Empowering Backbone Models for Visual Text Generation with Input Granularity Control and Glyph-Aware Training

• URL: http://arxiv.org/abs/2410.04439v1
• Date: Sun, 6 Oct 2024 10:25:39 GMT
• Title: Empowering Backbone Models for Visual Text Generation with Input Granularity Control and Glyph-Aware Training
• Authors: Wenbo Li, Guohao Li, Zhibin Lan, Xue Xu, Wanru Zhuang, Jiachen Liu, Xinyan Xiao, Jinsong Su,
• Abstract summary: Diffusion-based text-to-image models have demonstrated impressive achievements in diversity and aesthetics but struggle to generate images with visual texts. Existing backbone models have limitations such as misspelling, failing to generate texts, and lack of support for Chinese text. We propose a series of methods, aiming to empower backbone models to generate visual texts in English and Chinese.
• Score: 68.41837295318152
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Diffusion-based text-to-image models have demonstrated impressive achievements in diversity and aesthetics but struggle to generate images with legible visual texts. Existing backbone models have limitations such as misspelling, failing to generate texts, and lack of support for Chinese text, but their development shows promising potential. In this paper, we propose a series of methods, aiming to empower backbone models to generate visual texts in English and Chinese. We first conduct a preliminary study revealing that Byte Pair Encoding (BPE) tokenization and the insufficient learning of cross-attention modules restrict the performance of the backbone models. Based on these observations, we make the following improvements: (1) We design a mixed granularity input strategy to provide more suitable text representations; (2) We propose to augment the conventional training objective with three glyph-aware training losses, which enhance the learning of cross-attention modules and encourage the model to focus on visual texts. Through experiments, we demonstrate that our methods can effectively empower backbone models to generate semantic relevant, aesthetically appealing, and accurate visual text images, while maintaining their fundamental image generation quality.

Related papers

• Text Image Generation for Low-Resource Languages with Dual Translation Learning [0.0]
  This study proposes a novel approach that generates text images in low-resource languages by emulating the style of real text images from high-resource languages. The training of this model involves dual translation tasks, where it transforms plain text images into either synthetic or real text images. To enhance the accuracy and variety of generated text images, we introduce two guidance techniques.
  arXiv  Detail & Related papers  (2024-09-26T11:23:59Z)
• ARTIST: Improving the Generation of Text-rich Images with Disentangled Diffusion Models [52.23899502520261]
  We introduce a new framework named ARTIST to focus on the learning of text structures. We finetune a visual diffusion model, enabling it to assimilate textual structure information from the pretrained textual model. Empirical results on the MARIO-Eval benchmark underscore the effectiveness of the proposed method, showing an improvement of up to 15% in various metrics.
  arXiv  Detail & Related papers  (2024-06-17T19:31:24Z)
• Refining Text-to-Image Generation: Towards Accurate Training-Free Glyph-Enhanced Image Generation [5.55027585813848]
  The capability to generate visual text is crucial, offering both academic interest and a wide range of practical applications. We introduce a benchmark, LenCom-Eval, specifically designed for testing models' capability in generating images with Lengthy and Complex visual text. We demonstrate notable improvements across a range of evaluation metrics, including CLIPScore, OCR precision, recall, F1 score, accuracy, and edit distance scores.
  arXiv  Detail & Related papers  (2024-03-25T04:54:49Z)
• Expedited Training of Visual Conditioned Language Generation via Redundancy Reduction [61.16125290912494]
  $textEVL_textGen$ is a framework designed for the pre-training of visually conditioned language generation models. We show that our approach accelerates the training of vision-language models by a factor of 5 without a noticeable impact on overall performance.
  arXiv  Detail & Related papers  (2023-10-05T03:40:06Z)
• ViLTA: Enhancing Vision-Language Pre-training through Textual Augmentation [35.05755930636518]
  We propose ViLTA, comprising of two components to further facilitate the model to learn fine-grained representations among image-text pairs. For Masked Language Modeling (MLM), we propose a cross-distillation method to generate soft labels to enhance the robustness of model. For Image-Text Matching (ITM), we leverage the current language encoder to synthesize hard negatives based on the context of language input.
  arXiv  Detail & Related papers  (2023-08-31T12:46:36Z)
• Grounding Language Models to Images for Multimodal Inputs and Outputs [89.30027812161686]
  We propose an efficient method to ground pretrained text-only language models to the visual domain. We process arbitrarily interleaved image-and-text data, and generate text interleaved with retrieved images.
  arXiv  Detail & Related papers  (2023-01-31T18:33:44Z)
• Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models [103.61066310897928]
  Recent text-to-image generative models have demonstrated an unparalleled ability to generate diverse and creative imagery guided by a target text prompt. While revolutionary, current state-of-the-art diffusion models may still fail in generating images that fully convey the semantics in the given text prompt. We analyze the publicly available Stable Diffusion model and assess the existence of catastrophic neglect, where the model fails to generate one or more of the subjects from the input prompt. We introduce the concept of Generative Semantic Nursing (GSN), where we seek to intervene in the generative process on the fly during inference time to improve the faithfulness
  arXiv  Detail & Related papers  (2023-01-31T18:10:38Z)
• On Advances in Text Generation from Images Beyond Captioning: A Case Study in Self-Rationalization [89.94078728495423]
  We show that recent advances in each modality, CLIP image representations and scaling of language models, do not consistently improve multimodal self-rationalization of tasks with multimodal inputs. Our findings call for a backbone modelling approach that can be built on to advance text generation from images and text beyond image captioning.
  arXiv  Detail & Related papers  (2022-05-24T00:52:40Z)

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.