Cover Image

Aligning Information Capacity Between Vision and Language via Dense-to-Sparse Feature Distillation for Image-Text Matching

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liu, Yang, Feng, Wentao, Liu, Zhuoyao, Huang, Shudong, Lv, Jiancheng
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

PCSR: Pseudo-label Consistency-Guided Sample Refinement for Noisy Correspondence Learning
by: Liu, Zhuoyao, et al.
Published: (2025)

Asymmetric Visual Semantic Embedding Framework for Efficient Vision-Language Alignment
by: Liu, Yang, et al.
Published: (2025)

Dual Prompt Learning for Adapting Vision-Language Models to Downstream Image-Text Retrieval
by: Wang, Yifan, et al.
Published: (2025)

Mind the Gap: Aligning Vision Foundation Models to Image Feature Matching
by: Liu, Yuhan, et al.
Published: (2025)

DRKF: Distilled Rotated Kernel Fusion for Efficient Rotation Invariant Descriptors in Local Feature Matching
by: Huang, Ranran, et al.
Published: (2022)

CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction
by: Wu, Size, et al.
Published: (2023)

A Dense Reward View on Aligning Text-to-Image Diffusion with Preference
by: Yang, Shentao, et al.
Published: (2024)

Knowledge Distillation for Underwater Feature Extraction and Matching via GAN-synthesized Images
by: Yang, Jinghe, et al.
Published: (2025)

T-REN: Learning Text-Aligned Region Tokens Improves Dense Vision-Language Alignment and Scalability
by: Khosla, Savya, et al.
Published: (2026)

DenseGRPO: From Sparse to Dense Reward for Flow Matching Model Alignment
by: Deng, Haoyou, et al.
Published: (2026)

Towards Lossless Dataset Distillation via Difficulty-Aligned Trajectory Matching
by: Guo, Ziyao, et al.
Published: (2023)

Efficient LoFTR: Semi-Dense Local Feature Matching with Sparse-Like Speed
by: Wang, Yifan, et al.
Published: (2024)

ViT-CoMer: Vision Transformer with Convolutional Multi-scale Feature Interaction for Dense Predictions
by: Xia, Chunlong, et al.
Published: (2024)

LEAF: Latent Diffusion with Efficient Encoder Distillation for Aligned Features in Medical Image Segmentation
by: Huang, Qilin, et al.
Published: (2025)

CoMat: Aligning Text-to-Image Diffusion Model with Image-to-Text Concept Matching
by: Jiang, Dongzhi, et al.
Published: (2024)

AME: Aligned Manifold Entropy for Robust Vision-Language Distillation
by: Cao, Guiming, et al.
Published: (2025)

An Empirical Study of Parameter Efficient Fine-tuning on Vision-Language Pre-train Model
by: Tian, Yuxin, et al.
Published: (2024)

EAVL: Explicitly Align Vision and Language for Referring Image Segmentation
by: Yan, Yichen, et al.
Published: (2023)

Learning Dense Feature Matching via Lifting Single 2D Image to 3D Space
by: Liang, Yingping, et al.
Published: (2025)

Tag2Text: Guiding Vision-Language Model via Image Tagging
by: Huang, Xinyu, et al.
Published: (2023)

GPT4Motion: Scripting Physical Motions in Text-to-Video Generation via Blender-Oriented GPT Planning
by: Lv, Jiaxi, et al.
Published: (2023)

RoMa: Robust Dense Feature Matching
by: Edstedt, Johan, et al.
Published: (2023)

HomoMatcher: Dense Feature Matching Results with Semi-Dense Efficiency by Homography Estimation
by: Wang, Xiaolong, et al.
Published: (2024)

Align-KD: Distilling Cross-Modal Alignment Knowledge for Mobile Vision-Language Model
by: Feng, Qianhan, et al.
Published: (2024)

Vision Remember: Recovering Visual Information in Efficient LVLM with Vision Feature Resampling
by: Feng, Ze, et al.
Published: (2025)

Examining Vision Language Models through Multi-dimensional Experiments with Vision and Text Features
by: Sengupta, Saurav, et al.
Published: (2025)

PriorCLIP: Visual Prior Guided Vision-Language Model for Remote Sensing Image-Text Retrieval
by: Pan, Jiancheng, et al.
Published: (2024)

DOMR: Establishing Cross-View Segmentation via Dense Object Matching
by: Liao, Jitong, et al.
Published: (2025)

Latent Fingerprint Matching via Dense Minutia Descriptor
by: Pan, Zhiyu, et al.
Published: (2024)

Distilling Cross-Modal Knowledge via Feature Disentanglement
by: Liu, Junhong, et al.
Published: (2025)

CFDNet: A Generalizable Foggy Stereo Matching Network with Contrastive Feature Distillation
by: Liu, Zihua, et al.
Published: (2024)

Training-free Dense-Aligned Diffusion Guidance for Modular Conditional Image Synthesis
by: Wang, Zixuan, et al.
Published: (2025)

DistillMatch: Leveraging Knowledge Distillation from Vision Foundation Model for Multimodal Image Matching
by: Yang, Meng, et al.
Published: (2025)

Multimodal Distribution Matching for Vision-Language Dataset Distillation
by: Jeong, Jongoh, et al.
Published: (2026)

MiniDrive: More Efficient Vision-Language Models with Multi-Level 2D Features as Text Tokens for Autonomous Driving
by: Zhang, Enming, et al.
Published: (2024)

OTTER: A Vision-Language-Action Model with Text-Aware Visual Feature Extraction
by: Huang, Huang, et al.
Published: (2025)

Aligning What Vision-Language Models See and Perceive with Adaptive Information Flow
by: Liu, Chengxin, et al.
Published: (2026)

TAMISeg: Text-Aligned Multi-scale Medical Image Segmentation with Semantic Encoder Distillation
by: Gao, Qiang, et al.
Published: (2026)

3D Vision and Language Pretraining with Large-Scale Synthetic Data
by: Yang, Dejie, et al.
Published: (2024)

SynMatch: Rethinking Consistency in Medical Image Segmentation with Sparse Annotations
by: Shen, Zhiqiang, et al.
Published: (2025)