Computer Vision
Computer Vision
2024
2023
2021
- PixMatch簡介 - Unsupervised Domain Adaptation via Pixelwise Consistency Training
- Pixel2style2pixel(psp)簡介 - Encoding in Style a StyleGAN Encoder for Image-to-Image Translation
- YolactEdge簡介 - Real-time Instance Segmentation on the Edge
- 使用 Unet 將動漫圖片轉為素描
- 使用 StarGAN 轉換動漫人物的髮色
- 用於 GAN 生成之動漫圖片資料集
2020
- CUT簡介 - Contrastive Learning for Unpaired Image-to-Image Translation
- NICE-GAN簡介 - Reusing Discriminators for Encoding Towards Unsupervised Image-to-Image Translation
- 偵測視線目標簡介 - Detecting Attended Visual Targets in Video
- SSTDA簡介 - Action Segmentation with Joint Self-Supervised Temporal Domain Adaptation
2019
- 簡介 - Domain Bridge for Unpaired Image-to-Image Translation and Unsupervised Domain Adaptation
- Guided-pix2pix 簡介 - Guided Image-to-Image Translation with Bi-Directional Feature Transformation
- Tf-KD 簡介 - Revisit Knowledge Distillation a Teacher-free Framework
- Anchor Tasks 簡介 - Anchor Tasks Inexpensive, Shared, and Aligned Tasks for Domain Adaptation
- 簡介 - Regularizing Deep Networks by Modeling and Predicting Label Structure
- IBN-Net簡介 - Two at Once Enhancing Learning and Generalization Capacities via IBN-Net
- CACTUs簡介 - Unsupervised Learning via Meta-Learning
- OSNet簡介 - Omni-Scale Feature Learning for Person Re-Identification
- DEC簡介 - Unsupervised Deep Embedding for Clustering Analysis
- BTDA簡介 - Blending-target Domain Adaptation by Adversarial Meta-Adaptation Networks
- 簡介 - Instance Segmentation by Jointly Optimizing Spatial Embeddings and Clustering Bandwidth
- CRAFT簡介 - Character Region Awareness for Text Detection
- KASE簡介 - Known-class Aware Self-ensemble for Open Set Domain Adaptation
- Self-ensembling DA簡介 - Self-ensembling for visual domain adaptation
- 簡介 - Open Set Domain Adaptation by Backpropagation
- BDL簡介 - Bidirectional Learning for Domain Adaptation of Semantic Segmentation
- CLAN簡介 - Taking A Closer Look at Domain Shift Category-level Adversaries for Semantics Consistent Domain Adaptation
- DLOW簡介 - Domain Flow for Adaptation and Generalization
- YOLACT簡介 - Real-time Instance Segmentation
- HRNet 簡介 - Deep High-Resolution Representation Learning for Human Pose Estimation
- 簡介 - Structured Knowledge Distillation for Semantic Segmentation
- Image-level lower-count(ILC)簡介 - Object Counting and Instance Segmentation with Image-level Supervision
- DANet簡介 - Dual Attention Network for Scene Segmentation
- SC-FEGAN人臉圖像修復任務簡介 - Face Editing Generative Adversarial Network with User's Sketch and Color
- GeoGAN簡介 - Instance-level Facial Attributes Transfer with Geometry-Aware Flow
- OCNet語意分割模型簡介 - Object Context Network for Scene Parsing
2018
- InstaGAN簡介 - Instance-aware Image-to-Image Translation
- CoordConv簡介 - An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solution
- ST-GAN簡介 - Spatial Transformer Generative Adversarial Networks for Image Compositing
- TADA簡介 - Transferable Attention for Domain Adaptation
- PADA簡介 - Partial Adversarial Domain Adaptation
- GAN Dissection簡介 - Visualizing and Understanding Generative Adversarial Networks
- M2Det簡介 - A Single-Shot Object Detector based on Multi-Level Feature Pyramid Network
- CFENet簡介 - An Accurate and Efficient Single-Shot Object Detector for Autonomous Driving
- vid2vid簡介 - Video-to-Video Synthesis
- BigGAN簡介 - Large Scale GAN Training for High Fidelity Natural Image Synthesis
- SN-GAN簡介 - Spectral Normalization for Generative Adversarial Networks
- Deep image prior 簡介 - 不需資料集即可使用深度學習進行圖像修復/去雜訊等任務
- GAM簡介 - Domain transfer through deep activation matching
- Gated Convolution 圖像修復任務 Deepfillv2 - Free-Form Image Inpainting with Gated Convolution
- Partial Convolution 圖像修復任務PConv簡介 - Image Inpainting for Irregular Holes Using Partial Convolutions
- CBST簡介 - Unsupervised Domain Adaptation for Semantic Segmentation via Class-Balanced Self-Training
- 淘寶網的人物提取論文簡介 - Semantic Human Matting
- Look into Person簡介 - Look into Person Self-supervised Structure-sensitive Learning and A New Benchmark for Human Parsing
- pix2pixHD簡介 - High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs
- SPG簡介 - Self-produced Guidance for Weakly-supervised Object Localization
- Effective Use of Synthetic Data for Urban Scene Semantic Segmentation簡介
- Structure Inference Net簡介 - Object Detection Using Scene-Level Context and Instance-Level Relationships
- 圖片Domain轉換 - Domain Stylization- A Strong, Simple Baseline for Synthetic to Real Image Domain Adaptation
- 相片風格轉換 - A Closed-form Solution to Photorealistic Image Stylization簡介
- Synthesizing Images of Humans in Unseen Poses簡介
- ConvLSTM簡介 - Convolutional LSTM Network - A Machine Learning Approach for Precipitation Nowcasting
- Attentive-GAN簡介 - Attentive Generative Adversarial Network for Raindrop Removal from A Single Image
- AC-GAN簡介 - Conditional Image Synthesis With Auxiliary Classifier GANs
- Transferring GANs簡介 - Transferring GANs generating images from limited data
- FCAN簡介 - Fully Convolutional Adaptation Networks for Semantic Segmentation
- AdaptSegNet簡介 - Learning to Adapt Structured Output Space for Semantic Segmentation, CVPR 2018 (spotlight)
- SA-GAN 介紹 - Self-Attention Generative Adversarial Networks
- MSDNet 介紹 - Multi-Scale Dense Networks for Resource Efficient Image Classification
- Grad-CAM 介紹 - Grad-CAM:Visual Explanations from Deep Networks via Gradient-based Localization
- cGANs with projection介紹
- MUNIT 介紹 - Multimodal Unsupervised Image-to-Image Translation
- UNIT 介紹 - Unsupervised Image-to-Image Translation