paper-with-me

홈 › Papers

Low-Rank Similarity Mining for Multimodal Dataset Distillation

2024-06-06 · Yue Xu, Zhilin Lin, Yusong Qiu, Cewu Lu, Yong-Lu Li

Though dataset distillation has witnessed rapid development in recent years, the distillation of multimodal data, e.g., image-text pairs, poses unique and under-explored challenges. Unlike unimodal data, image-text contrastive learning (ITC) data lack inherent categorization and should instead place greater emphasis on modality correspondence. In this work, we propose Low-Rank Similarity Mining (LoRS) for multimodal dataset distillation, that concurrently distills a ground truth similarity matrix with image-text pairs, and leverages low-rank factorization for efficiency and scalability. The proposed approach brings significant improvement to the existing algorithms, marking a significant contribution to the field of visual-language dataset distillation. We advocate adopting LoRS as a foundational synthetic data setup for image-text dataset distillation. Our code is available at https://github.com/silicx/LoRS_Distill.

📄 PDF Abstract BibTeX arXiv:2406.03793

Code (1)

silicx/lors_distill 공식 구현 pytorch

Tasks

Contrastive LearningDataset Distillation

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음

Similar Papers 제목 키워드 기반

Unified Knowledge Distillation Framework: Fine-Grained Alignment and Geometric Relationship Preservation for Deep Face Recognition

2025-08-15 · Durgesh Mishra, Rishabh Uikey arxiv

Knowledge Distillation is crucial for optimizing face recognition models for deployment in computationally limited settings, such as edge devices. Traditional KD methods, such as Raw L2 Feature Distillation or Feature Co…

Knowledge DistillationFace Recognition

DALR: Dual-level Alignment Learning for Multimodal Sentence Representation Learning

2025-06-26 · Kang He, Yuzhe Ding. Haining Wang, Fei Li, Chong Teng 외

Previous multimodal sentence representation learning methods have achieved impressive performance. However, most approaches focus on aligning images and text at a coarse level, facing two critical challenges:cross-modal …

cross-modal alignmentRepresentation LearningSemantic SimilaritySemantic Textual Similarity+2

Rank-Aware Hyperbolic Alignment for Vision-Language Dataset Distillation

2026-06-28 · Jongoh Jeong, Sun-Kyung Lee, Kuk-Jin Yoon hf

Vision-language dataset distillation (VLDD) compresses a large image-text paired dataset into a small set of synthetic pairs that can efficiently train contrastive vision-language models under strict data and compute bud…

Cross-Modal Retrieval

MICIK: MIning Cross-Layer Inherent Similarity Knowledge for Deep Model Compression

2019-02-03 · Jie Zhang, Xiaolong Wang, Dawei Li, Shalini Ghosh 외

State-of-the-art deep model compression methods exploit the low-rank approximation and sparsity pruning to remove redundant parameters from a learned hidden layer. However, they process each hidden layer individually whi…

Knowledge DistillationModel Compression

UniME-V2: MLLM-as-a-Judge for Universal Multimodal Embedding Learning

2025-10-15 · Tiancheng Gu, Kaicheng Yang, Kaichen Zhang, Xiang An 외 arxiv

Universal multimodal embedding models are foundational to various tasks. Existing approaches typically employ in-batch negative mining by measuring the similarity of query-candidate pairs. However, these methods often st…

Representation Learning