| description |
|---|
Deep learning papers notes sharing |
骨干网络，多为图像分类的网络。
- Attention Is All You Need
- EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- Multi-Dimensional Model Compression of Vision Transformer
- Deep Residual Learning for Image Recognition
- Generative Adversarial Networks
图像篡改检测定位
- ObjectFormer for Image Manipulation Detection and Localization
- TransForensics: Image Forgery Localization with Dense Self-Attention
- Generate, Segment, and Refine: Towards Generic Manipulation Segmentation
- M2TR: Multi-modal Multi-scale Transformers for Deepfake Detection
- PSCC-Net: Progressive Spatio-Channel Correlation Network for Image Manipulation Detection and Localization
- Image manipulation detection by multiple tampering traces and edge artifact enhancement
- MSTA-Net: Forgery Detection by Generating Manipulation Trace Based on Multi-Scale Self-Texture Attention
- Learning to localize image forgery using end-to-end attention network
- MVSS-Net: Multi-View Multi-Scale Supervised Networks for Image Manipulation Detection
- Self-supervised Domain Adaptation for Forgery Localization of JPEG Compressed Images
- Image Tampering Localization Using a Dense Fully Convolutional Network
- MSMG-Net: Multi-scale Multi-grained Supervised Metworks for Multi-task Image Manipulation Detection and Localization
- Towards JPEG-Resistant Image Forgery Detection and Localization Via Self-Supervised Domain Adaptation
- ESRNet: Efficient Search and Recognition Network for Image Manipulation Detection
- LSTM and encoder–decoder architecture for detection of image forgeries
图像的拼接篡改检测定位
- ****Multi-Task SE-Network for Image Splicing Localization
- CAT-Net: Compression Artifact Tracing Network for Detection and Localization of Image Splicing
- Fighting Fake News: Image Splice Detection via Learned Self-Consistency
- Image splicing forgery detection by combining synthetic adversarial networks and hybrid dense U-net based on multiple spaces
- SISL:Self-Supervised Image Signature Learning for Splicing Detection & Localization
- Image Splicing Detection, Localization and Attribution via JPEG Primary Quantization Matrix Estimation and Clustering
- Adversarial Learning for Constrained Image Splicing Detection and Localization Based on Atrous Convolution
- Multiple Image Splicing Dataset (MISD): A Dataset for Multiple Splicing
- ET: Edge-Enhanced Transformer for Image Splicing Detection
图像协调化
- Harmonizer: Learning to Perform White-Box Image and Video Harmonization
- Image Harmonization with Transformer
- Image Harmonization with Region-wise Contrastive Learning
- Spatial-Separated Curve Rendering Network for Efficient and High-Resolution Image Harmonization
- SSH: A Self-Supervised Framework for Image Harmonization
- Toward Realistic Image Compositing with Adversarial Learning
人脸篡改，以及检测问题
- MC-LCR: Multi-modal contrastive classification by locally correlated representations for effective face forgery detection
- Multi-Scale Wavelet Transformer for Face Forgery Detection
- SSTNet: Detecting Manipulated Faces Through Spatial, Steganalysis and Temporal Features
- Portrait shadow manipulation
复制移动篡改定位问题
- DOA-GAN: Dual-Order Attentive Generative Adversarial Network for Image Copy-Move Forgery Detection and Localization
- Two-Stage Copy-Move Forgery Detection with Self Deep Matching and Proposal SuperGlue
- A Serial Image Copy-Move Forgery Localization Scheme With Source/Target Distinguishment
- QDL-CMFD: A Quality-independent and deep Learning-based Copy-Move image forgery detection method
- BusterNet: Detecting Copy-Move Image Forgery with Source/Target Localization
特征匹配，图像匹配问题。
目标检测，包括伪装物体目标检测和突出目标检测，COD以及SOD。
- Zoom In and Out: A Mixed-scale Triplet Network for Camouflaged Object Detection
- OTA: Optimal Transport Assignment for Object Detection\