PEA-Diffusion: Parameter-Efficient Adapter with Knowledge Distillation in non-English Text-to-Image Generation

• URL: http://arxiv.org/abs/2311.17086v2
• Date: Wed, 24 Jul 2024 01:41:01 GMT
• Title: PEA-Diffusion: Parameter-Efficient Adapter with Knowledge Distillation in non-English Text-to-Image Generation
• Abstract summary: We propose a plug-and-play language transfer method based on knowledge distillation. All we need to do is train a lightweight-like parameter-efficient adapter (PEA) with only 6M parameters under teacher knowledge distillation. We are surprised to find that freezing the parameters of UNet can still achieve remarkable performance on the language-specific prompt evaluation set.
• Score: 6.528169059491259
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Text-to-image diffusion models are well-known for their ability to generate realistic images based on textual prompts. However, the existing works have predominantly focused on English, lacking support for non-English text-to-image models. The most commonly used translation methods cannot solve the generation problem related to language culture, while training from scratch on a specific language dataset is prohibitively expensive. In this paper, we are inspired to propose a simple plug-and-play language transfer method based on knowledge distillation. All we need to do is train a lightweight MLP-like parameter-efficient adapter (PEA) with only 6M parameters under teacher knowledge distillation along with a small parallel data corpus. We are surprised to find that freezing the parameters of UNet can still achieve remarkable performance on the language-specific prompt evaluation set, demonstrating that PEA can stimulate the potential generation ability of the original UNet. Additionally, it closely approaches the performance of the English text-to-image model on a general prompt evaluation set. Furthermore, our adapter can be used as a plugin to achieve significant results in downstream tasks in cross-lingual text-to-image generation. Code will be available at: https://github.com/OPPO-Mente-Lab/PEA-Diffusion

Related papers

• Brazilian Portuguese Image Captioning with Transformers: A Study on Cross-Native-Translated Dataset [41.02122939888977]
  This study proposes a cross-native evaluation of Transformer-based vision and language models for Brazilian Portuguese IC.<n>We use a version of Flickr30K comprised of captions manually created by native Brazilian Portuguese speakers and compare it to a version with captions automatically translated from English to Portuguese.<n>Our findings show that Swin-DistilBERTimbau consistently outperforms other models, demonstrating strong generalization across datasets.
  arXiv  Detail & Related papers  (2026-01-30T23:12:03Z)
• uCLIP: Parameter-Efficient Multilingual Extension of Vision-Language Models with Unpaired Data [3.364569898365253]
  We propose a lightweight and data-efficient framework for multilingual vision-language alignment.<n>Our approach requires no image-text pairs or text-text pairs and freezes both the pretrained image encoder and multilingual text encoder during training.<n>This minimal training setup enables robust multilingual alignment even for languages with limited supervision.
  arXiv  Detail & Related papers  (2025-11-17T06:34:49Z)
• MuLan: Adapting Multilingual Diffusion Models for Hundreds of Languages with Negligible Cost [39.43930856789352]
  We find that, unlike models tuned on high-quality images with multilingual annotations, leveraging text encoders pre-trained on widely available, noisy Internet image-text pairs significantly enhances data efficiency. We introduce MuLan, Multi-Language adapter, a lightweight language adapter with fewer than 20M parameters, trained alongside a frozen text encoder and image diffusion model.
  arXiv  Detail & Related papers  (2024-12-02T08:38:19Z)
• Conditional Text-to-Image Generation with Reference Guidance [81.99538302576302]
  This paper explores using additional conditions of an image that provides visual guidance of the particular subjects for diffusion models to generate. We develop several small-scale expert plugins that efficiently endow a Stable Diffusion model with the capability to take different references. Our expert plugins demonstrate superior results than the existing methods on all tasks, each containing only 28.55M trainable parameters.
  arXiv  Detail & Related papers  (2024-11-22T21:38:51Z)
• An Empirical Study and Analysis of Text-to-Image Generation Using Large Language Model-Powered Textual Representation [21.154973705998945]
  Existing methods leverage the text encoder of the CLIP model to represent input prompts. Large Language Models (LLMs) offer multilingual input, accommodate longer context, and achieve superior text representation. We propose a lightweight adapter that enables fast training of the text-to-image model using the textual representations from LLMs.
  arXiv  Detail & Related papers  (2024-05-21T16:35:02Z)
• AltDiffusion: A Multilingual Text-to-Image Diffusion Model [4.534546889526814]
  We present AltDiffusion, a novel multilingual T2I diffusion model that supports eighteen different languages. Specifically, we first train a multilingual text encoder based on the knowledge distillation. Then we plug it into a pretrained English-only diffusion model and train the model with a two-stage schema to enhance the multilingual capability.
  arXiv  Detail & Related papers  (2023-08-19T11:52:12Z)
• Stop Pre-Training: Adapt Visual-Language Models to Unseen Languages [3.3227703089509304]
  We propose a simple yet efficient approach to adapt Vision-Language Pre-training to unseen languages using MPLM. Our approach does not require image input and primarily uses machine translation, eliminating the need for target language data.
  arXiv  Detail & Related papers  (2023-06-29T08:20:57Z)
• Language Quantized AutoEncoders: Towards Unsupervised Text-Image Alignment [81.73717488887938]
  Language-Quantized AutoEncoder (LQAE) learns to align text-image data in an unsupervised manner by leveraging pretrained language models. LQAE learns to represent similar images with similar clusters of text tokens, thereby aligning these two modalities without the use of aligned text-image pairs. This enables few-shot image classification with large language models (e.g., GPT-3) as well as linear classification of images based on BERT text features.
  arXiv  Detail & Related papers  (2023-02-02T06:38:44Z)
• 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)
• Language-Family Adapters for Low-Resource Multilingual Neural Machine Translation [129.99918589405675]
  Large multilingual models trained with self-supervision achieve state-of-the-art results in a wide range of natural language processing tasks. Multilingual fine-tuning improves performance on low-resource languages but requires modifying the entire model and can be prohibitively expensive. We propose training language-family adapters on top of mBART-50 to facilitate cross-lingual transfer.
  arXiv  Detail & Related papers  (2022-09-30T05:02:42Z)
• Align before Fuse: Vision and Language Representation Learning with Momentum Distillation [52.40490994871753]
  We introduce a contrastive loss to representations BEfore Fusing (ALBEF) through cross-modal attention. We propose momentum distillation, a self-training method which learns from pseudo-targets produced by a momentum model. ALBEF achieves state-of-the-art performance on multiple downstream vision-language tasks.
  arXiv  Detail & Related papers  (2021-07-16T00:19:22Z)
• VECO: Variable and Flexible Cross-lingual Pre-training for Language Understanding and Generation [77.82373082024934]
  We plug a cross-attention module into the Transformer encoder to explicitly build the interdependence between languages. It can effectively avoid the degeneration of predicting masked words only conditioned on the context in its own language. The proposed cross-lingual model delivers new state-of-the-art results on various cross-lingual understanding tasks of the XTREME benchmark.
  arXiv  Detail & Related papers  (2020-10-30T03:41:38Z)

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.