Learning from Mistakes: Iterative Prompt Relabeling for Text-to-Image Diffusion Model Training

• URL: http://arxiv.org/abs/2312.16204v3
• Date: Wed, 09 Oct 2024 11:39:44 GMT
• Title: Learning from Mistakes: Iterative Prompt Relabeling for Text-to-Image Diffusion Model Training
• Authors: Xinyan Chen, Jiaxin Ge, Tianjun Zhang, Jiaming Liu, Shanghang Zhang,
• Abstract summary: Iterative Prompt Relabeling (IPR) is a novel algorithm that aligns images to text through iterative image sampling and prompt relabeling with feedback. We conduct thorough experiments on SDv2 and SDXL, testing their capability to follow instructions on spatial relations.
• Score: 33.51524424536508
• License:
• Abstract: Diffusion models have shown impressive performance in many domains. However, the model's capability to follow natural language instructions (e.g., spatial relationships between objects, generating complex scenes) is still unsatisfactory. In this work, we propose Iterative Prompt Relabeling (IPR), a novel algorithm that aligns images to text through iterative image sampling and prompt relabeling with feedback. IPR first samples a batch of images conditioned on the text, then relabels the text prompts of unmatched text-image pairs with classifier feedback. We conduct thorough experiments on SDv2 and SDXL, testing their capability to follow instructions on spatial relations. With IPR, we improved up to 15.22% (absolute improvement) on the challenging spatial relation VISOR benchmark, demonstrating superior performance compared to previous RL methods. Our code is publicly available at https://github.com/cxy000000/IPR-RLDF.

Related papers

• Sentence-level Prompts Benefit Composed Image Retrieval [69.78119883060006]
  Composed image retrieval (CIR) is the task of retrieving specific images by using a query that involves both a reference image and a relative caption. We propose to leverage pretrained V-L models, e.g., BLIP-2, to generate sentence-level prompts. Our proposed method performs favorably against the state-of-the-art CIR methods on the Fashion-IQ and CIRR datasets.
  arXiv  Detail & Related papers  (2023-10-09T07:31:44Z)
• LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understanding [85.39419609430453]
  This work enhances the current visual instruction tuning pipeline with text-rich images. We first use publicly available OCR tools to collect results on 422K text-rich images from the LAION dataset. We prompt text-only GPT-4 with recognized texts and image captions to generate 16K conversations, each containing question-answer pairs for text-rich images.
  arXiv  Detail & Related papers  (2023-06-29T17:08:16Z)
• Prompt-Free Diffusion: Taking "Text" out of Text-to-Image Diffusion Models [94.25020178662392]
  Text-to-image (T2I) research has grown explosively in the past year. One pain point persists: the text prompt engineering, and searching high-quality text prompts for customized results is more art than science. In this paper, we take "Text" out of a pre-trained T2I diffusion model, to reduce the burdensome prompt engineering efforts for users.
  arXiv  Detail & Related papers  (2023-05-25T16:30:07Z)
• If at First You Don't Succeed, Try, Try Again: Faithful Diffusion-based Text-to-Image Generation by Selection [53.320946030761796]
  diffusion-based text-to-image (T2I) models can lack faithfulness to the text prompt. We show that large T2I diffusion models are more faithful than usually assumed, and can generate images faithful to even complex prompts. We introduce a pipeline that generates candidate images for a text prompt and picks the best one according to an automatic scoring system.
  arXiv  Detail & Related papers  (2023-05-22T17:59:41Z)
• Bi-directional Training for Composed Image Retrieval via Text Prompt Learning [46.60334745348141]
  Composed image retrieval searches for a target image based on a multi-modal user query comprised of a reference image and modification text. We propose a bi-directional training scheme that leverages such reversed queries and can be applied to existing composed image retrieval architectures. Experiments on two standard datasets show that our novel approach achieves improved performance over a baseline BLIP-based model.
  arXiv  Detail & Related papers  (2023-03-29T11:37:41Z)
• 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)
• STAIR: Learning Sparse Text and Image Representation in Grounded Tokens [84.14528645941128]
  We show that it is possible to build a sparse semantic representation that is as powerful as, or even better than, dense presentations. We extend the CLIP model and build a sparse text and image representation (STAIR), where the image and text are mapped to a sparse token space. It significantly outperforms a CLIP model with +$4.9%$ and +$4.3%$ absolute Recall@1 improvement.
  arXiv  Detail & Related papers  (2023-01-30T17:21:30Z)
• InDiReCT: Language-Guided Zero-Shot Deep Metric Learning for Images [4.544151613454639]
  We argue that depending on the application, users of image retrieval systems have different and changing similarity notions. We present Language-Guided Zero-Shot Deep Metric Learning (LanZ-DML) as a new DML setting. InDiReCT is a model for LanZ-DML on images that exclusively uses a few text prompts for training.
  arXiv  Detail & Related papers  (2022-11-23T08:09:50Z)
• Deep Multimodal Image-Text Embeddings for Automatic Cross-Media Retrieval [0.0]
  We introduce an end-to-end deep multimodal convolutional-recurrent network for learning both vision and language representations simultaneously. The model learns which pairs are a match (positive) and which ones are a mismatch (negative) using a hinge-based triplet ranking.
  arXiv  Detail & Related papers  (2020-02-23T23:58:04Z)

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.