Relation Rectification in Diffusion Model

• URL: http://arxiv.org/abs/2403.20249v1
• Date: Fri, 29 Mar 2024 15:54:36 GMT
• Title: Relation Rectification in Diffusion Model
• Authors: Yinwei Wu, Xingyi Yang, Xinchao Wang,
• Abstract summary: We introduce a novel task termed Relation Rectification, aiming to refine the model to accurately represent a given relationship it initially fails to generate. We propose an innovative solution utilizing a Heterogeneous Graph Convolutional Network (HGCN) The lightweight HGCN adjusts the text embeddings generated by the text encoder, ensuring the accurate reflection of the textual relation in the embedding space.
• Score: 64.84686527988809
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Despite their exceptional generative abilities, large text-to-image diffusion models, much like skilled but careless artists, often struggle with accurately depicting visual relationships between objects. This issue, as we uncover through careful analysis, arises from a misaligned text encoder that struggles to interpret specific relationships and differentiate the logical order of associated objects. To resolve this, we introduce a novel task termed Relation Rectification, aiming to refine the model to accurately represent a given relationship it initially fails to generate. To address this, we propose an innovative solution utilizing a Heterogeneous Graph Convolutional Network (HGCN). It models the directional relationships between relation terms and corresponding objects within the input prompts. Specifically, we optimize the HGCN on a pair of prompts with identical relational words but reversed object orders, supplemented by a few reference images. The lightweight HGCN adjusts the text embeddings generated by the text encoder, ensuring the accurate reflection of the textual relation in the embedding space. Crucially, our method retains the parameters of the text encoder and diffusion model, preserving the model's robust performance on unrelated descriptions. We validated our approach on a newly curated dataset of diverse relational data, demonstrating both quantitative and qualitative enhancements in generating images with precise visual relations. Project page: https://wuyinwei-hah.github.io/rrnet.github.io/.

Related papers

• Composing Object Relations and Attributes for Image-Text Matching [70.47747937665987]
  This work introduces a dual-encoder image-text matching model, leveraging a scene graph to represent captions with nodes for objects and attributes interconnected by relational edges. Our model efficiently encodes object-attribute and object-object semantic relations, resulting in a robust and fast-performing system.
  arXiv  Detail & Related papers  (2024-06-17T17:56:01Z)
• SG-Adapter: Enhancing Text-to-Image Generation with Scene Graph Guidance [46.77060502803466]
  We introduce the Scene Graph Adapter(SG-Adapter), leveraging the structured representation of scene graphs to rectify inaccuracies in the original text embeddings. The SG-Adapter's explicit and non-fully connected graph representation greatly improves the fully connected, transformer-based text representations.
  arXiv  Detail & Related papers  (2024-05-24T08:00:46Z)
• Scene-Graph ViT: End-to-End Open-Vocabulary Visual Relationship Detection [14.22646492640906]
  We propose a simple and highly efficient decoder-free architecture for open-vocabulary visual relationship detection. Our model consists of a Transformer-based image encoder that represents objects as tokens and models their relationships implicitly. Our approach achieves state-of-the-art relationship detection performance on Visual Genome and on the large-vocabulary GQA benchmark at real-time inference speeds.
  arXiv  Detail & Related papers  (2024-03-21T10:15:57Z)
• Zero-shot Referring Expression Comprehension via Structural Similarity Between Images and Captions [6.231370972617915]
  Zero-shot referring expression comprehension aims at localizing bounding boxes in an image corresponding to provided textual prompts. Existing vision-language alignment models, e.g., CLIP, struggle with both aspects so cannot be directly used for this task. We leverage large foundation models to disentangle both images and texts into triplets in the format of (subject, predicate, object)
  arXiv  Detail & Related papers  (2023-11-28T18:55:37Z)
• Exposing and Mitigating Spurious Correlations for Cross-Modal Retrieval [89.30660533051514]
  Cross-modal retrieval methods are the preferred tool to search databases for the text that best matches a query image and vice versa. Image-text retrieval models commonly learn to spurious correlations in the training data, such as frequent object co-occurrence. We introduce ODmAP@k, an object decorrelation metric that measures a model's robustness to spurious correlations in the training data.
  arXiv  Detail & Related papers  (2023-04-06T21:45:46Z)
• Unified Visual Relationship Detection with Vision and Language Models [89.77838890788638]
  This work focuses on training a single visual relationship detector predicting over the union of label spaces from multiple datasets. We propose UniVRD, a novel bottom-up method for Unified Visual Relationship Detection by leveraging vision and language models. Empirical results on both human-object interaction detection and scene-graph generation demonstrate the competitive performance of our model.
  arXiv  Detail & Related papers  (2023-03-16T00:06:28Z)
• What Are You Token About? Dense Retrieval as Distributions Over the Vocabulary [68.77983831618685]
  We propose to interpret the vector representations produced by dual encoders by projecting them into the model's vocabulary space. We show that the resulting projections contain rich semantic information, and draw connection between them and sparse retrieval.
  arXiv  Detail & Related papers  (2022-12-20T16:03:25Z)
• Expressing Objects just like Words: Recurrent Visual Embedding for Image-Text Matching [102.62343739435289]
  Existing image-text matching approaches infer the similarity of an image-text pair by capturing and aggregating the affinities between the text and each independent object of the image. We propose a Dual Path Recurrent Neural Network (DP-RNN) which processes images and sentences symmetrically by recurrent neural networks (RNN) Our model achieves the state-of-the-art performance on Flickr30K dataset and competitive performance on MS-COCO dataset.
  arXiv  Detail & Related papers  (2020-02-20T00:51:01Z)

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.