Copertina

ConceptMix: A Compositional Image Generation Benchmark with Controllable Difficulty

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Wu, Xindi, Yu, Dingli, Huang, Yangsibo, Russakovsky, Olga, Arora, Sanjeev
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

ConceptMix++: Leveling the Playing Field in Text-to-Image Benchmarking via Iterative Prompt Optimization
di: Gan, Haosheng, et al.
Pubblicazione: (2025)

Visual Compositional Tuning
di: Wu, Xindi, et al.
Pubblicazione: (2025)

Vision-Language Dataset Distillation
di: Wu, Xindi, et al.
Pubblicazione: (2023)

Beyond Objects: Contextual Synthetic Data Generation for Fine-Grained Classification
di: Yang, William, et al.
Pubblicazione: (2025)

The Silent Assistant: NoiseQuery as Implicit Guidance for Goal-Driven Image Generation
di: Wang, Ruoyu, et al.
Pubblicazione: (2024)

D2D: Detector-to-Differentiable Critic for Improved Numeracy in Text-to-Image Generation
di: Yoo, Nobline, et al.
Pubblicazione: (2025)

ImageNet-OOD: Deciphering Modern Out-of-Distribution Detection Algorithms
di: Yang, William, et al.
Pubblicazione: (2023)

Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs?
di: Park, Simon, et al.
Pubblicazione: (2025)

SOWing Information: Cultivating Contextual Coherence with MLLMs in Image Generation
di: Pei, Yuhan, et al.
Pubblicazione: (2024)

ICONS: Influence Consensus for Vision-Language Data Selection
di: Wu, Xindi, et al.
Pubblicazione: (2024)

Video Models Reason Early: Exploiting Plan Commitment for Maze Solving
di: Newman, Kaleb, et al.
Pubblicazione: (2026)

D$^3$: Scaling Up Deepfake Detection by Learning from Discrepancy
di: Yang, Yongqi, et al.
Pubblicazione: (2024)

A Sampling-Based Domain Generalization Study with Diffusion Generative Models
di: Zhu, Ye, et al.
Pubblicazione: (2023)

Seeing Beyond the Scene: Analyzing and Mitigating Background Bias in Action Recognition
di: Zhou, Ellie, et al.
Pubblicazione: (2025)

Chimera: Compositional Image Generation using Part-based Concepting
di: Singh, Shivam, et al.
Pubblicazione: (2025)

Attention IoU: Examining Biases in CelebA using Attention Maps
di: Serianni, Aaron, et al.
Pubblicazione: (2025)

TweedieMix: Improving Multi-Concept Fusion for Diffusion-based Image/Video Generation
di: Kwon, Gihyun, et al.
Pubblicazione: (2024)

ColorConceptBench: A Benchmark for Probabilistic Color-Concept Understanding in Text-to-Image Models
di: Ruan, Chenxi, et al.
Pubblicazione: (2026)

FreeCustom: Tuning-Free Customized Image Generation for Multi-Concept Composition
di: Ding, Ganggui, et al.
Pubblicazione: (2024)

No Concept Left Behind: Test-Time Optimization for Compositional Text-to-Image Generation
di: Sameti, Mohammad Hossein, et al.
Pubblicazione: (2025)

Canvas-to-Image: Compositional Image Generation with Multimodal Controls
di: Dalva, Yusuf, et al.
Pubblicazione: (2025)

Denoising, Fast and Slow: Difficulty-Aware Adaptive Sampling for Image Generation
di: Schusterbauer, Johannes, et al.
Pubblicazione: (2026)

DSH-Bench: A Difficulty- and Scenario-Aware Benchmark with Hierarchical Subject Taxonomy for Subject-Driven Text-to-Image Generation
di: Hu, Zhenyu, et al.
Pubblicazione: (2026)

VMix: Improving Text-to-Image Diffusion Model with Cross-Attention Mixing Control
di: Wu, Shaojin, et al.
Pubblicazione: (2024)

TwoHamsters: Benchmarking Multi-Concept Compositional Unsafety in Text-to-Image Models
di: Zhang, Chaoshuo, et al.
Pubblicazione: (2026)

JRDB-Reasoning: A Difficulty-Graded Benchmark for Visual Reasoning in Robotics
di: Jahangard, Simindokht, et al.
Pubblicazione: (2025)

T2V-CompBench: A Comprehensive Benchmark for Compositional Text-to-video Generation
di: Sun, Kaiyue, et al.
Pubblicazione: (2024)

The Impact of Coreset Selection on Spurious Correlations and Group Robustness
di: Dharmasiri, Amaya, et al.
Pubblicazione: (2025)

Cached Multi-Lora Composition for Multi-Concept Image Generation
di: Zou, Xiandong, et al.
Pubblicazione: (2025)

DCoAR: Deep Concept Injection into Unified Autoregressive Models for Personalized Text-to-Image Generation
di: Wu, Fangtai, et al.
Pubblicazione: (2025)

GMValuator: Similarity-based Data Valuation for Generative Models
di: Yang, Jiaxi, et al.
Pubblicazione: (2023)

CustomCrafter: Customized Video Generation with Preserving Motion and Concept Composition Abilities
di: Wu, Tao, et al.
Pubblicazione: (2024)

Image-Difficulty-Aware Evaluation of Super-Resolution Models
di: Topaloglu, Atakan, et al.
Pubblicazione: (2025)

Intrinsic Concept Extraction Based on Compositional Interpretability
di: Shi, Hanyu, et al.
Pubblicazione: (2026)

Personalized Generative Models for Contextual Debiasing
di: Liang, Xinran, et al.
Pubblicazione: (2026)

Unlocking Compositional Control: Self-Supervision for LVLM-Based Image Generation
di: Garcia, Fernando Gabriela, et al.
Pubblicazione: (2025)

Dataset Augmentation by Mixing Visual Concepts
di: Rahat, Abdullah Al, et al.
Pubblicazione: (2024)

T2I-FactualBench: Benchmarking the Factuality of Text-to-Image Models with Knowledge-Intensive Concepts
di: Huang, Ziwei, et al.
Pubblicazione: (2024)

RecipeGen: A Benchmark for Real-World Recipe Image Generation
di: Zhang, Ruoxuan, et al.
Pubblicazione: (2025)

Bias at the End of the Score
di: Magid, Salma Abdel, et al.
Pubblicazione: (2026)