paper-with-me

Papers

ConceptBed: Evaluating Concept Learning Abilities of Text-to-Image Diffusion Models

2023-06-07 · Maitreya Patel, Tejas Gokhale, Chitta Baral, Yezhou Yang

The ability to understand visual concepts and replicate and compose these concepts from images is a central goal for computer vision. Recent advances in text-to-image (T2I) models have lead to high definition and realistic image quality generation by learning from large databases of images and their descriptions. However, the evaluation of T2I models has focused on photorealism and limited qualitative measures of visual understanding. To quantify the ability of T2I models in learning and synthesizing novel visual concepts (a.k.a. personalized T2I), we introduce ConceptBed, a large-scale dataset that consists of 284 unique visual concepts, and 33K composite text prompts. Along with the dataset, we propose an evaluation metric, Concept Confidence Deviation (CCD), that uses the confidence of oracle concept classifiers to measure the alignment between concepts generated by T2I generators and concepts contained in target images. We evaluate visual concepts that are either objects, attributes, or styles, and also evaluate four dimensions of compositionality: counting, attributes, relations, and actions. Our human study shows that CCD is highly correlated with human understanding of concepts. Our results point to a trade-off between learning the concepts and preserving the compositionality which existing approaches struggle to overcome. The data, code, and interactive demo is available at: https://conceptbed.github.io/

📄 PDF Abstract BibTeX arXiv:2306.04695

Code (1)

conceptbed/evaluations 공식 구현 pytorch

Tasks

Concept Alignment

Similar Papers 제목 키워드 기반

Comparing Humans, GPT-4, and GPT-4V On Abstraction and Reasoning Tasks

2023-11-14 · Melanie Mitchell, Alessandro B. Palmarini, Arseny Moskvichev

We explore the abstract reasoning abilities of text-only and multimodal versions of GPT-4, using the ConceptARC benchmark [10], which is designed to evaluate robust understanding and reasoning with core-knowledge concept…

T2I-FactualBench: Benchmarking the Factuality of Text-to-Image Models with Knowledge-Intensive Concepts

2024-12-05 · Ziwei Huang, Wanggui He, Quanyu Long, Yandi Wang 외

Evaluating the quality of synthesized images remains a significant challenge in the development of text-to-image (T2I) generation. Most existing studies in this area primarily focus on evaluating text-image alignment, im…

BenchmarkingImage GenerationMemorizationQuestion Answering+4

A Framework for Evaluating Zero-Shot Image Generation in Concept-based Explainability

2026-05-19 · Giacomo Astolfi, Matteo Bianchi, Riccardo Campi, Antonio De Santis 외 arxiv

Concept-based Explainable Artificial Intelligence (XAI) interprets deep learning models using human-understandable visual features (e.g., textures or object parts) by linking internal representations to class predictions…

Image Generation

Evaluating a Synthetic Image Dataset Generated with Stable Diffusion

2022-11-03 · Andreas Stöckl

We generate synthetic images with the "Stable Diffusion" image generation model using the Wordnet taxonomy and the definitions of concepts it contains. This synthetic image database can be used as training data for data …

Data Augmentationimage-classificationImage ClassificationImage Generation

On the Fairness, Diversity and Reliability of Text-to-Image Generative Models

2024-11-21 · Jordan Vice, Naveed Akhtar, Richard Hartley, Ajmal Mian

The widespread availability of multimodal generative models has sparked critical discussions on their fairness, reliability, and potential for misuse. While text-to-image models can produce high-fidelity, user-guided ima…

DiversityEthicsFairness