some methods leverage semantic knowledge from smaller-scale models to mitigate data scarcity, these approa…

Few-Shot Learning

TF-CLIP: Learning Text-free CLIP for Video-based Person Re-Identification

2023-12-15 · Chenyang Yu, Xuehu Liu, Yingquan Wang, Pingping Zhang 외

Large-scale language-image pre-trained models (e.g., CLIP) have shown superior performances on many cross-modal retrieval tasks. However, the problem of transferring the knowledge learned from such models to video-based …

Cross-Modal RetrievalPerson Re-IdentificationVideo-Based Person Re-Identification

UP-Person: Unified Parameter-Efficient Transfer Learning for Text-based Person Retrieval

2025-04-14 · Yating Liu, Yaowei Li, Xiangyuan Lan, Wenming Yang 외

Text-based Person Retrieval (TPR) as a multi-modal task, which aims to retrieve the target person from a pool of candidate images given a text description, has recently garnered considerable attention due to the progress…

Person RetrievalRetrievalText based Person RetrievalText-based Person Retrieval+1

Gradient-Attention Guided Dual-Masking Synergetic Framework for Robust Text-based Person Retrieval

2025-09-11 · Tianlu Zheng, Yifan Zhang, Xiang An, Ziyong Feng 외 arxiv

Although Contrastive Language-Image Pre-training (CLIP) exhibits strong performance across diverse vision tasks, its application to person representation learning faces two critical challenges: (i) the scarcity of large-…

Representation LearningContrastive LearningPerson Retrieval

Hierarchical Semantic Tree Anchoring for CLIP-Based Class-Incremental Learning

2025-11-19 · Tao Hu, Lan Li, Zhen-Hao Xie, Da-Wei Zhou arxiv

Class-Incremental Learning (CIL) enables models to learn new classes continually while preserving past knowledge. Recently, vision-language models like CLIP offer transferable features via multi-modal pre-training, makin…

class-incremental learning