paper-with-me

홈 › Papers

D4C: Data-Free Quantization for Contrastive Language-Image Pre-training Models

2025-11-19 · Wenlun Zhang, Yunshan Zhong, Zihao Ding, Xinyu Li, Kentaro Yoshioka arxiv

Data-Free Quantization (DFQ) offers a practical solution for model compression without requiring access to real data, making it particularly attractive in privacy-sensitive scenarios. While DFQ has shown promise for unimodal models, its extension to Vision-Language Models such as Contrastive Language-Image Pre-training (CLIP) models remains underexplored. In this work, we reveal that directly applying existing DFQ techniques to CLIP results in substantial performance degradation due to two key limitations: insufficient semantic content and low intra-image diversity in synthesized samples. To tackle these challenges, we propose D4C, the first DFQ framework tailored for CLIP. D4C synthesizes semantically rich and structurally diverse pseudo images through three key components: 1) Prompt-Guided Semantic Injection aligns generated images with real-world semantics using text prompts; 2) Structural Contrastive Generation reproduces compositional structures of natural images by leveraging foreground-background contrastive synthesis; and 3) Perturbation-Aware Enhancement applies controlled perturbations to improve sample diversity and robustness. These components jointly empower D4C to synthesize images that are both semantically informative and structurally diverse, effectively bridging the performance gap of DFQ on CLIP. Extensive experiments validate the effectiveness of D4C, showing significant performance improvements on various bit-widths and models.

📄 PDF Abstract BibTeX arXiv:2511.15411

Code (0)

등록된 구현이 없습니다.

Tasks

Model Compression

Similar Papers 제목 키워드 기반

CLAMP-ViT: Contrastive Data-Free Learning for Adaptive Post-Training Quantization of ViTs

2024-07-07 · Akshat Ramachandran, Souvik Kundu, Tushar Krishna

We present CLAMP-ViT, a data-free post-training quantization method for vision transformers (ViTs). We identify the limitations of recent techniques, notably their inability to leverage meaningful inter-patch relationshi…

Contrastive Learningobject-detectionObject DetectionQuantization

Contrastive Quantization with Code Memory for Unsupervised Image Retrieval

2021-09-11 · Jinpeng Wang, Ziyun Zeng, Bin Chen, Tao Dai 외

The high efficiency in computation and storage makes hashing (including binary hashing and quantization) a common strategy in large-scale retrieval systems. To alleviate the reliance on expensive annotations, unsupervise…

Contrastive LearningDeep HashingDiversityImage Retrieval+1

Self-supervised Product Quantization for Deep Unsupervised Image Retrieval

2021-09-06 · ICCV 2021 10 · Young Kyun Jang, Nam Ik Cho

Supervised deep learning-based hash and vector quantization are enabling fast and large-scale image retrieval systems. By fully exploiting label annotations, they are achieving outstanding retrieval performances compared…

Contrastive LearningDescriptiveImage RetrievalQuantization+1

Massive Spikes in LLMs are Bias Vectors: Mechanistic Uncovering and Spike-Free Quantization

2026-06-01 · Yung-Chin Chen, Chung Peng Lee, Ze-Wei Liou, Naveen Verma arxiv

Massive activation spikes in Large Language Models (LLMs) severely degrade quantization by stretching dynamic ranges. While prior hypotheses characterize these as high-level scalar biases, we argue that they are merely t…

Contrastive Quant: Quantization Makes Stronger Contrastive Learning

2021-09-29 · Yonggan Fu, Qixuan Yu, Meng Li, Xu Ouyang 외

Contrastive learning, which learns visual representations by enforcing feature consistency under different augmented views, has emerged as one of the most effective unsupervised learning methods. In this work, we explore…

Contrastive LearningQuantization