Adaptive Forensic Feature Refinement via Intrinsic Importance Perception

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yang, Jiazhen, Zheng, Junjun, Chen, Kejia, Kong, Xiangheng, Lei, Jie, Feng, Zunlei, Hu, Bingde, Gao, Yang
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908985548865536
author Yang, Jiazhen
Zheng, Junjun
Chen, Kejia
Kong, Xiangheng
Lei, Jie
Feng, Zunlei
Hu, Bingde
Gao, Yang
author_facet Yang, Jiazhen
Zheng, Junjun
Chen, Kejia
Kong, Xiangheng
Lei, Jie
Feng, Zunlei
Hu, Bingde
Gao, Yang
contents With the rapid development of generative models and multimodal content editing technologies, the key challenge faced by synthetic image detection (SID) lies in cross-distribution generalization to unknown generation sources. In recent years, visual foundation models (VFM), which acquire rich visual priors through large scale image-text alignment pretraining, have become a promising technical route for improving the generalization ability of SID. However, existing VFM-based methods remain relatively coarse-grained in their adaptation strategies. They typically either directly use the final layer representations of VFM or simply fuse multi layer features, lacking explicit modeling of the optimal representational hierarchy for transferable forgery cues. Meanwhile, although directly fine-tuning VFM can enhance task adaptation, it may also damage the cross-modal pretrained structure that supports open-set generalization. To address this task specific tension, we reformulate VFM adaptation for SID as a joint optimization problem: it is necessary both to identify the critical representational layer that is more suitable for carrying forgery discriminative information and to constrain the disturbance caused by task knowledge injection to the pretrained structure. Based on this, we propose I2P, an SID framework centered on intrinsic importance perception. I2P first adaptively identifies the critical layer representations that are most discriminative for SID, and then constrains task-driven parameter updates within a low sensitivity parameter subspace, thereby improving task specificity while preserving the transferable structure of pretrained representations as much as possible.
format Preprint
id arxiv_https___arxiv_org_abs_2604_16879
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Adaptive Forensic Feature Refinement via Intrinsic Importance Perception
Yang, Jiazhen
Zheng, Junjun
Chen, Kejia
Kong, Xiangheng
Lei, Jie
Feng, Zunlei
Hu, Bingde
Gao, Yang
Computer Vision and Pattern Recognition
With the rapid development of generative models and multimodal content editing technologies, the key challenge faced by synthetic image detection (SID) lies in cross-distribution generalization to unknown generation sources. In recent years, visual foundation models (VFM), which acquire rich visual priors through large scale image-text alignment pretraining, have become a promising technical route for improving the generalization ability of SID. However, existing VFM-based methods remain relatively coarse-grained in their adaptation strategies. They typically either directly use the final layer representations of VFM or simply fuse multi layer features, lacking explicit modeling of the optimal representational hierarchy for transferable forgery cues. Meanwhile, although directly fine-tuning VFM can enhance task adaptation, it may also damage the cross-modal pretrained structure that supports open-set generalization. To address this task specific tension, we reformulate VFM adaptation for SID as a joint optimization problem: it is necessary both to identify the critical representational layer that is more suitable for carrying forgery discriminative information and to constrain the disturbance caused by task knowledge injection to the pretrained structure. Based on this, we propose I2P, an SID framework centered on intrinsic importance perception. I2P first adaptively identifies the critical layer representations that are most discriminative for SID, and then constrains task-driven parameter updates within a low sensitivity parameter subspace, thereby improving task specificity while preserving the transferable structure of pretrained representations as much as possible.
title Adaptive Forensic Feature Refinement via Intrinsic Importance Perception
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.16879