Imagen de Portada

DGS-Net: Distillation-Guided Gradient Surgery for CLIP Fine-Tuning in AI-Generated Image Detection

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Yan, Jiazhen, Li, Ziqiang, Wang, Fan, Wang, Boyu, He, Ziwen, Fu, Zhangjie
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

NS-Net: Decoupling CLIP Semantic Information through NULL-Space for Generalizable AI-Generated Image Detection
por: Yan, Jiazhen, et al.
Publicado: (2025)

Dual Frequency Branch Framework with Reconstructed Sliding Windows Attention for AI-Generated Image Detection
por: Yan, Jiazhen, et al.
Publicado: (2025)

How Noise Benefits AI-generated Image Detection
por: Li, Ziqiang, et al.
Publicado: (2025)

Is Artificial Intelligence Generated Image Detection a Solved Problem?
por: Li, Ziqiang, et al.
Publicado: (2025)

Low-rank Orthogonal Subspace Intervention for Generalizable Face Forgery Detection
por: Wang, Chi, et al.
Publicado: (2026)

Generalizable Deepfake Detection Based on Forgery-aware Layer Masking and Multi-artifact Subspace Decomposition
por: Zhang, Xiang, et al.
Publicado: (2026)

MoCLIP: Motion-Aware Fine-Tuning and Distillation of CLIP for Human Motion Generation
por: Maldonado, Gabriel, et al.
Publicado: (2025)

Breaking the Resolution Barrier: Arbitrary-resolution Deep Image Steganography Framework
por: Hu, Xinjue, et al.
Publicado: (2026)

CLIP-KD: An Empirical Study of CLIP Model Distillation
por: Yang, Chuanguang, et al.
Publicado: (2023)

Scaling Exposes the Trigger: Input-Level Backdoor Detection in Text-to-Image Diffusion Models via Cross-Attention Scaling
por: Li, Zida, et al.
Publicado: (2026)

Distilled-3DGS:Distilled 3D Gaussian Splatting
por: Xiang, Lintao, et al.
Publicado: (2025)

Image-to-Brain Signal Generation for Visual Prosthesis with CLIP Guided Multimodal Diffusion Models
por: Xu, Ganxi, et al.
Publicado: (2025)

CLIP-Flow: A Universal Discriminator for AI-Generated Images Inspired by Anomaly Detection
por: Yuan, Zhipeng, et al.
Publicado: (2025)

CLIP-AGIQA: Boosting the Performance of AI-Generated Image Quality Assessment with CLIP
por: Tang, Zhenchen, et al.
Publicado: (2024)

Detecting AI-Generated Images via CLIP
por: Moskowitz, A. G., et al.
Publicado: (2024)

A Comprehensive Survey on Visual Concept Mining in Text-to-image Diffusion Models
por: Li, Ziqiang, et al.
Publicado: (2025)

Relational Diffusion Distillation for Efficient Image Generation
por: Feng, Weilun, et al.
Publicado: (2024)

IPAD-CLIP: Teaching CLIP to Detect Image Local Perceptual Artifacts
por: Wang, Juan, et al.
Publicado: (2026)

Noise-Informed Diffusion-Generated Image Detection with Anomaly Attention
por: Guan, Weinan, et al.
Publicado: (2025)

Low-light Image Enhancement via CLIP-Fourier Guided Wavelet Diffusion
por: Xue, Minglong, et al.
Publicado: (2024)

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

Few-Step Distillation for Text-to-Image Generation: A Practical Guide
por: Pu, Yifan, et al.
Publicado: (2025)

CLIP-Guided Source-Free Object Detection in Aerial Images
por: Liu, Nanqing, et al.
Publicado: (2024)

Contrast-Aware Calibration for Fine-Tuned CLIP: Leveraging Image-Text Alignment
por: Lv, Song-Lin, et al.
Publicado: (2025)

Raising the Bar of AI-generated Image Detection with CLIP
por: Cozzolino, Davide, et al.
Publicado: (2023)

LOTA: Bit-Planes Guided AI-Generated Image Detection
por: Wang, Hongsong, et al.
Publicado: (2025)

CLIP-RD: Relative Distillation for Efficient CLIP Knowledge Distillation
por: Chung, Jeannie, et al.
Publicado: (2026)

Incremental Object Detection with CLIP
por: Huang, Ziyue, et al.
Publicado: (2023)

Ref-DGS: Reflective Dual Gaussian Splatting
por: Fan, Ningjing, et al.
Publicado: (2026)

Skeleton2Stage: Reward-Guided Fine-Tuning for Physically Plausible Dance Generation
por: Jia, Jidong, et al.
Publicado: (2026)

Beyond Hallucinations: A Multimodal-Guided Task-Aware Generative Image Compression for Ultra-Low Bitrate
por: Wang, Kaile, et al.
Publicado: (2025)

Beyond Text Prompts: Precise Concept Erasure through Text-Image Collaboration
por: Li, Jun, et al.
Publicado: (2026)

Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields
por: Zhou, Shijie, et al.
Publicado: (2023)

MediCLIP: Adapting CLIP for Few-shot Medical Image Anomaly Detection
por: Zhang, Ximiao, et al.
Publicado: (2024)

Advancing Compositional Awareness in CLIP with Efficient Fine-Tuning
por: Peleg, Amit, et al.
Publicado: (2025)

CausalCLIP: Causally-Informed Feature Disentanglement and Filtering for Generalizable Detection of Generated Images
por: Liu, Bo, et al.
Publicado: (2025)

UB-FineNet: Urban Building Fine-grained Classification Network for Open-access Satellite Images
por: He, Zhiyi, et al.
Publicado: (2024)

Exploring the Adversarial Robustness of CLIP for AI-generated Image Detection
por: De Rosa, Vincenzo, et al.
Publicado: (2024)

FriendNet: Detection-Friendly Dehazing Network
por: Fan, Yihua, et al.
Publicado: (2024)

CLIP-MUSED: CLIP-Guided Multi-Subject Visual Neural Information Semantic Decoding
por: Zhou, Qiongyi, et al.
Publicado: (2024)