Cover Image

When and How Does CLIP Enable Domain and Compositional Generalization?

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kempf, Elias, Schrodi, Simon, Argus, Max, Brox, Thomas
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Concept Bottleneck Models Without Predefined Concepts
by: Schrodi, Simon, et al.
Published: (2024)

Two Effects, One Trigger: On the Modality Gap, Object Bias, and Information Imbalance in Contrastive Vision-Language Models
by: Schrodi, Simon, et al.
Published: (2024)

What Drives Compositional Generalization? The Importance of Continuous Training Objectives in Visual Generative Models
by: Farid, Karim, et al.
Published: (2025)

Towards Understanding Subliminal Learning: When and How Hidden Biases Transfer
by: Schrodi, Simon, et al.
Published: (2025)

Eureka-Moments in Transformers: Multi-Step Tasks Reveal Softmax Induced Optimization Problems
by: Hoffmann, David T., et al.
Published: (2023)

Using Knowledge Graphs to harvest datasets for efficient CLIP model training
by: Ging, Simon, et al.
Published: (2025)

Open-ended VQA benchmarking of Vision-Language models by exploiting Classification datasets and their semantic hierarchy
by: Ging, Simon, et al.
Published: (2024)

DITTO: Demonstration Imitation by Trajectory Transformation
by: Heppert, Nick, et al.
Published: (2024)

CLIP-Powered Domain Generalization and Domain Adaptation: A Comprehensive Survey
by: Li, Jindong, et al.
Published: (2025)

Exploring How Generative MLLMs Perceive More Than CLIP with the Same Vision Encoder
by: Li, Siting, et al.
Published: (2024)

When Does Perceptual Alignment Benefit Vision Representations?
by: Sundaram, Shobhita, et al.
Published: (2024)

MoP-CLIP: A Mixture of Prompt-Tuned CLIP Models for Domain Incremental Learning
by: Nicolas, Julien, et al.
Published: (2023)

Robustness in Both Domains: CLIP Needs a Robust Text Encoder
by: Rocamora, Elias Abad, et al.
Published: (2025)

Advancing Compositional Awareness in CLIP with Efficient Fine-Tuning
by: Peleg, Amit, et al.
Published: (2025)

Does CLIP Know My Face?
by: Hintersdorf, Dominik, et al.
Published: (2022)

CLIPArTT: Adaptation of CLIP to New Domains at Test Time
by: Hakim, Gustavo Adolfo Vargas, et al.
Published: (2024)

Language Plays a Pivotal Role in the Object-Attribute Compositional Generalization of CLIP
by: Abbasi, Reza, et al.
Published: (2024)

Common Data Properties Limit Object-Attribute Binding in CLIP
by: Gurung, Bijay, et al.
Published: (2025)

Learning to Adapt Frozen CLIP for Few-Shot Test-Time Domain Adaptation
by: Chi, Zhixiang, et al.
Published: (2025)

Does CLIP's Generalization Performance Mainly Stem from High Train-Test Similarity?
by: Mayilvahanan, Prasanna, et al.
Published: (2023)

Detecting AI-Generated Images via CLIP
by: Moskowitz, A. G., et al.
Published: (2024)

Diffusion for Out-of-Distribution Detection on Road Scenes and Beyond
by: Galesso, Silvio, et al.
Published: (2024)

Simple LLM Baselines are Competitive for Model Diffing
by: Kempf, Elias, et al.
Published: (2026)

DeCLIP: Decoding CLIP representations for deepfake localization
by: Smeu, Stefan, et al.
Published: (2024)

kNN-CLIP: Retrieval Enables Training-Free Segmentation on Continually Expanding Large Vocabularies
by: Gui, Zhongrui, et al.
Published: (2024)

Aggregate-and-Adapt Natural Language Prompts for Downstream Generalization of CLIP
by: Huang, Chen, et al.
Published: (2024)

IsoCLIP: Decomposing CLIP Projectors for Efficient Intra-modal Alignment
by: Magistri, Simone, et al.
Published: (2026)

Enhancing CLIP with CLIP: Exploring Pseudolabeling for Limited-Label Prompt Tuning
by: Menghini, Cristina, et al.
Published: (2023)

Does FLUX Already Know How to Perform Physically Plausible Image Composition?
by: Lu, Shilin, et al.
Published: (2025)

Strong but simple: A Baseline for Domain Generalized Dense Perception by CLIP-based Transfer Learning
by: Hümmer, Christoph, et al.
Published: (2023)

NeuCLIP: Efficient Large-Scale CLIP Training with Neural Normalizer Optimization
by: Wei, Xiyuan, et al.
Published: (2025)

FairerCLIP: Debiasing CLIP's Zero-Shot Predictions using Functions in RKHSs
by: Dehdashtian, Sepehr, et al.
Published: (2024)

Orbis: Overcoming Challenges of Long-Horizon Prediction in Driving World Models
by: Mousakhan, Arian, et al.
Published: (2025)

PHyCLIP: $\ell_1$-Product of Hyperbolic Factors Unifies Hierarchy and Compositionality in Vision-Language Representation Learning
by: Yoshikawa, Daiki, et al.
Published: (2025)

Advancing Vision-based Human Action Recognition: Exploring Vision-Language CLIP Model for Generalisation in Domain-Independent Tasks
by: Shandilya, Utkarsh, et al.
Published: (2025)

FastCLIP: A Suite of Optimization Techniques to Accelerate CLIP Training with Limited Resources
by: Wei, Xiyuan, et al.
Published: (2024)

Learning to Read Where to Look: Disease-Aware Vision-Language Pretraining for 3D CT
by: Ging, Simon, et al.
Published: (2026)

Domain Generalization by Rejecting Extreme Augmentations
by: Aminbeidokhti, Masih, et al.
Published: (2023)

CLIP-UP: A Simple and Efficient Mixture-of-Experts CLIP Training Recipe with Sparse Upcycling
by: Wang, Xinze, et al.
Published: (2025)

Breaking the Limits of Open-Weight CLIP: An Optimization Framework for Self-supervised Fine-tuning of CLIP
by: Mehta, Anant, et al.
Published: (2026)