paper-with-me

홈 › Papers

Beyond Semantic Features: Pixel-level Mapping for Generalized AI-Generated Image Detection

2025-12-19 · Chenming Zhou, Jiaan Wang, Yu Li, Lei Li, Juan Cao, Sheng Tang arxiv

The rapid evolution of generative technologies necessitates reliable methods for detecting AI-generated images. A critical limitation of current detectors is their failure to generalize to images from unseen generative models, as they often overfit to source-specific semantic cues rather than learning universal generative artifacts. To overcome this, we introduce a simple yet remarkably effective pixel-level mapping pre-processing step to disrupt the pixel value distribution of images and break the fragile, non-essential semantic patterns that detectors commonly exploit as shortcuts. This forces the detector to focus on more fundamental and generalizable high-frequency traces inherent to the image generation process. Through comprehensive experiments on GAN and diffusion-based generators, we show that our approach significantly boosts the cross-generator performance of state-of-the-art detectors. Extensive analysis further verifies our hypothesis that the disruption of semantic cues is the key to generalization.

📄 PDF Abstract BibTeX arXiv:2512.17350

Code (0)

등록된 구현이 없습니다.

Tasks

Image Generation

Similar Papers 제목 키워드 기반

Dense RGB-D semantic mapping with Pixel-Voxel neural network

2017-09-30 · Cheng Zhao, Li Sun, Pulak Purkait, Rustam Stolkin

For intelligent robotics applications, extending 3D mapping to 3D semantic mapping enables robots to, not only localize themselves with respect to the scene's geometrical features but also simultaneously understand the h…

3D ReconstructionGPUScene UnderstandingSemantic Segmentation

From Pixels to Buildings: End-to-end Probabilistic Deep Networks for Large-scale Semantic Mapping

2018-12-31 · Kaiyu Zheng, Andrzej Pronobis

We introduce TopoNets, end-to-end probabilistic deep networks for modeling semantic maps with structure reflecting the topology of large-scale environments. TopoNets build a unified deep network spanning multiple levels …

Natural Language-Driven Global Mapping of Martian Landforms

2026-01-22 · Yiran Wang, Shuoyuan Wang, Zhaoran Wei, Jiannan Zhao 외 arxiv

Planetary surfaces are typically analyzed using high-level semantic concepts in natural language, yet vast orbital image archives remain organized at the pixel level. This mismatch limits scalable, open-ended exploration…

Semantic Retrieval

Zoom-CAM: Generating Fine-grained Pixel Annotations from Image Labels

2020-10-16 · Xiangwei Shi, Seyran Khademi, Yunqiang Li, Jan van Gemert

Current weakly supervised object localization and segmentation rely on class-discriminative visualization techniques to generate pseudo-labels for pixel-level training. Such visualization methods, including class activat…

Object LocalizationSegmentationSemantic SegmentationWeakly-Supervised Object Localization+2

FashionMirror: Co-Attention Feature-Remapping Virtual Try-On With Sequential Template Poses

2021-01-01 · ICCV 2021 10 · Chieh-Yun Chen, Ling Lo, Pin-Jui Huang, Hong-Han Shuai 외

Virtual try-on tasks have drawn increased attention. Prior arts focus on tackling this task via warping clothes and fusing the information at the pixel level with the help of semantic segmentation. However, conductin…

SegmentationSemantic SegmentationVirtual Try-on