Evaluating Text-to-Visual Generation with Image-to-Text Generation

• URL: http://arxiv.org/abs/2404.01291v2
• Date: Tue, 18 Jun 2024 07:09:55 GMT
• Title: Evaluating Text-to-Visual Generation with Image-to-Text Generation
• Authors: Zhiqiu Lin, Deepak Pathak, Baiqi Li, Jiayao Li, Xide Xia, Graham Neubig, Pengchuan Zhang, Deva Ramanan,
• Abstract summary: VQAScore is a visual-question-answering (VQA) model to produce an alignment score. It produces state-of-the-art results across many (8) image-text alignment benchmarks. We introduce GenAI-Bench, a more challenging benchmark with 1,600 compositional text prompts.
• Score: 113.07368313330994
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Despite significant progress in generative AI, comprehensive evaluation remains challenging because of the lack of effective metrics and standardized benchmarks. For instance, the widely-used CLIPScore measures the alignment between a (generated) image and text prompt, but it fails to produce reliable scores for complex prompts involving compositions of objects, attributes, and relations. One reason is that text encoders of CLIP can notoriously act as a "bag of words", conflating prompts such as "the horse is eating the grass" with "the grass is eating the horse". To address this, we introduce the VQAScore, which uses a visual-question-answering (VQA) model to produce an alignment score by computing the probability of a "Yes" answer to a simple "Does this figure show '{text}'?" question. Though simpler than prior art, VQAScore computed with off-the-shelf models produces state-of-the-art results across many (8) image-text alignment benchmarks. We also compute VQAScore with an in-house model that follows best practices in the literature. For example, we use a bidirectional image-question encoder that allows image embeddings to depend on the question being asked (and vice versa). Our in-house model, CLIP-FlanT5, outperforms even the strongest baselines that make use of the proprietary GPT-4V. Interestingly, although we train with only images, VQAScore can also align text with video and 3D models. VQAScore allows researchers to benchmark text-to-visual generation using complex texts that capture the compositional structure of real-world prompts. We introduce GenAI-Bench, a more challenging benchmark with 1,600 compositional text prompts that require parsing scenes, objects, attributes, relationships, and high-order reasoning like comparison and logic. GenAI-Bench also offers over 15,000 human ratings for leading image and video generation models such as Stable Diffusion, DALL-E 3, and Gen2.

Related papers

• ABHINAW: A method for Automatic Evaluation of Typography within AI-Generated Images [0.44241702149260337]
  We introduce a novel evaluation matrix designed explicitly for quantifying the performance of text and typography generation within AI-generated images. Our novel approach to calculate the score takes care of multiple redundancies such as repetition of words, case sensitivity, mixing of words, irregular incorporation of letters etc.
  arXiv  Detail & Related papers  (2024-09-18T11:04:35Z)
• GenAI-Bench: Evaluating and Improving Compositional Text-to-Visual Generation [103.3465421081531]
  VQAScore is a metric measuring the likelihood that a VQA model views an image as accurately depicting the prompt. Ranking by VQAScore is 2x to 3x more effective than other scoring methods like PickScore, HPSv2, and ImageReward. We release a new GenAI-Rank benchmark with over 40,000 human ratings to evaluate scoring metrics on ranking images generated from the same prompt.
  arXiv  Detail & Related papers  (2024-06-19T18:00:07Z)
• T2I-CompBench: A Comprehensive Benchmark for Open-world Compositional Text-to-image Generation [62.71574695256264]
  T2I-CompBench is a comprehensive benchmark for open-world compositional text-to-image generation. We propose several evaluation metrics specifically designed to evaluate compositional text-to-image generation. We introduce a new approach, Generative mOdel fine-tuning with Reward-driven Sample selection (GORS) to boost the compositional text-to-image generation abilities.
  arXiv  Detail & Related papers  (2023-07-12T17:59:42Z)
• TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering [86.38098280689027]
  We introduce an automatic evaluation metric that measures the faithfulness of a generated image to its text input via visual question answering (VQA) We present a comprehensive evaluation of existing text-to-image models using a benchmark consisting of 4K diverse text inputs and 25K questions across 12 categories (object, counting, etc.)
  arXiv  Detail & Related papers  (2023-03-21T14:41:02Z)
• Look, Read and Ask: Learning to Ask Questions by Reading Text in Images [3.3972119795940525]
  We present a novel problem of text-based visual question generation or TextVQG. To address TextVQG, we present an OCR consistent visual question generation model that Looks into the visual content, Reads the scene text, and Asks a relevant and meaningful natural language question.
  arXiv  Detail & Related papers  (2022-11-23T13:52:46Z)
• TAG: Boosting Text-VQA via Text-aware Visual Question-answer Generation [55.83319599681002]
  Text-VQA aims at answering questions that require understanding the textual cues in an image. We develop a new method to generate high-quality and diverse QA pairs by explicitly utilizing the existing rich text available in the scene context of each image.
  arXiv  Detail & Related papers  (2022-08-03T02:18:09Z)
• GIT: A Generative Image-to-text Transformer for Vision and Language [138.91581326369837]
  We train a Generative Image-to-text Transformer, GIT, to unify vision-language tasks such as image/video captioning and question answering. Our model surpasses the human performance for the first time on TextCaps (138.2 vs. 125.5 in CIDEr)
  arXiv  Detail & Related papers  (2022-05-27T17:03:38Z)

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.