paper-with-me

홈 › Papers

Multi-spectral Class Center Network for Face Manipulation Detection and Localization

2023-05-18 · Changtao Miao, Qi Chu, Zhentao Tan, Zhenchao Jin, Tao Gong, Wanyi Zhuang, Yue Wu, Bin Liu, Honggang Hu, Nenghai Yu

As deepfake content proliferates online, advancing face manipulation forensics has become crucial. To combat this emerging threat, previous methods mainly focus on studying how to distinguish authentic and manipulated face images. Although impressive, image-level classification lacks explainability and is limited to specific application scenarios, spurring recent research on pixel-level prediction for face manipulation forensics. However, existing forgery localization methods suffer from exploring frequency-based forgery traces in the localization network. In this paper, we observe that multi-frequency spectrum information is effective for identifying tampered regions. To this end, a novel Multi-Spectral Class Center Network (MSCCNet) is proposed for face manipulation detection and localization. Specifically, we design a Multi-Spectral Class Center (MSCC) module to learn more generalizable and multi-frequency features. Based on the features of different frequency bands, the MSCC module collects multi-spectral class centers and computes pixel-to-class relations. Applying multi-spectral class-level representations suppresses the semantic information of the visual concepts which is insensitive to manipulated regions of forgery images. Furthermore, we propose a Multi-level Features Aggregation (MFA) module to employ more low-level forgery artifacts and structural textures. Meanwhile, we conduct a comprehensive localization benchmark based on pixel-level FF++ and Dolos datasets. Experimental results quantitatively and qualitatively demonstrate the effectiveness and superiority of the proposed MSCCNet. We expect this work to inspire more studies on pixel-level face manipulation localization. The codes are available (https://github.com/miaoct/MSCCNet).

📄 PDF Abstract BibTeX arXiv:2305.10794

Code (1)

miaoct/msccnet 공식 구현 pytorch

Tasks

Face Swapping

Similar Papers 제목 키워드 기반

Spectral-Spatial Feature Extraction and Classification by ANN Supervised with Center Loss in Hyperspectral Imagery

2017-11-20 · Alan J. X. Guo, Fei Zhu

In this paper, we propose a spectral-spatial feature extraction and classification framework based on artificial neuron network (ANN) in the context of hyperspectral imagery. With limited labeled samples, only spectral i…

Face RecognitionGeneral Classification

Hyperspectral Image Classification via Efficient Global Spectral Supertoken Clustering

2026-04-30 · Peifu Liu, Tingfa Xu, Jie Wang, Huan Chen 외 arxiv

Hyperspectral image classification demands spatially coherent predictions and precise boundary delineation. Yet prevailing superpixel-based methods face an inherent contradiction: clustering aggregates similar pixels int…

Hyperspectral Image Classification

Hyperspectral image classification using spectral-spatial LSTMs

2018-08-20 · Feng Zhou, Renlong Hang, Qingshan Liu, Xiaotong Yuan

In this paper, we propose a hyperspectral image (HSI) classification method using spectral-spatial long short term memory (LSTM) networks. Specifically, for each pixel, we feed its spectral values in different channels i…

ClassificationGeneral ClassificationHyperspectral Image Classificationimage-classification+1

From Autoencoders to CycleGAN: Robust Unpaired Face Manipulation via Adversarial Learning

2025-09-15 · Collin Guo, Yi Qian arxiv

Human face synthesis and manipulation are increasingly important in entertainment and AI, with a growing demand for highly realistic, identity-preserving images even when only unpaired, unaligned datasets are available. …

Multispectral Palmprint Recognition Using a Hybrid Feature

2011-12-27 · Sina Akbari Mistani, Shervin Minaee, Emad Fatemizadeh

Personal identification problem has been a major field of research in recent years. Biometrics-based technologies that exploit fingerprints, iris, face, voice and palmprints, have been in the center of attention to solve…