UniGenDet: A Unified Generative-Discriminative Framework for Co-Evolutionary Image Generation and Generated Image Detection

• URL: http://arxiv.org/abs/2604.21904v1
• Date: Thu, 23 Apr 2026 17:49:25 GMT
• Title: UniGenDet: A Unified Generative-Discriminative Framework for Co-Evolutionary Image Generation and Generated Image Detection
• Abstract summary: We propose UniGenDet: a Unified generative-discriminative framework for co-evolutionary image Generation and generated image Detection.<n>To bridge the task gap, we design a multimodal symbiotic self-attention mechanism and a unified fine-tuning algorithm.<n>Our method achieves state-of-the-art performance on multiple datasets.
• Score: 68.03391421239583
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In recent years, significant progress has been made in both image generation and generated image detection. Despite their rapid, yet largely independent, development, these two fields have evolved distinct architectural paradigms: the former predominantly relies on generative networks, while the latter favors discriminative frameworks. A recent trend in both domains is the use of adversarial information to enhance performance, revealing potential for synergy. However, the significant architectural divergence between them presents considerable challenges. Departing from previous approaches, we propose UniGenDet: a Unified generative-discriminative framework for co-evolutionary image Generation and generated image Detection. To bridge the task gap, we design a symbiotic multimodal self-attention mechanism and a unified fine-tuning algorithm. This synergy allows the generation task to improve the interpretability of authenticity identification, while authenticity criteria guide the creation of higher-fidelity images. Furthermore, we introduce a detector-informed generative alignment mechanism to facilitate seamless information exchange. Extensive experiments on multiple datasets demonstrate that our method achieves state-of-the-art performance. Code: \href{https://github.com/Zhangyr2022/UniGenDet}{https://github.com/Zhangyr2022/UniGenDet}.

Related papers

• Improving Sample Diversity in Autoregressive Text-to-Image Generation via Cluster Truncation [13.22167262492576]
  We present the first systematic study of sample diversity in AR image generation models.<n>We show that two key properties of AR image generation, persistently high token-level entropy and substantial redundancy in visual token spaces, limit the effectiveness of existing token-level decoding methods for diversity enhancement.<n>We propose $p$-less cluster, a new decoding strategy that performs entropy-based truncation sampling at cluster level rather than at token level.
  arXiv  Detail & Related papers  (2026-07-12T02:14:16Z)
• Diversity Matters: Dataset Diversification and Dual-Branch Network for Generalized AI-Generated Image Detection [2.1410799064827235]
  We present textbfDiversity Matters, a novel framework that emphasizes data diversity and feature domain complementarity for AI-generated image detection.<n>The proposed method introduces a feature-domain similarity filtering mechanism that discards redundant or highly similar samples.<n>Extensive experiments on benchmark datasets demonstrate that the proposed approach significantly improves cross-model and cross-dataset performance.
  arXiv  Detail & Related papers  (2026-03-29T18:29:00Z)
• Open Multimodal Retrieval-Augmented Factual Image Generation [86.34546873830152]
  We introduce ORIG, an agentic open multimodal retrieval-augmented framework for Factual Image Generation (FIG)<n> ORIG iteratively retrieves and filters multimodal evidence from the web and incrementally integrates the refined knowledge into enriched prompts to guide generation.<n>Experiments demonstrate that ORIG substantially improves factual consistency and overall image quality over strong baselines.
  arXiv  Detail & Related papers  (2025-10-26T04:13:31Z)
• ContextGen: Contextual Layout Anchoring for Identity-Consistent Multi-Instance Generation [24.487453636504707]
  We introduce ContextGen, a novel Diffusion Transformer framework for multi-instance generation.<n>We show that ContextGen sets a new state-of-the-art, outperforming existing methods in control precision, identity fidelity, and overall visual quality.
  arXiv  Detail & Related papers  (2025-10-13T04:21:19Z)
• Interleaving Reasoning for Better Text-to-Image Generation [83.69082794730664]
  We introduce Interleaving Reasoning Generation (IRG), a framework that alternates between text-based thinking and image synthesis.<n>To train IRG effectively, we propose Interleaving Reasoning Generation Learning (IRGL), which targets two sub-goals.<n>Experiments show SoTA performance, yielding absolute gains of 5-10 points on GenEval, WISE, TIIF, GenAI-Bench, and OneIG-EN.
  arXiv  Detail & Related papers  (2025-09-08T17:56:23Z)
• UniToken: Harmonizing Multimodal Understanding and Generation through Unified Visual Encoding [84.87802580670579]
  We introduce UniToken, an auto-regressive generation model that encodes visual inputs through a combination of discrete and continuous representations.<n>Our unified visual encoding framework captures both high-level semantics and low-level details, delivering multidimensional information.
  arXiv  Detail & Related papers  (2025-04-06T09:20:49Z)
• Fusion is all you need: Face Fusion for Customized Identity-Preserving Image Synthesis [7.099258248662009]
  Text-to-image (T2I) models have significantly advanced the development of artificial intelligence. However, existing T2I-based methods often struggle to accurately reproduce the appearance of individuals from a reference image. We leverage the pre-trained UNet from Stable Diffusion to incorporate the target face image directly into the generation process.
  arXiv  Detail & Related papers  (2024-09-27T19:31:04Z)
• Generative Unlearning for Any Identity [6.872154067622779]
  In certain domains related to privacy issues, advanced generative models along with strong inversion methods can lead to potential misuses. We propose an essential yet under-explored task called generative identity unlearning, which steers the model not to generate an image of a specific identity. We propose a novel framework, Generative Unlearning for Any Identity (GUIDE), which prevents the reconstruction of a specific identity by unlearning the generator with only a single image.
  arXiv  Detail & Related papers  (2024-05-16T08:00:55Z)
• DiffDis: Empowering Generative Diffusion Model with Cross-Modal Discrimination Capability [75.9781362556431]
  We propose DiffDis to unify the cross-modal generative and discriminative pretraining into one single framework under the diffusion process. We show that DiffDis outperforms single-task models on both the image generation and the image-text discriminative tasks.
  arXiv  Detail & Related papers  (2023-08-18T05:03:48Z)
• T-Person-GAN: Text-to-Person Image Generation with Identity-Consistency and Manifold Mix-Up [16.165889084870116]
  We present an end-to-end approach to generate high-resolution person images conditioned on texts only. We develop an effective generative model to produce person images with two novel mechanisms.
  arXiv  Detail & Related papers  (2022-08-18T07:41:02Z)
• XingGAN for Person Image Generation [149.54517767056382]
  We propose a novel Generative Adversarial Network (XingGAN) for person image generation tasks. XingGAN consists of two generation branches that model the person's appearance and shape information. We show that the proposed XingGAN advances the state-of-the-art performance in terms of objective quantitative scores and subjective visual realness.
  arXiv  Detail & Related papers  (2020-07-17T23:40:22Z)

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.