Image de couverture de livre

Common Data Properties Limit Object-Attribute Binding in CLIP

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Gurung, Bijay, Hoffmann, David T., Brox, Thomas
Format:	Preprint
Publié:	2025
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Two Effects, One Trigger: On the Modality Gap, Object Bias, and Information Imbalance in Contrastive Vision-Language Models
par: Schrodi, Simon, et autres
Publié: (2024)

When and How Does CLIP Enable Domain and Compositional Generalization?
par: Kempf, Elias, et autres
Publié: (2025)

Object-Attribute Binding in Text-to-Image Generation: Evaluation and Control
par: Trusca, Maria Mihaela, et autres
Publié: (2024)

Real Classification by Description: Extending CLIP's Limits of Part Attributes Recognition
par: Baron, Ethan, et autres
Publié: (2024)

ABE-CLIP: Training-Free Attribute Binding Enhancement for Compositional Image-Text Matching
par: Zhang, Qi, et autres
Publié: (2025)

Anomaly Detection with Conditioned Denoising Diffusion Models
par: Mousakhan, Arian, et autres
Publié: (2023)

Incremental Object Detection with CLIP
par: Huang, Ziyue, et autres
Publié: (2023)

CLIP-FTI: Fine-Grained Face Template Inversion via CLIP-Driven Attribute Conditioning
par: Dai, Longchen, et autres
Publié: (2025)

Analyzing CLIP's Performance Limitations in Multi-Object Scenarios: A Controlled High-Resolution Study
par: Abbasi, Reza, et autres
Publié: (2025)

Using Knowledge Graphs to harvest datasets for efficient CLIP model training
par: Ging, Simon, et autres
Publié: (2025)

Language Plays a Pivotal Role in the Object-Attribute Compositional Generalization of CLIP
par: Abbasi, Reza, et autres
Publié: (2024)

C2P-CLIP: Injecting Category Common Prompt in CLIP to Enhance Generalization in Deepfake Detection
par: Tan, Chuangchuang, et autres
Publié: (2024)

Box It to Bind It: Unified Layout Control and Attribute Binding in T2I Diffusion Models
par: Taghipour, Ashkan, et autres
Publié: (2024)

SANER: Annotation-free Societal Attribute Neutralizer for Debiasing CLIP
par: Hirota, Yusuke, et autres
Publié: (2024)

GazeCLIP: Gaze-Guided CLIP with Adaptive-Enhanced Fine-Grained Language Prompt for Deepfake Attribution and Detection
par: Zhang, Yaning, et autres
Publié: (2026)

On Geometric Understanding and Learned Priors in Feed-forward 3D Reconstruction Models
par: Bratulić, Jelena, et autres
Publié: (2025)

Eureka-Moments in Transformers: Multi-Step Tasks Reveal Softmax Induced Optimization Problems
par: Hoffmann, David T., et autres
Publié: (2023)

Efficiently Disentangling CLIP for Multi-Object Perception
par: Rawlekar, Samyak, et autres
Publié: (2025)

NeuroCLIP: Neuromorphic Data Understanding by CLIP and SNN
par: Guo, Yufei, et autres
Publié: (2023)

StorySync: Training-Free Subject Consistency in Text-to-Image Generation via Region Harmonization
par: Gaur, Gopalji, et autres
Publié: (2025)

Are CLIP features all you need for Universal Synthetic Image Origin Attribution?
par: Cioni, Dario, et autres
Publié: (2024)

ET tu, CLIP? Addressing Common Object Errors for Unseen Environments
par: Byun, Ye Won, et autres
Publié: (2024)

MultiBind: A Benchmark for Attribute Misbinding in Multi-Subject Generation
par: Tian, Wenqing, et autres
Publié: (2026)

InstructAttribute: Fine-grained Object Attributes editing with Instruction
par: Yin, Xingxi, et autres
Publié: (2025)

SEED4D: A Synthetic Ego--Exo Dynamic 4D Data Generator, Driving Dataset and Benchmark
par: Kästingschäfer, Marius, et autres
Publié: (2024)

FairCLIP: Social Bias Elimination based on Attribute Prototype Learning and Representation Neutralization
par: Wang, Junyang, et autres
Publié: (2022)

Detect, Classify, Act: Categorizing Industrial Anomalies with Multi-Modal Large Language Models
par: Mokhtar, Sassan, et autres
Publié: (2025)

sshELF: Single-Shot Hierarchical Extrapolation of Latent Features for 3D Reconstruction from Sparse-Views
par: Najafli, Eyvaz, et autres
Publié: (2025)

Enhancing CLIP with CLIP: Exploring Pseudolabeling for Limited-Label Prompt Tuning
par: Menghini, Cristina, et autres
Publié: (2023)

CLIP-Guided Source-Free Object Detection in Aerial Images
par: Liu, Nanqing, et autres
Publié: (2024)

Exploring Open-Vocabulary Object Recognition in Images using CLIP
par: Chen, Wei Yu, et autres
Publié: (2026)

Demystifying CLIP Data
par: Xu, Hu, et autres
Publié: (2023)

GA2-CLIP: Generic Attribute Anchor for Efficient Prompt Tuningin Video-Language Models
par: Wang, Bin, et autres
Publié: (2025)

MSCI: Addressing CLIP's Inherent Limitations for Compositional Zero-Shot Learning
par: Wang, Yue, et autres
Publié: (2025)

The Common Objects Underwater (COU) Dataset for Robust Underwater Object Detection
par: Mukherjee, Rishi, et autres
Publié: (2025)

Neural Point Cloud Diffusion for Disentangled 3D Shape and Appearance Generation
par: Schröppel, Philipp, et autres
Publié: (2023)

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

BlendCLIP: Bridging Synthetic and Real Domains for Zero-Shot 3D Object Classification with Multimodal Pretraining
par: Khoche, Ajinkya, et autres
Publié: (2025)

Few-Shot Class-Incremental Model Attribution Using Learnable Representation From CLIP-ViT Features
par: Lee, Hanbyul, et autres
Publié: (2025)

Concept Bottleneck Models Without Predefined Concepts
par: Schrodi, Simon, et autres
Publié: (2024)