Z-Magic: Zero-shot Multiple Attributes Guided Image Creator

• URL: http://arxiv.org/abs/2503.12124v1
• Date: Sat, 15 Mar 2025 13:07:58 GMT
• Title: Z-Magic: Zero-shot Multiple Attributes Guided Image Creator
• Authors: Yingying Deng, Xiangyu He, Fan Tang, Weiming Dong,
• Abstract summary: We reformulate multi-attribute creation from a conditional probability theory perspective and tackle the challenging zero-shot setting.<n>By explicitly modeling the dependencies between attributes, we further enhance the coherence of generated images.<n>We identify connections between multi-attribute customization and multi-task learning, effectively addressing the high computing cost encountered in multi-attribute synthesis.
• Score: 24.88532732093652
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The customization of multiple attributes has gained popularity with the rising demand for personalized content creation. Despite promising empirical results, the contextual coherence between different attributes has been largely overlooked. In this paper, we argue that subsequent attributes should follow the multivariable conditional distribution introduced by former attribute creation. In light of this, we reformulate multi-attribute creation from a conditional probability theory perspective and tackle the challenging zero-shot setting. By explicitly modeling the dependencies between attributes, we further enhance the coherence of generated images across diverse attribute combinations. Furthermore, we identify connections between multi-attribute customization and multi-task learning, effectively addressing the high computing cost encountered in multi-attribute synthesis. Extensive experiments demonstrate that Z-Magic outperforms existing models in zero-shot image generation, with broad implications for AI-driven design and creative applications.

Related papers

• FiVA: Fine-grained Visual Attribute Dataset for Text-to-Image Diffusion Models [112.94440113631897]
  Current methods attempt to distill identity and style from source images.<n>"style" is a broad concept that includes texture, color, and artistic elements, but does not cover other important attributes such as lighting and dynamics.<n>We formulate a more effective approach to decompose the aesthetics of a picture into specific visual attributes, allowing users to apply characteristics such as lighting, texture, and dynamics from different images.
  arXiv  Detail & Related papers  (2024-12-10T17:02:58Z)
• Hybrid Discriminative Attribute-Object Embedding Network for Compositional Zero-Shot Learning [83.10178754323955]
  Hybrid Discriminative Attribute-Object Embedding (HDA-OE) network is proposed to solve the problem of complex interactions between attributes and object visual representations.<n>To increase the variability of training data, HDA-OE introduces an attribute-driven data synthesis (ADDS) module.<n>To further improve the discriminative ability of the model, HDA-OE introduces the subclass-driven discriminative embedding (SDDE) module.<n>The proposed model has been evaluated on three benchmark datasets, and the results verify its effectiveness and reliability.
  arXiv  Detail & Related papers  (2024-11-28T09:50:25Z)
• ARMADA: Attribute-Based Multimodal Data Augmentation [93.05614922383822]
  Attribute-based Multimodal Data Augmentation (ARMADA) is a novel multimodal data augmentation method via knowledge-guided manipulation of visual attributes. ARMADA is a novel multimodal data generation framework that: (i) extracts knowledge-grounded attributes from symbolic KBs for semantically consistent yet distinctive image-text pair generation. This also highlights the need to leverage external knowledge proxies for enhanced interpretability and real-world grounding.
  arXiv  Detail & Related papers  (2024-08-19T15:27:25Z)
• MAC: A Benchmark for Multiple Attributes Compositional Zero-Shot Learning [33.12021227971062]
  Compositional Zero-Shot Learning (CZSL) aims to learn semantic primitives (attributes and objects) from seen neglecting and recognize unseen attribute-object compositions. We introduce the Multi-Attribute Composition dataset, encompassing 18,217 images and 11,067 compositions with comprehensive, representative, and diverse attribute annotations. Our dataset supports deeper semantic understanding and higher-order attribute associations, providing a more realistic and challenging benchmark for the CZSL task.
  arXiv  Detail & Related papers  (2024-06-18T16:24:48Z)
• Attribute-Aware Deep Hashing with Self-Consistency for Large-Scale Fine-Grained Image Retrieval [65.43522019468976]
  We propose attribute-aware hashing networks with self-consistency for generating attribute-aware hash codes. We develop an encoder-decoder structure network of a reconstruction task to unsupervisedly distill high-level attribute-specific vectors. Our models are equipped with a feature decorrelation constraint upon these attribute vectors to strengthen their representative abilities.
  arXiv  Detail & Related papers  (2023-11-21T08:20:38Z)
• UMAAF: Unveiling Aesthetics via Multifarious Attributes of Images [16.647573404422175]
  We propose the Unified Multi-attribute Aesthetic Assessment Framework (UMAAF) to model both absolute and relative attributes of images. UMAAF achieves state-of-the-art performance on TAD66K and AVA datasets.
  arXiv  Detail & Related papers  (2023-11-19T11:57:01Z)
• AdaTag: Multi-Attribute Value Extraction from Product Profiles with Adaptive Decoding [55.89773725577615]
  We present AdaTag, which uses adaptive decoding to handle attribute extraction. Our experiments on a real-world e-Commerce dataset show marked improvements over previous methods.
  arXiv  Detail & Related papers  (2021-06-04T07:54:11Z)
• Learning to Infer Unseen Attribute-Object Compositions [55.58107964602103]
  A graph-based model is proposed that can flexibly recognize both single- and multi-attribute-object compositions. We build a large-scale Multi-Attribute dataset with 116,099 images and 8,030 composition categories.
  arXiv  Detail & Related papers  (2020-10-27T14:57:35Z)
• Prominent Attribute Modification using Attribute Dependent Generative Adversarial Network [4.654937118111992]
  The proposed approach is based on two generators and two discriminators that utilize the binary as well as the real representation of the attributes. Experiments on the CelebA dataset show that our method effectively performs the multiple attribute editing with preserving other facial details intactly.
  arXiv  Detail & Related papers  (2020-04-24T13:38:05Z)

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.