Salvato in:
Dettagli Bibliografici
Autori principali: Cheng, Yi, Xu, Ziwei, Lin, Dongyun, Cheng, Harry, Wong, Yongkang, Sun, Ying, Lim, Joo Hwee, Kankanhalli, Mohan
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2405.12538
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914803904151552
author Cheng, Yi
Xu, Ziwei
Lin, Dongyun
Cheng, Harry
Wong, Yongkang
Sun, Ying
Lim, Joo Hwee
Kankanhalli, Mohan
author_facet Cheng, Yi
Xu, Ziwei
Lin, Dongyun
Cheng, Harry
Wong, Yongkang
Sun, Ying
Lim, Joo Hwee
Kankanhalli, Mohan
contents For visual content generation, discrepancies between user intentions and the generated content have been a longstanding problem. This discrepancy arises from two main factors. First, user intentions are inherently complex, with subtle details not fully captured by input prompts. The absence of such details makes it challenging for generative models to accurately reflect the intended meaning, leading to a mismatch between the desired and generated output. Second, generative models trained on visual-label pairs lack the comprehensive knowledge to accurately represent all aspects of the input data in their generated outputs. To address these challenges, we propose a knowledge-enhanced iterative refinement framework for visual content generation. We begin by analyzing and identifying the key challenges faced by existing generative models. Then, we introduce various knowledge sources, including human insights, pre-trained models, logic rules, and world knowledge, which can be leveraged to address these challenges. Furthermore, we propose a novel visual generation framework that incorporates a knowledge-based feedback module to iteratively refine the generation process. This module gradually improves the alignment between the generated content and user intentions. We demonstrate the efficacy of the proposed framework through preliminary results, highlighting the potential of knowledge-enhanced generative models for intention-aligned content generation.
format Preprint
id arxiv_https___arxiv_org_abs_2405_12538
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Bridging the Intent Gap: Knowledge-Enhanced Visual Generation
Cheng, Yi
Xu, Ziwei
Lin, Dongyun
Cheng, Harry
Wong, Yongkang
Sun, Ying
Lim, Joo Hwee
Kankanhalli, Mohan
Computer Vision and Pattern Recognition
For visual content generation, discrepancies between user intentions and the generated content have been a longstanding problem. This discrepancy arises from two main factors. First, user intentions are inherently complex, with subtle details not fully captured by input prompts. The absence of such details makes it challenging for generative models to accurately reflect the intended meaning, leading to a mismatch between the desired and generated output. Second, generative models trained on visual-label pairs lack the comprehensive knowledge to accurately represent all aspects of the input data in their generated outputs. To address these challenges, we propose a knowledge-enhanced iterative refinement framework for visual content generation. We begin by analyzing and identifying the key challenges faced by existing generative models. Then, we introduce various knowledge sources, including human insights, pre-trained models, logic rules, and world knowledge, which can be leveraged to address these challenges. Furthermore, we propose a novel visual generation framework that incorporates a knowledge-based feedback module to iteratively refine the generation process. This module gradually improves the alignment between the generated content and user intentions. We demonstrate the efficacy of the proposed framework through preliminary results, highlighting the potential of knowledge-enhanced generative models for intention-aligned content generation.
title Bridging the Intent Gap: Knowledge-Enhanced Visual Generation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.12538