Cover Image

Two Effects, One Trigger: On the Modality Gap, Object Bias, and Information Imbalance in Contrastive Vision-Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Schrodi, Simon, Hoffmann, David T., Argus, Max, Fischer, Volker, Brox, Thomas
Format:	Preprint
Published:	2024
Subjects:	Computer Vision and Pattern Recognition Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

When and How Does CLIP Enable Domain and Compositional Generalization?
by: Kempf, Elias, et al.
Published: (2025)

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

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

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

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

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

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

Detect, Classify, Act: Categorizing Industrial Anomalies with Multi-Modal Large Language Models
by: Mokhtar, Sassan, et al.
Published: (2025)

COST: Contrastive One-Stage Transformer for Vision-Language Small Object Tracking
by: Zhang, Chunhui, et al.
Published: (2025)

On the Domain Robustness of Contrastive Vision-Language Models
by: Koddenbrock, Mario, et al.
Published: (2025)

Freeze and Reveal: Exposing Modality Bias in Vision-Language Models
by: Kavuri, Vivek Hruday, et al.
Published: (2025)

Bridge the Modality and Capability Gaps in Vision-Language Model Selection
by: Yi, Chao, et al.
Published: (2024)

Towards Mitigating Modality Bias in Vision-Language Models for Temporal Action Localization
by: Li, Jiaqi, et al.
Published: (2026)

Beyond Cross-Modal Alignment: Measuring and Leveraging Modality Gap in Vision-Language Models
by: Yan, Hanqi, et al.
Published: (2025)

A Tale of Two Classes: Adapting Supervised Contrastive Learning to Binary Imbalanced Datasets
by: Mildenberger, David, et al.
Published: (2025)

It's Not a Modality Gap: Characterizing and Addressing the Contrastive Gap
by: Fahim, Abrar, et al.
Published: (2024)

Anomaly Detection with Conditioned Denoising Diffusion Models
by: Mousakhan, Arian, et al.
Published: (2023)

See-Saw Modality Balance: See Gradient, and Sew Impaired Vision-Language Balance to Mitigate Dominant Modality Bias
by: Kwon, JuneHyoung, et al.
Published: (2025)

Contrast-Guided Cross-Modal Distillation for Thermal Object Detection
by: Kim, SiWoo, et al.
Published: (2025)

Extending 6D Object Pose Estimators for Stereo Vision
by: Pöllabauer, Thomas, et al.
Published: (2024)

SOCO: Benchmarking Semantic Object Correspondence in Vision Foundation Models
by: Dünkel, Olaf, et al.
Published: (2026)

Explaining and Mitigating the Modality Gap in Contrastive Multimodal Learning
by: Yaras, Can, et al.
Published: (2024)

Do Vision-Language Models Truly Perform Vision Reasoning? A Rigorous Study of the Modality Gap
by: Xu, Yige, et al.
Published: (2026)

Label-Efficient LiDAR Semantic Segmentation with 2D-3D Vision Transformer Adapters
by: Hindel, Julia, et al.
Published: (2025)

Unsupervised Open-Vocabulary Object Localization in Videos
by: Fan, Ke, et al.
Published: (2023)

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

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

StorySync: Training-Free Subject Consistency in Text-to-Image Generation via Region Harmonization
by: Gaur, Gopalji, et al.
Published: (2025)

Benchmarking and Mitigating MCQA Selection Bias of Large Vision-Language Models
by: Atabuzzaman, Md., et al.
Published: (2025)

Visual Modality Prompt for Adapting Vision-Language Object Detectors
by: Medeiros, Heitor R., et al.
Published: (2024)

Beyond Memorization: A Multi-Modal Ordinal Regression Benchmark to Expose Popularity Bias in Vision-Language Models
by: Szu-Tu, Li-Zhong, et al.
Published: (2025)

All in One: Exploring Unified Vision-Language Tracking with Multi-Modal Alignment
by: Zhang, Chunhui, et al.
Published: (2023)

Mind the Modality Gap: Towards a Remote Sensing Vision-Language Model via Cross-modal Alignment
by: Zavras, Angelos, et al.
Published: (2024)

On Geometric Understanding and Learned Priors in Feed-forward 3D Reconstruction Models
by: Bratulić, Jelena, et al.
Published: (2025)

Do Not Leave a Gap: Hallucination-Free Object Concealment in Vision-Language Models
by: Guesmi, Amira, et al.
Published: (2026)

Pathological Truth Bias in Vision-Language Models
by: Thube, Yash
Published: (2025)

Information Router for Mitigating Modality Dominance in Vision-Language Models
by: Kim, Seulgi, et al.
Published: (2026)

Bridging the Missing-Modality Gap: Improving Text-Only Calibration of Vision Language Models
by: Kim, Mingyeong, et al.
Published: (2026)

Respecting Modality Gap in Post-hoc Out-of-distribution Detection with Pre-trained Vision-Language Models
by: Hu, Yuanwei, et al.
Published: (2026)

Cross-Modal Redundancy and the Geometry of Vision-Language Embeddings
by: Dhimoïla, Grégoire, et al.
Published: (2026)