Cover Image

Captured by Captions: On Memorization and its Mitigation in CLIP Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Wenhao, Dziedzic, Adam, Kim, Grace C., Backes, Michael, Boenisch, Franziska
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Localizing Memorization in SSL Vision Encoders
by: Wang, Wenhao, et al.
Published: (2024)

Finding DoRI: Discovery of Retained Images in Diffusion Models
by: Kowalczuk, Antoni, et al.
Published: (2025)

Demystifying Foreground-Background Memorization in Diffusion Models
by: Di, Jimmy Z., et al.
Published: (2025)

Privacy Attacks on Image AutoRegressive Models
by: Kowalczuk, Antoni, et al.
Published: (2025)

Radioactive Watermarks in Diffusion and Autoregressive Image Generative Models
by: Meintz, Michel, et al.
Published: (2025)

BitMark: Watermarking Bitwise Autoregressive Image Generative Models
by: Kerner, Louis, et al.
Published: (2025)

Finding NeMo: Localizing Neurons Responsible For Memorization in Diffusion Models
by: Hintersdorf, Dominik, et al.
Published: (2024)

Localizing and Mitigating Memorization in Image Autoregressive Models
by: Kasliwal, Aditya, et al.
Published: (2025)

Memorization In Stable Diffusion Is Unexpectedly Driven by CLIP Embeddings
by: Kim, Bumjun, et al.
Published: (2026)

VeCLIP: Improving CLIP Training via Visual-enriched Captions
by: Lai, Zhengfeng, et al.
Published: (2023)

Conditioned Activation Transport for T2I Safety Steering
by: Chrabąszcz, Maciej, et al.
Published: (2026)

Implementing Adaptations for Vision AutoRegressive Model
by: Shaikh, Kaif, et al.
Published: (2025)

Detecting and Mitigating Memorization in Diffusion Models through Anisotropy of the Log-Probability
by: Asthana, Rohan, et al.
Published: (2026)

Memorization in Self-Supervised Learning Improves Downstream Generalization
by: Wang, Wenhao, et al.
Published: (2024)

On Memorization in Diffusion Models
by: Gu, Xiangming, et al.
Published: (2023)

Unlocking Post-hoc Dataset Inference with Synthetic Data
by: Zhao, Bihe, et al.
Published: (2025)

CLIP Can Understand Depth
by: Kim, Sohee, et al.
Published: (2024)

SafeR-CLIP: Mitigating NSFW Content in Vision-Language Models While Preserving Pre-Trained Knowledge
by: Yousaf, Adeel, et al.
Published: (2025)

Zero-Shot, But at What Cost? Unveiling the Hidden Overhead of MILS's LLM-CLIP Framework for Image Captioning
by: Benhammou, Yassir, et al.
Published: (2025)

Benchmarking Robust Self-Supervised Learning Across Diverse Downstream Tasks
by: Kowalczuk, Antoni, et al.
Published: (2024)

DiffCLIP: Differential Attention Meets CLIP
by: Hammoud, Hasan Abed Al Kader, et al.
Published: (2025)

Memorization in Graph Neural Networks
by: Jamadandi, Adarsh, et al.
Published: (2025)

CountCLIP -- [Re] Teaching CLIP to Count to Ten
by: Mestha, Harshvardhan, et al.
Published: (2024)

Generalizable Geometric Image Caption Synthesis
by: Xin, Yue, et al.
Published: (2025)

Steering Away from Memorization: Reachability-Constrained Reinforcement Learning for Text-to-Image Diffusion
by: Karnik, Sathwik, et al.
Published: (2026)

CaptionFormer: Unified Segmentation, Tracking, and Captioning for Spatio-Temporal Objects
by: Fiastre, Gabriel, et al.
Published: (2025)

Graph-Based Captioning: Enhancing Visual Descriptions by Interconnecting Region Captions
by: Hsieh, Yu-Guan, et al.
Published: (2024)

Image Captions are Natural Prompts for Text-to-Image Models
by: Lei, Shiye, et al.
Published: (2023)

Memorized Images in Diffusion Models share a Subspace that can be Located and Deleted
by: Chavhan, Ruchika, et al.
Published: (2024)

Beautiful Images, Toxic Words: Understanding and Addressing Offensive Text in Generated Images
by: Kumar, Aditya, et al.
Published: (2025)

Impact of Layer Norm on Memorization and Generalization in Transformers
by: Singhal, Rishi, et al.
Published: (2025)

CompCap: Improving Multimodal Large Language Models with Composite Captions
by: Chen, Xiaohui, et al.
Published: (2024)

SynthCLIP: Are We Ready for a Fully Synthetic CLIP Training?
by: Hammoud, Hasan Abed Al Kader, et al.
Published: (2024)

QG-CoC: Question-Guided Chain-of-Captions for Large Multimodal Models
by: Kao, Kuei-Chun, et al.
Published: (2025)

SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training
by: Chu, Tianzhe, et al.
Published: (2025)

SynC: Synthetic Image Caption Dataset Refinement with One-to-many Mapping for Zero-shot Image Captioning
by: Kim, Si-Woo, et al.
Published: (2025)

Fine-tuning CLIP Text Encoders with Two-step Paraphrasing
by: Kim, Hyunjae, et al.
Published: (2024)

Mitigate the Gap: Investigating Approaches for Improving Cross-Modal Alignment in CLIP
by: Eslami, Sedigheh, et al.
Published: (2024)

IDEA: Image Description Enhanced CLIP-Adapter
by: Ye, Zhipeng, et al.
Published: (2025)

FG-CLIP 2: A Bilingual Fine-grained Vision-Language Alignment Model
by: Xie, Chunyu, et al.
Published: (2025)