Image de couverture de livre

Debiasing Vison-Language Models with Text-Only Training

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Yang, Yunfan, Jiang, Chaoquan, Lin, Zhiyu, Xiao, Jinlin, Zhang, Jiaming, Sang, Jitao
Format:	Preprint
Publié:	2024
Sujets:	Computer Vision and Pattern Recognition Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Debiased Prompt Tuning in Vision-Language Model without Annotations
par: Jiang, Chaoquan, et autres
Publié: (2025)

Language-assisted Vision Model Debugger: A Sample-Free Approach to Finding and Fixing Bugs
par: Jiang, Chaoquan, et autres
Publié: (2023)

Investigating and Enhancing Vision-Audio Capability in Omnimodal Large Language Models
par: Hu, Rui, et autres
Publié: (2025)

Not Only Text: Exploring Compositionality of Visual Representations in Vision-Language Models
par: Berasi, Davide, et autres
Publié: (2025)

PARIC: Probabilistic Attention Regularization for Language Guided Image Classification from Pre-trained Vison Language Models
par: Nautiyal, Mayank, et autres
Publié: (2025)

AIGCs Confuse AI Too: Investigating and Explaining Synthetic Image-induced Hallucinations in Large Vision-Language Models
par: Gao, Yifei, et autres
Publié: (2024)

An Experimental Study of Semantic Continuity for Deep Learning Models
par: Wu, Shangxi, et autres
Publié: (2020)

You Only Train Once
par: Sakaridis, Christos
Publié: (2025)

Robust Emotion Recognition in Context Debiasing
par: Yang, Dingkang, et autres
Publié: (2024)

Debiased Negative Mining Improves Out-of-distribution Detection with Pre-trained Vision-Language Models
par: Peng, Bo, et autres
Publié: (2026)

BendVLM: Test-Time Debiasing of Vision-Language Embeddings
par: Gerych, Walter, et autres
Publié: (2024)

Model Debiasing by Learnable Data Augmentation
par: Morerio, Pietro, et autres
Publié: (2024)

Catch-Up Distillation: You Only Need to Train Once for Accelerating Sampling
par: Shao, Shitong, et autres
Publié: (2023)

NanoVDR: Distilling a 2B Vision-Language Retriever into a 70M Text-Only Encoder for Visual Document Retrieval
par: Liu, Zhuchenyang, et autres
Publié: (2026)

Debiasing Large Vision-Language Models by Ablating Protected Attribute Representations
par: Ratzlaff, Neale, et autres
Publié: (2024)

Navigate Beyond Shortcuts: Debiased Learning through the Lens of Neural Collapse
par: Wang, Yining, et autres
Publié: (2024)

Growing Visual Generative Capacity for Pre-Trained MLLMs
par: Wang, Hanyu, et autres
Publié: (2025)

SharpZO: Hybrid Sharpness-Aware Vision Language Model Prompt Tuning via Forward-Only Passes
par: Yang, Yifan, et autres
Publié: (2025)

Training-free Editioning of Text-to-Image Models
par: Wang, Jinqi, et autres
Publié: (2024)

SurrogateSHAP: Training-Free Contributor Attribution for Text-to-Image (T2I) Models
par: Lu, Mingyu, et autres
Publié: (2026)

Gradient Extrapolation for Debiased Representation Learning
par: Asaad, Ihab, et autres
Publié: (2025)

Training-Only Heterogeneous Image-Patch-Text Graph Supervision for Advancing Few-Shot Learning Adapters
par: Mohammad, Mohammed Rahman Sherif Khan, et autres
Publié: (2026)

DiFiC: Your Diffusion Model Holds the Secret to Fine-Grained Clustering
par: Yang, Ruohong, et autres
Publié: (2024)

Text-to-CAD Generation Through Infusing Visual Feedback in Large Language Models
par: Wang, Ruiyu, et autres
Publié: (2025)

Debiasing Diffusion Model: Enhancing Fairness through Latent Representation Learning in Stable Diffusion Model
par: Huang, Lin-Chun, et autres
Publié: (2025)

Doubly Debiased Test-Time Prompt Tuning for Vision-Language Models
par: Song, Fei, et autres
Publié: (2025)

Transitive Vision-Language Prompt Learning for Domain Generalization
par: Wang, Liyuan, et autres
Publié: (2024)

Fast-Slow Efficient Training for Multimodal Large Language Models via Visual Token Pruning
par: Zhang, Dingkun, et autres
Publié: (2026)

You Only Look One Step: Accelerating Backpropagation in Diffusion Sampling with Gradient Shortcuts
par: Dou, Hongkun, et autres
Publié: (2025)

Learning Decomposable and Debiased Representations via Attribute-Centric Information Bottlenecks
par: Hong, Jinyung, et autres
Publié: (2024)

SEM: Sparse Embedding Modulation for Post-Hoc Debiasing of Vision-Language Models
par: Guimard, Quentin, et autres
Publié: (2026)

DUDE: Diffusion-Based Unsupervised Cross-Domain Image Retrieval
par: Yang, Ruohong, et autres
Publié: (2025)

Personalized Generative Models for Contextual Debiasing
par: Liang, Xinran, et autres
Publié: (2026)

DeNetDM: Debiasing by Network Depth Modulation
par: Sreelatha, Silpa Vadakkeeveetil, et autres
Publié: (2024)

Mirage in the Eyes: Hallucination Attack on Multi-modal Large Language Models with Only Attention Sink
par: Wang, Yining, et autres
Publié: (2025)

High-Fidelity Text-to-Image Generation from Pre-Trained Vision-Language Models via Distribution-Conditioned Diffusion Decoding
par: Hong, Ji Woo, et autres
Publié: (2026)

A Survey on Deep Clustering: From the Prior Perspective
par: Lu, Yiding, et autres
Publié: (2024)

BiPrompt: Bilateral Prompt Optimization for Visual and Textual Debiasing in Vision-Language Models
par: Gupta, Sunny, et autres
Publié: (2026)

Transferring Visual Explainability of Self-Explaining Models to Prediction-Only Models without Additional Training
par: Yoshikawa, Yuya, et autres
Publié: (2025)

Forward-Only Continual Learning
par: Chen, Jiao, et autres
Publié: (2025)