Copertina

Leveraging Failed Samples: A Few-Shot and Training-Free Framework for Generalized Deepfake Detection

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Yao, Shibo, Tao, Renshuai, Zheng, Xiaolong, Liang, Chao, Zhang, Chunjie
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Leveraging Unlabeled Data from Unknown Sources via Dual-Path Guidance for Deepfake Face Detection
di: Yang, Zhiqiang, et al.
Pubblicazione: (2025)

C2P-CLIP: Injecting Category Common Prompt in CLIP to Enhance Generalization in Deepfake Detection
di: Tan, Chuangchuang, et al.
Pubblicazione: (2024)

ODDN: Addressing Unpaired Data Challenges in Open-World Deepfake Detection on Online Social Networks
di: Tao, Renshuai, et al.
Pubblicazione: (2024)

Scaling Up AI-Generated Image Detection with Generator-Aware Prototypes
di: Qin, Ziheng, et al.
Pubblicazione: (2025)

SWIFT: Sliding Window Reconstruction for Few-Shot Training-Free Generated Video Attribution
di: Wang, Chao, et al.
Pubblicazione: (2026)

Hypergraph-Enhanced Training-Free and Language-Free Few-Shot Anomaly Detection
di: Xie, Guohuan, et al.
Pubblicazione: (2026)

AnomalyAgent: Training-Free Agentic Models for Zero-/Few-Shot Anomaly Detection
di: Zhang, Yi, et al.
Pubblicazione: (2026)

PVLM: Parsing-Aware Vision Language Model with Dynamic Contrastive Learning for Zero-Shot Deepfake Attribution
di: Zhang, Yaning, et al.
Pubblicazione: (2025)

PAD-F: Prior-Aware Debiasing Framework for Long-Tailed X-ray Prohibited Item Detection
di: Wang, Haoyu, et al.
Pubblicazione: (2024)

Data-Independent Operator: A Training-Free Artifact Representation Extractor for Generalizable Deepfake Detection
di: Tan, Chuangchuang, et al.
Pubblicazione: (2024)

Generalization-Enhanced Few-Shot Object Detection in Remote Sensing
di: Lin, Hui, et al.
Pubblicazione: (2025)

Generalized Few-Shot Out-of-Distribution Detection
di: Li, Pinxuan, et al.
Pubblicazione: (2025)

LAB-Det: Language as a Domain-Invariant Bridge for Training-Free One-Shot Domain Generalization in Object Detection
di: Zhang, Xu, et al.
Pubblicazione: (2026)

Beyond Visual Cues: Leveraging General Semantics as Support for Few-Shot Segmentation
di: Wang, Jin, et al.
Pubblicazione: (2025)

GazeCLIP: Gaze-Guided CLIP with Adaptive-Enhanced Fine-Grained Language Prompt for Deepfake Attribution and Detection
di: Zhang, Yaning, et al.
Pubblicazione: (2026)

ForenX: Towards Explainable AI-Generated Image Detection with Multimodal Large Language Models
di: Tan, Chuangchuang, et al.
Pubblicazione: (2025)

Leveraging Bottom-Up and Top-Down Attention for Few-Shot Object Detection
di: Chen, Xianyu, et al.
Pubblicazione: (2020)

SMILe: Leveraging Submodular Mutual Information For Robust Few-Shot Object Detection
di: Majee, Anay, et al.
Pubblicazione: (2024)

Semantic Visual Anomaly Detection and Reasoning in AI-Generated Images
di: Tan, Chuangchuang, et al.
Pubblicazione: (2025)

BGM: Background Mixup for X-ray Prohibited Items Detection
di: Liu, Weizhe, et al.
Pubblicazione: (2024)

Towards Generalized Few-Shot Open-Set Object Detection
di: Su, Binyi, et al.
Pubblicazione: (2022)

Cross-Modal Prototype Alignment and Mixing for Training-Free Few-Shot Classification
di: Goswami, Dipam, et al.
Pubblicazione: (2026)

Training-Free Multimodal Deepfake Detection via Graph Reasoning
di: Liu, Yuxin, et al.
Pubblicazione: (2025)

LampMark: Proactive Deepfake Detection via Training-Free Landmark Perceptual Watermarks
di: Wang, Tianyi, et al.
Pubblicazione: (2024)

Taming Generative Synthetic Data for X-ray Prohibited Item Detection
di: Sun, Jialong, et al.
Pubblicazione: (2025)

SubspaceAD: Training-Free Few-Shot Anomaly Detection via Subspace Modeling
di: Lendering, Camile, et al.
Pubblicazione: (2026)

Deepfake Generation and Detection: A Benchmark and Survey
di: Pei, Gan, et al.
Pubblicazione: (2024)

PromptAD: Learning Prompts with only Normal Samples for Few-Shot Anomaly Detection
di: Li, Xiaofan, et al.
Pubblicazione: (2024)

Pay Less Attention to Deceptive Artifacts: Robust Detection of Compressed Deepfakes on Online Social Networks
di: Li, Manyi, et al.
Pubblicazione: (2025)

Text and Image Are Mutually Beneficial: Enhancing Training-Free Few-Shot Classification with CLIP
di: Li, Yayuan, et al.
Pubblicazione: (2024)

Patch-Discontinuity Mining for Generalized Deepfake Detection
di: Yuan, Huanhuan, et al.
Pubblicazione: (2025)

LoRA-Composer: Leveraging Low-Rank Adaptation for Multi-Concept Customization in Training-Free Diffusion Models
di: Yang, Yang, et al.
Pubblicazione: (2024)

Background Prompt for Few-Shot Out-of-Distribution Detection
di: Cai, Songyue, et al.
Pubblicazione: (2025)

CP-VoteNet: Contrastive Prototypical VoteNet for Few-Shot Point Cloud Object Detection
di: Li, Xuejing, et al.
Pubblicazione: (2024)

SAM-IF: Leveraging SAM for Incremental Few-Shot Instance Segmentation
di: Zhou, Xudong, et al.
Pubblicazione: (2024)

Few-Shot Learner Generalizes Across AI-Generated Image Detection
di: Wu, Shiyu, et al.
Pubblicazione: (2025)

Local-Prompt: Extensible Local Prompts for Few-Shot Out-of-Distribution Detection
di: Zeng, Fanhu, et al.
Pubblicazione: (2024)

Dual-view X-ray Detection: Can AI Detect Prohibited Items from Dual-view X-ray Images like Humans?
di: Tao, Renshuai, et al.
Pubblicazione: (2024)

Few-Shot Adaptation of Training-Free Foundation Model for 3D Medical Image Segmentation
di: He, Xingxin, et al.
Pubblicazione: (2025)

Breaking Forgetting: Training-Free Few-Shot Class-Incremental Learning via Conditional Diffusion
di: Kang, Haidong, et al.
Pubblicazione: (2025)