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

• URL: http://arxiv.org/abs/2306.04695v2
• Date: Thu, 22 Feb 2024 19:11:46 GMT
• Title: ConceptBed: Evaluating Concept Learning Abilities of Text-to-Image Diffusion Models
• Authors: Maitreya Patel and Tejas Gokhale and Chitta Baral and Yezhou Yang
• Abstract summary: We introduce ConceptBed, a large-scale dataset that consists of 284 unique visual concepts and 33K composite text prompts. We evaluate visual concepts that are either objects, attributes, or styles, and also evaluate four dimensions of compositionality: counting, attributes, relations, and actions. Our results point to a trade-off between learning the concepts and preserving the compositionality which existing approaches struggle to overcome.
• Score: 79.10890337599166
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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/

Related papers

• CusConcept: Customized Visual Concept Decomposition with Diffusion Models [13.95568624067449]
  We propose a two-stage framework, CusConcept, to extract customized visual concept embedding vectors. In the first stage, CusConcept employs a vocabularies-guided concept decomposition mechanism. In the second stage, joint concept refinement is performed to enhance the fidelity and quality of generated images.
  arXiv  Detail & Related papers  (2024-10-01T04:41:44Z)
• ConceptMix: A Compositional Image Generation Benchmark with Controllable Difficulty [52.15933752463479]
  ConceptMix is a scalable, controllable, and customizable benchmark. It automatically evaluates compositional generation ability of Text-to-Image (T2I) models. It reveals that the performance of several models, especially open models, drops dramatically with increased k.
  arXiv  Detail & Related papers  (2024-08-26T15:08:12Z)
• Explainable Concept Generation through Vision-Language Preference Learning [7.736445799116692]
  Concept-based explanations have become a popular choice for explaining deep neural networks post-hoc. We devise a reinforcement learning-based preference optimization algorithm that fine-tunes the vision-language generative model. In addition to showing the efficacy and reliability of our method, we show how our method can be used as a diagnostic tool for analyzing neural networks.
  arXiv  Detail & Related papers  (2024-08-24T02:26:42Z)
• Towards Compositionality in Concept Learning [20.960438848942445]
  We show that existing unsupervised concept extraction methods find concepts which are not compositional. We propose Compositional Concept Extraction (CCE) for finding concepts which obey these properties. CCE finds more compositional concept representations than baselines and yields better accuracy on four downstream classification tasks.
  arXiv  Detail & Related papers  (2024-06-26T17:59:30Z)
• Knowledge graphs for empirical concept retrieval [1.06378109904813]
  Concept-based explainable AI is promising as a tool to improve the understanding of complex models at the premises of a given user. Here, we present a workflow for user-driven data collection in both text and image domains. We test the retrieved concept datasets on two concept-based explainability methods, namely concept activation vectors (CAVs) and concept activation regions (CARs)
  arXiv  Detail & Related papers  (2024-04-10T13:47:22Z)
• M^2ConceptBase: A Fine-Grained Aligned Concept-Centric Multimodal Knowledge Base [61.53959791360333]
  We introduce M2ConceptBase, the first concept-centric multimodal knowledge base (MMKB) We propose a context-aware approach to align concept-image and concept-description pairs using context information from image-text datasets. Human studies confirm more than 95% alignment accuracy, underscoring its quality.
  arXiv  Detail & Related papers  (2023-12-16T11:06:11Z)
• Text-to-Image Generation for Abstract Concepts [76.32278151607763]
  We propose a framework of Text-to-Image generation for Abstract Concepts (TIAC) The abstract concept is clarified into a clear intent with a detailed definition to avoid ambiguity. The concept-dependent form is retrieved from an LLM-extracted form pattern set.
  arXiv  Detail & Related papers  (2023-09-26T02:22:39Z)
• Create Your World: Lifelong Text-to-Image Diffusion [75.14353789007902]
  We propose Lifelong text-to-image Diffusion Model (L2DM) to overcome knowledge "catastrophic forgetting" for the past encountered concepts. In respect of knowledge "catastrophic forgetting", our L2DM framework devises a task-aware memory enhancement module and a elastic-concept distillation module. Our model can generate more faithful image across a range of continual text prompts in terms of both qualitative and quantitative metrics.
  arXiv  Detail & Related papers  (2023-09-08T16:45:56Z)
• FALCON: Fast Visual Concept Learning by Integrating Images, Linguistic descriptions, and Conceptual Relations [99.54048050189971]
  We present a framework for learning new visual concepts quickly, guided by multiple naturally occurring data streams. The learned concepts support downstream applications, such as answering questions by reasoning about unseen images. We demonstrate the effectiveness of our model on both synthetic and real-world datasets.
  arXiv  Detail & Related papers  (2022-03-30T19:45:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.