PPM-CLIP is proposed, a new framework that shifts from static classification to conditional generative modeling based on the CLIP vision-language model, and a Probabilistic Prompt Modeling module is used as a generator that produces an adaptive distribution of prompts according to the input image.
The proposed Attention-Based Deep Learning Pipeline of AI-Created Image Recognition incorporates three integrated branches, including low-level statistical feature extraction, high-level semantic representation learning, and attention-based feature refinement mechanism, which support the robustness and generalization a...
Nadia Ali· Al-Noor Journal of Engineeri...· 0 citations
DECODE is proposed, a decoupled continual detection framework that jointly mitigates representation- and decision-level forgetting and introduces Subspace Diversity Regularization to preserve diverse forensic representations and Closed-Form Decision Alignment to recalibrate the shared classification head after each ada...
Zihao Cai, Xing-Hang Li, Ruiyan Yang et al.· arXiv.org· 0 citations
This work establishes a new paradigm for generated image detection by recasting the detection task as a problem of machine unlearning, and introduces two detection methods: data-free detection, which prunes model parameters to induce unlearning without data access, and data-driven detection, which optimizes LVMs to unl...
Jun Nie, Yonggang Zhang, Tongliang Liu et al.· 0 citations
GFRE employs a lightweight autoencoder to model the reconstructability of image representations, producing a reconstruction signal that is inherently generator-agnostic and transferable across diverse generative processes, enabling efficient and scalable deployment.
Qing-Hui He, Hai-Feng Zhang, Bo Liu et al.· Proceedings of the Thirty-Fi...· 0 citations
This work formats the AI-generated image detection task as a Visual Question Answering problem, leveraging a fine-tuned vision-language framework to fully exploit the complementary information between visual and textual modalities, and proposes a novel high-resolution AI-generated image detector, termed LHSDet.
Qian Yao, Jun-Jie Huang, Yong-Jun Wang et al.· 0 citations
Strong sensitivity to the training prior, data-efficiency of moment-based heads, and representation dependence of Gaussian shift metrics, motivating (prior, encoder, head)-level reporting and stronger analytical baselines for AIGI transfer are quantified.
Shashank Kotyan, Makoto Shing, Yuki Imajuku et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
